Spaces:
Runtime error
Runtime error
Commit
Β·
31e192b
0
Parent(s):
Duplicate from Abhilashvj/computer-vision-backend
Browse files- .env +2 -0
- .gitattributes +36 -0
- Dockerfile +52 -0
- Licenseplate_model.pt +3 -0
- README.md +12 -0
- app.py +652 -0
- best.pt +3 -0
- best_classifer_model.pt +3 -0
- deploy.prototxt +1789 -0
- download_models.py +56 -0
- requirements.txt +60 -0
- res10_300x300_ssd_iter_140000_fp16.caffemodel +3 -0
- run_cmds.txt +5 -0
.env
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
PINECONE_KEY=696a2b15-b4c0-4581-af5d-2d52d0198950
|
2 |
+
PINECONE_ENV=us-central1-gcp
|
.gitattributes
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
res10_300x300_ssd_iter_140000_fp16.caffemodel filter=lfs diff=lfs merge=lfs -text
|
Dockerfile
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# backend/Dockerfile
|
2 |
+
|
3 |
+
FROM python:3.10.1-slim
|
4 |
+
|
5 |
+
WORKDIR /app
|
6 |
+
|
7 |
+
RUN apt-get update
|
8 |
+
RUN apt-get install git \
|
9 |
+
'ffmpeg'\
|
10 |
+
'libsm6'\
|
11 |
+
'libxext6' -y
|
12 |
+
|
13 |
+
COPY requirements.txt .
|
14 |
+
RUN pip install -r requirements.txt
|
15 |
+
# Clone Real-ESRGAN and enter the Real-ESRGAN
|
16 |
+
# RUN git clone https://github.com/xinntao/Real-ESRGAN.git
|
17 |
+
# RUN cd Real-ESRGAN
|
18 |
+
# # Set up the environment
|
19 |
+
# RUN pip install basicsr
|
20 |
+
# RUN pip install facexlib
|
21 |
+
# RUN pip install gfpgan
|
22 |
+
# RUN pip install -r requirements.txt
|
23 |
+
# RUN python setup.py develop
|
24 |
+
|
25 |
+
# Set up a new user named "user" with user ID 1000
|
26 |
+
RUN useradd -m -u 1000 user
|
27 |
+
|
28 |
+
# Switch to the "user" user
|
29 |
+
USER user
|
30 |
+
|
31 |
+
# Set home to the user's home directory
|
32 |
+
ENV HOME=/home/user \
|
33 |
+
PATH=/home/user/.local/bin:$PATH
|
34 |
+
|
35 |
+
# Set the working directory to the user's home directory
|
36 |
+
WORKDIR $HOME/app
|
37 |
+
|
38 |
+
|
39 |
+
|
40 |
+
# Copy the current directory contents into the container at $HOME/app setting the owner to the user
|
41 |
+
COPY --chown=user . $HOME/app
|
42 |
+
# EXPOSE 8000
|
43 |
+
# RUN python download_models.py
|
44 |
+
# CMD ["python", "app.py"]
|
45 |
+
# Start app
|
46 |
+
# ENTRYPOINT ["gunicorn", "-c", "gunicorn.py", "-k", "uvicorn.workers.UvicornWorker", "app:app"]
|
47 |
+
|
48 |
+
# RUN python download_models.py
|
49 |
+
# CMD ["python", "app.py"]
|
50 |
+
|
51 |
+
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]
|
52 |
+
|
Licenseplate_model.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c9a080781aa7ff722968c944a702983af8a452753edd5ba20719d42349ec7bd
|
3 |
+
size 71780037
|
README.md
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
title: Computer Vision Backend
|
3 |
+
emoji: π
|
4 |
+
colorFrom: red
|
5 |
+
colorTo: indigo
|
6 |
+
sdk: docker
|
7 |
+
pinned: false
|
8 |
+
license: mit
|
9 |
+
duplicated_from: Abhilashvj/computer-vision-backend
|
10 |
+
---
|
11 |
+
|
12 |
+
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
app.py
ADDED
@@ -0,0 +1,652 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import cv2
|
2 |
+
import numpy as np
|
3 |
+
import argparse
|
4 |
+
import base64
|
5 |
+
import io
|
6 |
+
import os
|
7 |
+
import re
|
8 |
+
import sys
|
9 |
+
import traceback
|
10 |
+
import uuid
|
11 |
+
from typing import List, Optional
|
12 |
+
from PIL import ImageEnhance
|
13 |
+
import traceback
|
14 |
+
import cv2
|
15 |
+
import numpy as np
|
16 |
+
import pandas as pd
|
17 |
+
import pinecone
|
18 |
+
import pyiqa
|
19 |
+
import timm
|
20 |
+
import torch
|
21 |
+
import uvicorn
|
22 |
+
from dotenv import load_dotenv
|
23 |
+
from fastapi import FastAPI, File, Form, HTTPException, UploadFile
|
24 |
+
from PIL import Image
|
25 |
+
from pydantic import BaseModel
|
26 |
+
from sentence_transformers import SentenceTransformer, util
|
27 |
+
from transformers import (
|
28 |
+
AutoFeatureExtractor,
|
29 |
+
AutoModel,
|
30 |
+
DonutProcessor,
|
31 |
+
VisionEncoderDecoderModel,
|
32 |
+
)
|
33 |
+
|
34 |
+
load_dotenv()
|
35 |
+
pinecone.init(api_key=os.getenv("PINECONE_KEY"), environment=os.getenv("PINECONE_ENV"))
|
36 |
+
DETECTION_URL = "/object-detection/"
|
37 |
+
CLASSIFICATION_URL = "/object-classification/"
|
38 |
+
QUALITY_ASSESSMENT_URL = "/quality-assessment/"
|
39 |
+
FACE_URL = "/face-anonymization/"
|
40 |
+
LICENCE_URL = "/licenceplate-anonymization/"
|
41 |
+
DOCUMENT_QA = "/document-qa/"
|
42 |
+
IMAGE_SIMILARITY_DEMO = "/find-similar-image/"
|
43 |
+
IMAGE_SIMILARITY_PINECONE_DEMO = "/find-similar-image-pinecone/"
|
44 |
+
INDEX_NAME = "imagesearch-demo"
|
45 |
+
INDEX_DIMENSION = 512
|
46 |
+
TMP_DIR = "tmp"
|
47 |
+
|
48 |
+
|
49 |
+
|
50 |
+
def enhance_image(pil_image):
|
51 |
+
# Convert PIL Image to OpenCV format
|
52 |
+
open_cv_image = np.array(pil_image)
|
53 |
+
# Convert RGB to BGR
|
54 |
+
open_cv_image = open_cv_image[:, :, ::-1].copy()
|
55 |
+
|
56 |
+
# Convert to grayscale
|
57 |
+
gray = cv2.cvtColor(open_cv_image, cv2.COLOR_BGR2GRAY)
|
58 |
+
|
59 |
+
# Histogram equalization
|
60 |
+
equ = cv2.equalizeHist(gray)
|
61 |
+
|
62 |
+
# Adaptive Histogram Equalization
|
63 |
+
clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8,8))
|
64 |
+
adaptive_hist_eq = clahe.apply(gray)
|
65 |
+
|
66 |
+
# Gaussian Blurring
|
67 |
+
gaussian_blurred = cv2.GaussianBlur(adaptive_hist_eq, (5,5), 0)
|
68 |
+
|
69 |
+
# Noise reduction
|
70 |
+
denoised = cv2.medianBlur(gaussian_blurred, 3)
|
71 |
+
|
72 |
+
# Brightness & Contrast adjustment
|
73 |
+
lab = cv2.cvtColor(open_cv_image, cv2.COLOR_BGR2Lab)
|
74 |
+
l, a, b = cv2.split(lab)
|
75 |
+
cl = clahe.apply(l)
|
76 |
+
limg = cv2.merge((cl, a, b))
|
77 |
+
enhanced_image = cv2.cvtColor(limg, cv2.COLOR_Lab2BGR)
|
78 |
+
|
79 |
+
# Convert back to PIL Image
|
80 |
+
enhanced_pil_image = Image.fromarray(cv2.cvtColor(enhanced_image, cv2.COLOR_BGR2RGB))
|
81 |
+
|
82 |
+
# IMAGE AUGMENTATION
|
83 |
+
# For demonstration purposes, let's do a simple brightness adjustment.
|
84 |
+
# In practice, choose the augmentations that suit your task.
|
85 |
+
enhancer = ImageEnhance.Brightness(enhanced_pil_image)
|
86 |
+
enhanced_pil_image = enhancer.enhance(1.2) # Brighten the image by 20%
|
87 |
+
|
88 |
+
return enhanced_pil_image
|
89 |
+
|
90 |
+
|
91 |
+
if INDEX_NAME not in pinecone.list_indexes():
|
92 |
+
pinecone.create_index(INDEX_NAME, dimension=512, metric='cosine')
|
93 |
+
|
94 |
+
print("Connecting to Pinecone Index")
|
95 |
+
index = pinecone.Index(INDEX_NAME)
|
96 |
+
|
97 |
+
|
98 |
+
device = "cuda" if torch.cuda.is_available() else "cpu"
|
99 |
+
|
100 |
+
os.makedirs(TMP_DIR, exist_ok=True)
|
101 |
+
|
102 |
+
licence_model = torch.hub.load(
|
103 |
+
"ultralytics/yolov5", "custom", path="Licenseplate_model.pt", device="cpu", force_reload=True
|
104 |
+
)
|
105 |
+
licence_model.cpu()
|
106 |
+
|
107 |
+
detector = cv2.dnn.DetectionModel(
|
108 |
+
"res10_300x300_ssd_iter_140000_fp16.caffemodel", "deploy.prototxt"
|
109 |
+
)
|
110 |
+
|
111 |
+
processor = DonutProcessor.from_pretrained("naver-clova-ix/donut-base-finetuned-docvqa")
|
112 |
+
doc_qa_model = VisionEncoderDecoderModel.from_pretrained(
|
113 |
+
"naver-clova-ix/donut-base-finetuned-docvqa"
|
114 |
+
)
|
115 |
+
|
116 |
+
device = "cuda" if torch.cuda.is_available() else "cpu"
|
117 |
+
doc_qa_model.to(device)
|
118 |
+
|
119 |
+
|
120 |
+
os.makedirs(TMP_DIR, exist_ok=True)
|
121 |
+
|
122 |
+
model = torch.hub.load(
|
123 |
+
"ultralytics/yolov5", "custom", path="best.pt", device="cpu", force_reload=True
|
124 |
+
)
|
125 |
+
model.cpu()
|
126 |
+
|
127 |
+
classes = [
|
128 |
+
"gas-distribution-meter",
|
129 |
+
"gas-distribution-piping",
|
130 |
+
"gas-distribution-regulator",
|
131 |
+
"gas-distribution-valve",
|
132 |
+
]
|
133 |
+
|
134 |
+
class_to_idx = {
|
135 |
+
"gas-distribution-meter": 0,
|
136 |
+
"gas-distribution-piping": 1,
|
137 |
+
"gas-distribution-regulator": 2,
|
138 |
+
"gas-distribution-valve": 3,
|
139 |
+
}
|
140 |
+
|
141 |
+
idx_to_classes = {v: k for k, v in class_to_idx.items()}
|
142 |
+
modelname = "resnet50d"
|
143 |
+
model_weights = "best_classifer_model.pt"
|
144 |
+
num_classes = len(classes)
|
145 |
+
|
146 |
+
classifier_model = timm.create_model(
|
147 |
+
"resnet50d", pretrained=True, num_classes=num_classes, drop_path_rate=0.05
|
148 |
+
)
|
149 |
+
classifier_model.load_state_dict(
|
150 |
+
torch.load(model_weights, map_location=torch.device("cpu"))["model_state_dict"]
|
151 |
+
)
|
152 |
+
|
153 |
+
musiq_metric = pyiqa.create_metric("musiq-koniq", device=torch.device("cpu"))
|
154 |
+
image_sim_model = SentenceTransformer("clip-ViT-B-32")
|
155 |
+
|
156 |
+
|
157 |
+
# model_ckpt = "nateraw/vit-base-beans"
|
158 |
+
# extractor = AutoFeatureExtractor.from_pretrained(model_ckpt)
|
159 |
+
# image_sim_model = AutoModel.from_pretrained(model_ckpt)
|
160 |
+
|
161 |
+
|
162 |
+
app = FastAPI(title="CV Demos")
|
163 |
+
|
164 |
+
# Define the Response
|
165 |
+
class Prediction(BaseModel):
|
166 |
+
filename: str
|
167 |
+
contenttype: str
|
168 |
+
prediction: List[float] = []
|
169 |
+
|
170 |
+
|
171 |
+
# define response
|
172 |
+
@app.get("/")
|
173 |
+
def root_route():
|
174 |
+
return {"error": f"Use GET {DETECTION_URL} instead of the root route!"}
|
175 |
+
|
176 |
+
|
177 |
+
@app.post(
|
178 |
+
DETECTION_URL,
|
179 |
+
)
|
180 |
+
async def predict(file: UploadFile = File(...), quality_check: bool = False):
|
181 |
+
try:
|
182 |
+
extension = file.filename.split(".")[-1] in ("jpg", "jpeg", "png")
|
183 |
+
if not extension:
|
184 |
+
return "Image must be jpg or png format!"
|
185 |
+
# read image contain
|
186 |
+
contents = await file.read()
|
187 |
+
pil_image = Image.open(io.BytesIO(contents))
|
188 |
+
if quality_check:
|
189 |
+
print("RUNNING QUALITY CEHCK BEFORE OBJEFCT DETECTION!!!")
|
190 |
+
tmp_file = f"{TMP_DIR}/tmp.png"
|
191 |
+
pil_image.save(tmp_file)
|
192 |
+
score = musiq_metric(tmp_file)
|
193 |
+
if score < 50:
|
194 |
+
return {
|
195 |
+
"Error": "Image quality is not sufficient enough to be considered for object detection"
|
196 |
+
}
|
197 |
+
|
198 |
+
results = model(pil_image, size=640) # reduce size=320 for faster inference
|
199 |
+
return results.pandas().xyxy[0].to_json(orient="records")
|
200 |
+
except:
|
201 |
+
e = sys.exc_info()[1]
|
202 |
+
raise HTTPException(status_code=500, detail=str(e))
|
203 |
+
|
204 |
+
|
205 |
+
@app.post(CLASSIFICATION_URL)
|
206 |
+
async def classify(file: UploadFile = File(...)):
|
207 |
+
try:
|
208 |
+
extension = file.filename.split(".")[-1] in ("jpg", "jpeg", "png")
|
209 |
+
if not extension:
|
210 |
+
return "Image must be jpg or png format!"
|
211 |
+
# read image contain
|
212 |
+
contents = await file.read()
|
213 |
+
pil_image = Image.open(io.BytesIO(contents))
|
214 |
+
data_mean = (0.485, 0.456, 0.406)
|
215 |
+
data_std = (0.229, 0.224, 0.225)
|
216 |
+
image_size = (224, 224)
|
217 |
+
eval_transforms = timm.data.create_transform(
|
218 |
+
input_size=image_size, mean=data_mean, std=data_std
|
219 |
+
)
|
220 |
+
eval_transforms(pil_image).unsqueeze(dim=0).shape
|
221 |
+
classifier_model.eval()
|
222 |
+
print("RUNNING Image Classification!!!")
|
223 |
+
max_class_idx = np.argmax(
|
224 |
+
classifier_model(eval_transforms(pil_image).unsqueeze(dim=0)).detach().numpy()
|
225 |
+
)
|
226 |
+
predicted_class = idx_to_classes[max_class_idx]
|
227 |
+
print(f"Predicted Class idx: {max_class_idx} with name : {predicted_class}")
|
228 |
+
return {"object": predicted_class}
|
229 |
+
|
230 |
+
except:
|
231 |
+
e = sys.exc_info()[1]
|
232 |
+
raise HTTPException(status_code=500, detail=str(e))
|
233 |
+
|
234 |
+
|
235 |
+
@app.post(QUALITY_ASSESSMENT_URL)
|
236 |
+
async def quality_check(file: UploadFile = File(...)):
|
237 |
+
try:
|
238 |
+
extension = file.filename.split(".")[-1] in ("jpg", "jpeg", "png")
|
239 |
+
if not extension:
|
240 |
+
return "Image must be jpg or png format!"
|
241 |
+
# read image contain
|
242 |
+
contents = await file.read()
|
243 |
+
pil_image = Image.open(io.BytesIO(contents))
|
244 |
+
tmp_file = f"{TMP_DIR}/tmp.png"
|
245 |
+
pil_image.save(tmp_file)
|
246 |
+
score = musiq_metric(tmp_file).detach().numpy().tolist()
|
247 |
+
return {"score": score}
|
248 |
+
|
249 |
+
except:
|
250 |
+
e = sys.exc_info()[1]
|
251 |
+
raise HTTPException(status_code=500, detail=str(e))
|
252 |
+
|
253 |
+
|
254 |
+
def anonymize_simple(image, factor=3.0):
|
255 |
+
# automatically determine the size of the blurring kernel based
|
256 |
+
# on the spatial dimensions of the input image
|
257 |
+
(h, w) = image.shape[:2]
|
258 |
+
kW = int(w / factor)
|
259 |
+
kH = int(h / factor)
|
260 |
+
# ensure the width of the kernel is odd
|
261 |
+
if kW % 2 == 0:
|
262 |
+
kW -= 1
|
263 |
+
# ensure the height of the kernel is odd
|
264 |
+
if kH % 2 == 0:
|
265 |
+
kH -= 1
|
266 |
+
# apply a Gaussian blur to the input image using our computed
|
267 |
+
# kernel size
|
268 |
+
return cv2.GaussianBlur(image, (kW, kH), 0)
|
269 |
+
|
270 |
+
|
271 |
+
def anonymize_pixelate(image, blocks=3):
|
272 |
+
# divide the input image into NxN blocks
|
273 |
+
(h, w) = image.shape[:2]
|
274 |
+
xSteps = np.linspace(0, w, blocks + 1, dtype="int")
|
275 |
+
ySteps = np.linspace(0, h, blocks + 1, dtype="int")
|
276 |
+
# loop over the blocks in both the x and y direction
|
277 |
+
for i in range(1, len(ySteps)):
|
278 |
+
for j in range(1, len(xSteps)):
|
279 |
+
# compute the starting and ending (x, y)-coordinates
|
280 |
+
# for the current block
|
281 |
+
startX = xSteps[j - 1]
|
282 |
+
startY = ySteps[i - 1]
|
283 |
+
endX = xSteps[j]
|
284 |
+
endY = ySteps[i]
|
285 |
+
# extract the ROI using NumPy array slicing, compute the
|
286 |
+
# mean of the ROI, and then draw a rectangle with the
|
287 |
+
# mean RGB values over the ROI in the original image
|
288 |
+
roi = image[startY:endY, startX:endX]
|
289 |
+
(B, G, R) = [int(x) for x in cv2.mean(roi)[:3]]
|
290 |
+
cv2.rectangle(image, (startX, startY), (endX, endY), (B, G, R), -1)
|
291 |
+
# return the pixelated blurred image
|
292 |
+
return image
|
293 |
+
|
294 |
+
|
295 |
+
# define response
|
296 |
+
@app.get("/")
|
297 |
+
def root_route():
|
298 |
+
return {"error": f"Use GET {FACE_URL} or {LICENCE_URL} instead of the root route!"}
|
299 |
+
|
300 |
+
|
301 |
+
@app.post(
|
302 |
+
FACE_URL,
|
303 |
+
)
|
304 |
+
async def face_anonymize(
|
305 |
+
file: UploadFile = File(...), blur_type="simple", quality_check: bool = False
|
306 |
+
):
|
307 |
+
"""
|
308 |
+
https://pyimagesearch.com/2020/04/06/blur-and-anonymize-faces-with-opencv-and-python/
|
309 |
+
"""
|
310 |
+
try:
|
311 |
+
extension = file.filename.split(".")[-1] in ("jpg", "jpeg", "png")
|
312 |
+
if not extension:
|
313 |
+
return "Image must be jpg or png format!"
|
314 |
+
# read image contain
|
315 |
+
contents = await file.read()
|
316 |
+
pil_image = Image.open(io.BytesIO(contents)).convert("RGB")
|
317 |
+
detector = cv2.dnn.DetectionModel(
|
318 |
+
"res10_300x300_ssd_iter_140000_fp16.caffemodel", "deploy.prototxt"
|
319 |
+
)
|
320 |
+
open_cv_image = np.array(pil_image)
|
321 |
+
# Convert RGB to BGR
|
322 |
+
open_cv_image = open_cv_image[:, :, ::-1].copy()
|
323 |
+
(h, w) = open_cv_image.shape[:2]
|
324 |
+
# Getting the detections
|
325 |
+
detections = detector.detect(open_cv_image)
|
326 |
+
if len(detections[2]) > 0:
|
327 |
+
for face in detections[2]:
|
328 |
+
(x, y, w, h) = face.astype("int")
|
329 |
+
# extract the face ROI
|
330 |
+
|
331 |
+
face = open_cv_image[y : y + h, x : x + w]
|
332 |
+
if blur_type == "simple":
|
333 |
+
face = anonymize_simple(face)
|
334 |
+
else:
|
335 |
+
face = anonymize_pixelate(face)
|
336 |
+
open_cv_image[y : y + h, x : x + w] = face
|
337 |
+
|
338 |
+
_, encoded_img = cv2.imencode(".PNG", open_cv_image)
|
339 |
+
|
340 |
+
encoded_img = base64.b64encode(encoded_img)
|
341 |
+
return {
|
342 |
+
"filename": file.filename,
|
343 |
+
"dimensions": str(open_cv_image.shape),
|
344 |
+
"encoded_img": encoded_img,
|
345 |
+
}
|
346 |
+
except:
|
347 |
+
e = sys.exc_info()[1]
|
348 |
+
print(traceback.format_exc())
|
349 |
+
raise HTTPException(status_code=500, detail=str(e))
|
350 |
+
|
351 |
+
|
352 |
+
@app.post(LICENCE_URL)
|
353 |
+
async def licence_anonymize(file: UploadFile = File(...), blur_type="simple"):
|
354 |
+
"""https://www.kaggle.com/code/gowrishankarp/license-plate-detection-yolov5-pytesseract/notebook#Visualize"""
|
355 |
+
try:
|
356 |
+
extension = file.filename.split(".")[-1] in ("jpg", "jpeg", "png")
|
357 |
+
if not extension:
|
358 |
+
return "Image must be jpg or png format!"
|
359 |
+
# read image contain
|
360 |
+
contents = await file.read()
|
361 |
+
pil_image = Image.open(io.BytesIO(contents))
|
362 |
+
results = licence_model(pil_image, size=640) # reduce size=320 for faster inference
|
363 |
+
pil_image = pil_image.convert("RGB")
|
364 |
+
open_cv_image = np.array(pil_image)
|
365 |
+
open_cv_image = open_cv_image[:, :, ::-1].copy()
|
366 |
+
df = results.pandas().xyxy[0]
|
367 |
+
for i, row in df.iterrows():
|
368 |
+
xmin = int(row["xmin"])
|
369 |
+
ymin = int(row["ymin"])
|
370 |
+
xmax = int(row["xmax"])
|
371 |
+
ymax = int(row["ymax"])
|
372 |
+
licence = open_cv_image[ymin:ymax, xmin:xmax]
|
373 |
+
if blur_type == "simple":
|
374 |
+
licence = anonymize_simple(licence)
|
375 |
+
else:
|
376 |
+
licence = anonymize_pixelate(licence)
|
377 |
+
open_cv_image[ymin:ymax, xmin:xmax] = licence
|
378 |
+
|
379 |
+
_, encoded_img = cv2.imencode(".PNG", open_cv_image)
|
380 |
+
|
381 |
+
encoded_img = base64.b64encode(encoded_img)
|
382 |
+
return {
|
383 |
+
"filename": file.filename,
|
384 |
+
"dimensions": str(open_cv_image.shape),
|
385 |
+
"encoded_img": encoded_img,
|
386 |
+
}
|
387 |
+
|
388 |
+
except:
|
389 |
+
e = sys.exc_info()[1]
|
390 |
+
raise HTTPException(status_code=500, detail=str(e))
|
391 |
+
|
392 |
+
|
393 |
+
def process_document(image, question):
|
394 |
+
# prepare encoder inputs
|
395 |
+
pixel_values = processor(image, return_tensors="pt").pixel_values
|
396 |
+
|
397 |
+
# prepare decoder inputs
|
398 |
+
task_prompt = "<s_docvqa><s_question>{user_input}</s_question><s_answer>"
|
399 |
+
prompt = task_prompt.replace("{user_input}", question)
|
400 |
+
decoder_input_ids = processor.tokenizer(
|
401 |
+
prompt, add_special_tokens=False, return_tensors="pt"
|
402 |
+
).input_ids
|
403 |
+
|
404 |
+
# generate answer
|
405 |
+
outputs = doc_qa_model.generate(
|
406 |
+
pixel_values.to(device),
|
407 |
+
decoder_input_ids=decoder_input_ids.to(device),
|
408 |
+
max_length=doc_qa_model.decoder.config.max_position_embeddings,
|
409 |
+
early_stopping=True,
|
410 |
+
pad_token_id=processor.tokenizer.pad_token_id,
|
411 |
+
eos_token_id=processor.tokenizer.eos_token_id,
|
412 |
+
use_cache=True,
|
413 |
+
num_beams=1,
|
414 |
+
bad_words_ids=[[processor.tokenizer.unk_token_id]],
|
415 |
+
return_dict_in_generate=True,
|
416 |
+
)
|
417 |
+
|
418 |
+
# postprocess
|
419 |
+
sequence = processor.batch_decode(outputs.sequences)[0]
|
420 |
+
sequence = sequence.replace(processor.tokenizer.eos_token, "").replace(
|
421 |
+
processor.tokenizer.pad_token, ""
|
422 |
+
)
|
423 |
+
sequence = re.sub(r"<.*?>", "", sequence, count=1).strip() # remove first task start token
|
424 |
+
|
425 |
+
return processor.token2json(sequence)
|
426 |
+
|
427 |
+
|
428 |
+
@app.post(DOCUMENT_QA)
|
429 |
+
async def document_qa(question: str = Form(...), file: UploadFile = File(...)):
|
430 |
+
|
431 |
+
try:
|
432 |
+
extension = file.filename.split(".")[-1] in ("jpg", "jpeg", "png")
|
433 |
+
if not extension:
|
434 |
+
return "Image must be jpg or png format!"
|
435 |
+
# read image contain
|
436 |
+
contents = await file.read()
|
437 |
+
pil_image = Image.open(io.BytesIO(contents))
|
438 |
+
# tmp_file = f"{TMP_DIR}/tmp.png"
|
439 |
+
# pil_image.save(tmp_file)
|
440 |
+
# answer_git_large = generate_answer_git(git_processor_large, git_model_large, image, question)
|
441 |
+
|
442 |
+
answer = process_document(pil_image, question)["answer"]
|
443 |
+
|
444 |
+
return {"answer": answer}
|
445 |
+
|
446 |
+
except:
|
447 |
+
e = sys.exc_info()[1]
|
448 |
+
raise HTTPException(status_code=500, detail=str(e))
|
449 |
+
|
450 |
+
|
451 |
+
@app.post(IMAGE_SIMILARITY_DEMO)
|
452 |
+
async def image_search_local(
|
453 |
+
images_to_search: List[UploadFile], query_image: UploadFile = File(...), top_k: int = 5
|
454 |
+
):
|
455 |
+
print(
|
456 |
+
f"Recived images of length: {len(images_to_search)} needs to retrieve top k : {top_k} similar images as result"
|
457 |
+
)
|
458 |
+
try:
|
459 |
+
extension = query_image.filename.split(".")[-1] in ("jpg", "jpeg", "png")
|
460 |
+
search_images = []
|
461 |
+
search_filenames = []
|
462 |
+
print("Processing request...")
|
463 |
+
for image in images_to_search:
|
464 |
+
if image.filename.split(".")[-1] not in ("jpg", "jpeg", "png"):
|
465 |
+
return "Image must be jpg or png format!"
|
466 |
+
# read image contain
|
467 |
+
search_filenames.append(image.filename)
|
468 |
+
contents = await image.read()
|
469 |
+
search_images.append(Image.open(io.BytesIO(contents)))
|
470 |
+
print("Indexing images to search...")
|
471 |
+
|
472 |
+
corpus_embeddings = image_sim_model.encode(
|
473 |
+
search_images, convert_to_tensor=True, show_progress_bar=True
|
474 |
+
)
|
475 |
+
if not extension:
|
476 |
+
return "Image must be jpg or png format!"
|
477 |
+
# read image contain
|
478 |
+
contents = await query_image.read()
|
479 |
+
query_image = Image.open(io.BytesIO(contents))
|
480 |
+
print("Indexing query image...")
|
481 |
+
|
482 |
+
prompt_embedding = image_sim_model.encode(query_image, convert_to_tensor=True)
|
483 |
+
print("Searching query image...")
|
484 |
+
|
485 |
+
hits = util.semantic_search(prompt_embedding, corpus_embeddings, top_k=top_k)
|
486 |
+
# hits = pd.DataFrame(hits[0], columns=['corpus_id', 'score'])
|
487 |
+
# tmp_file = f"{TMP_DIR}/tmp.png"
|
488 |
+
# pil_image.save(tmp_file)
|
489 |
+
# answer_git_large = generate_answer_git(git_processor_large, git_model_large, image, question)
|
490 |
+
print("Creating the result..")
|
491 |
+
similar_images = []
|
492 |
+
print("hits ", hits)
|
493 |
+
for hit in hits[0]:
|
494 |
+
# print("Finding the image ")
|
495 |
+
# print("Type of images list ", type(search_images), "similar image id ", hit['corpus_id'])
|
496 |
+
open_cv_image = np.array(search_images[hit["corpus_id"]].convert("RGB"))[:, :, ::-1]
|
497 |
+
# print("cv2.imencode the image ")
|
498 |
+
_, encoded_img = cv2.imencode(".PNG", open_cv_image)
|
499 |
+
# print("base64 the image ")
|
500 |
+
encoded_img = base64.b64encode(encoded_img)
|
501 |
+
# print("Appending the image ")
|
502 |
+
similar_images.append(
|
503 |
+
{
|
504 |
+
"filename": search_filenames[hit["corpus_id"]],
|
505 |
+
"dimensions": str(open_cv_image.shape),
|
506 |
+
"score": hit["score"],
|
507 |
+
"encoded_img": encoded_img,
|
508 |
+
}
|
509 |
+
)
|
510 |
+
print("Sending result..")
|
511 |
+
|
512 |
+
return {"similar_images": similar_images}
|
513 |
+
|
514 |
+
except:
|
515 |
+
e = sys.exc_info()[1]
|
516 |
+
raise HTTPException(status_code=500, detail=str(e))
|
517 |
+
|
518 |
+
|
519 |
+
@app.post(IMAGE_SIMILARITY_PINECONE_DEMO)
|
520 |
+
async def image_search_pinecone(
|
521 |
+
images_to_search: Optional[List[UploadFile]] = File(None),
|
522 |
+
query_image: Optional[UploadFile] = File(None),
|
523 |
+
top_k: int = 5,
|
524 |
+
namespace="av_local",
|
525 |
+
action="query",
|
526 |
+
):
|
527 |
+
|
528 |
+
try:
|
529 |
+
# Function to delete all files from the database
|
530 |
+
print(f"Received request with images_to_search: {images_to_search} and query_image: {query_image} with action: {action}")
|
531 |
+
if action == "delete":
|
532 |
+
index = pinecone.Index(INDEX_NAME)
|
533 |
+
delete_response = index.delete(delete_all=True, namespace=namespace)
|
534 |
+
return {f"Deleted the namespace: {namespace}": delete_response}
|
535 |
+
|
536 |
+
elif action == "query" and query_image is not None:
|
537 |
+
extension = query_image.filename.split(".")[-1] in ("jpg", "jpeg", "png", "JPG", "PNG", "JPEG")
|
538 |
+
if not extension:
|
539 |
+
return "Image must be jpg or png format!"
|
540 |
+
# read image contain
|
541 |
+
contents = await query_image.read()
|
542 |
+
query_image = Image.open(io.BytesIO(contents))
|
543 |
+
print("Indexing query image...")
|
544 |
+
query_image = enhance_image(query_image)
|
545 |
+
prompt_embedding = image_sim_model.encode(query_image, convert_to_tensor=True).tolist()
|
546 |
+
if INDEX_NAME not in pinecone.list_indexes():
|
547 |
+
return {"similar_images": [], "status": "No index found for images"}
|
548 |
+
|
549 |
+
else:
|
550 |
+
index = pinecone.Index(INDEX_NAME)
|
551 |
+
query_response = index.query(
|
552 |
+
namespace=namespace,
|
553 |
+
top_k=top_k,
|
554 |
+
include_values=True,
|
555 |
+
include_metadata=True,
|
556 |
+
vector=prompt_embedding,
|
557 |
+
)
|
558 |
+
result_images = [d["metadata"]["file_path"] for d in query_response["matches"]]
|
559 |
+
print("Creating the result..")
|
560 |
+
similar_images = []
|
561 |
+
print("Retrieved matches ", query_response["matches"])
|
562 |
+
for file_path in result_images:
|
563 |
+
try:
|
564 |
+
# print("Finding the image ")
|
565 |
+
# print("Type of images list ", type(search_images), "similar image id ", hit['corpus_id'])
|
566 |
+
open_cv_image = cv2.imread(file_path)
|
567 |
+
# print("cv2.imencode the image ")
|
568 |
+
_, encoded_img = cv2.imencode(".PNG", open_cv_image)
|
569 |
+
# print("base64 the image ")
|
570 |
+
encoded_img = base64.b64encode(encoded_img)
|
571 |
+
# print("Appending the image ")
|
572 |
+
similar_images.append(
|
573 |
+
{
|
574 |
+
"filename": file_path,
|
575 |
+
"dimensions": str(open_cv_image.shape),
|
576 |
+
"score": 0,
|
577 |
+
"encoded_img": encoded_img,
|
578 |
+
}
|
579 |
+
)
|
580 |
+
except:
|
581 |
+
similar_images.append(
|
582 |
+
{
|
583 |
+
"filename": file_path,
|
584 |
+
"dimensions": None,
|
585 |
+
"score": 0,
|
586 |
+
"encoded_img": None,
|
587 |
+
}
|
588 |
+
)
|
589 |
+
print("Sending result..")
|
590 |
+
|
591 |
+
return {"similar_images": similar_images}
|
592 |
+
|
593 |
+
elif action == "index" and len(images_to_search) > 0:
|
594 |
+
print(
|
595 |
+
f"Recived images of length: {len(images_to_search)} needs to retrieve top k : {top_k} similar images as result"
|
596 |
+
)
|
597 |
+
print(f"Action indexing is executing for : {len(images_to_search)} images")
|
598 |
+
# if the index does not already exist, we create it
|
599 |
+
# check if the abstractive-question-answering index exists
|
600 |
+
print("checking pinecone Index")
|
601 |
+
if INDEX_NAME not in pinecone.list_indexes():
|
602 |
+
# delete the current index and create the new index if it does not exist
|
603 |
+
for delete_index in pinecone.list_indexes():
|
604 |
+
print(f"Deleting exitsing pinecone Index : {delete_index}")
|
605 |
+
|
606 |
+
pinecone.delete_index(delete_index)
|
607 |
+
print(f"Creating new pinecone Index : {INDEX_NAME}")
|
608 |
+
pinecone.create_index(INDEX_NAME, dimension=INDEX_DIMENSION, metric="cosine")
|
609 |
+
# instantiate connection to your Pinecone index
|
610 |
+
print(f"Connecting to pinecone Index : {INDEX_NAME}")
|
611 |
+
index = pinecone.Index(INDEX_NAME)
|
612 |
+
search_images = []
|
613 |
+
meta_datas = []
|
614 |
+
ids = []
|
615 |
+
print("Processing request...")
|
616 |
+
for image in images_to_search:
|
617 |
+
if image.filename.split(".")[-1] not in ("jpg", "jpeg", "png", "JPG", "PNG", "JPEG"):
|
618 |
+
return "Image must be jpg or png format!"
|
619 |
+
# read image contain
|
620 |
+
contents = await image.read()
|
621 |
+
pil_image = Image.open(io.BytesIO(contents))
|
622 |
+
tmp_file = f"{TMP_DIR}/{image.filename}"
|
623 |
+
pil_image.save(tmp_file)
|
624 |
+
meta_datas.append({"file_path": tmp_file})
|
625 |
+
search_images.append(pil_image)
|
626 |
+
ids.append(str(uuid.uuid1()).replace("-",""))
|
627 |
+
|
628 |
+
print("Encoding images to vectors...")
|
629 |
+
corpus_embeddings = image_sim_model.encode(
|
630 |
+
search_images, convert_to_tensor=True, show_progress_bar=True
|
631 |
+
).tolist()
|
632 |
+
print(f"Indexing images to pinecone Index : {INDEX_NAME}")
|
633 |
+
index.upsert(
|
634 |
+
vectors=list(zip(ids, corpus_embeddings, meta_datas)), namespace=namespace
|
635 |
+
)
|
636 |
+
|
637 |
+
|
638 |
+
return {"similar_images": [], "status": "Indexing succesfull for uploaded files"}
|
639 |
+
else:
|
640 |
+
return {"similar_images": []}
|
641 |
+
except Exception as e:
|
642 |
+
e = sys.exc_info()[1]
|
643 |
+
print(f"exception happened {e} {str(traceback.print_exc())}")
|
644 |
+
raise HTTPException(status_code=500, detail=str(e))
|
645 |
+
|
646 |
+
|
647 |
+
if __name__ == "__main__":
|
648 |
+
parser = argparse.ArgumentParser(description="Fast API exposing YOLOv5 model")
|
649 |
+
parser.add_argument("--port", default=8000, type=int, help="port number")
|
650 |
+
# parser.add_argument('--model', nargs='+', default=['yolov5s'], help='model(s) to run, i.e. --model yolov5n yolov5s')
|
651 |
+
opt = parser.parse_args()
|
652 |
+
uvicorn.run(app, port=opt.port)
|
best.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8faa2592e29248e58453cb031e536bd96f2929d9768bbd3c78ea54944f045db
|
3 |
+
size 14447677
|
best_classifer_model.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e5c0f63fbe8f8349ceda742cc6c7d333c1a2ae443b6f7aa1d100859d59322a7
|
3 |
+
size 377080432
|
deploy.prototxt
ADDED
@@ -0,0 +1,1789 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
input: "data"
|
2 |
+
input_shape {
|
3 |
+
dim: 1
|
4 |
+
dim: 3
|
5 |
+
dim: 300
|
6 |
+
dim: 300
|
7 |
+
}
|
8 |
+
|
9 |
+
layer {
|
10 |
+
name: "data_bn"
|
11 |
+
type: "BatchNorm"
|
12 |
+
bottom: "data"
|
13 |
+
top: "data_bn"
|
14 |
+
param {
|
15 |
+
lr_mult: 0.0
|
16 |
+
}
|
17 |
+
param {
|
18 |
+
lr_mult: 0.0
|
19 |
+
}
|
20 |
+
param {
|
21 |
+
lr_mult: 0.0
|
22 |
+
}
|
23 |
+
}
|
24 |
+
layer {
|
25 |
+
name: "data_scale"
|
26 |
+
type: "Scale"
|
27 |
+
bottom: "data_bn"
|
28 |
+
top: "data_bn"
|
29 |
+
param {
|
30 |
+
lr_mult: 1.0
|
31 |
+
decay_mult: 1.0
|
32 |
+
}
|
33 |
+
param {
|
34 |
+
lr_mult: 2.0
|
35 |
+
decay_mult: 1.0
|
36 |
+
}
|
37 |
+
scale_param {
|
38 |
+
bias_term: true
|
39 |
+
}
|
40 |
+
}
|
41 |
+
layer {
|
42 |
+
name: "conv1_h"
|
43 |
+
type: "Convolution"
|
44 |
+
bottom: "data_bn"
|
45 |
+
top: "conv1_h"
|
46 |
+
param {
|
47 |
+
lr_mult: 1.0
|
48 |
+
decay_mult: 1.0
|
49 |
+
}
|
50 |
+
param {
|
51 |
+
lr_mult: 2.0
|
52 |
+
decay_mult: 1.0
|
53 |
+
}
|
54 |
+
convolution_param {
|
55 |
+
num_output: 32
|
56 |
+
pad: 3
|
57 |
+
kernel_size: 7
|
58 |
+
stride: 2
|
59 |
+
weight_filler {
|
60 |
+
type: "msra"
|
61 |
+
variance_norm: FAN_OUT
|
62 |
+
}
|
63 |
+
bias_filler {
|
64 |
+
type: "constant"
|
65 |
+
value: 0.0
|
66 |
+
}
|
67 |
+
}
|
68 |
+
}
|
69 |
+
layer {
|
70 |
+
name: "conv1_bn_h"
|
71 |
+
type: "BatchNorm"
|
72 |
+
bottom: "conv1_h"
|
73 |
+
top: "conv1_h"
|
74 |
+
param {
|
75 |
+
lr_mult: 0.0
|
76 |
+
}
|
77 |
+
param {
|
78 |
+
lr_mult: 0.0
|
79 |
+
}
|
80 |
+
param {
|
81 |
+
lr_mult: 0.0
|
82 |
+
}
|
83 |
+
}
|
84 |
+
layer {
|
85 |
+
name: "conv1_scale_h"
|
86 |
+
type: "Scale"
|
87 |
+
bottom: "conv1_h"
|
88 |
+
top: "conv1_h"
|
89 |
+
param {
|
90 |
+
lr_mult: 1.0
|
91 |
+
decay_mult: 1.0
|
92 |
+
}
|
93 |
+
param {
|
94 |
+
lr_mult: 2.0
|
95 |
+
decay_mult: 1.0
|
96 |
+
}
|
97 |
+
scale_param {
|
98 |
+
bias_term: true
|
99 |
+
}
|
100 |
+
}
|
101 |
+
layer {
|
102 |
+
name: "conv1_relu"
|
103 |
+
type: "ReLU"
|
104 |
+
bottom: "conv1_h"
|
105 |
+
top: "conv1_h"
|
106 |
+
}
|
107 |
+
layer {
|
108 |
+
name: "conv1_pool"
|
109 |
+
type: "Pooling"
|
110 |
+
bottom: "conv1_h"
|
111 |
+
top: "conv1_pool"
|
112 |
+
pooling_param {
|
113 |
+
kernel_size: 3
|
114 |
+
stride: 2
|
115 |
+
}
|
116 |
+
}
|
117 |
+
layer {
|
118 |
+
name: "layer_64_1_conv1_h"
|
119 |
+
type: "Convolution"
|
120 |
+
bottom: "conv1_pool"
|
121 |
+
top: "layer_64_1_conv1_h"
|
122 |
+
param {
|
123 |
+
lr_mult: 1.0
|
124 |
+
decay_mult: 1.0
|
125 |
+
}
|
126 |
+
convolution_param {
|
127 |
+
num_output: 32
|
128 |
+
bias_term: false
|
129 |
+
pad: 1
|
130 |
+
kernel_size: 3
|
131 |
+
stride: 1
|
132 |
+
weight_filler {
|
133 |
+
type: "msra"
|
134 |
+
}
|
135 |
+
bias_filler {
|
136 |
+
type: "constant"
|
137 |
+
value: 0.0
|
138 |
+
}
|
139 |
+
}
|
140 |
+
}
|
141 |
+
layer {
|
142 |
+
name: "layer_64_1_bn2_h"
|
143 |
+
type: "BatchNorm"
|
144 |
+
bottom: "layer_64_1_conv1_h"
|
145 |
+
top: "layer_64_1_conv1_h"
|
146 |
+
param {
|
147 |
+
lr_mult: 0.0
|
148 |
+
}
|
149 |
+
param {
|
150 |
+
lr_mult: 0.0
|
151 |
+
}
|
152 |
+
param {
|
153 |
+
lr_mult: 0.0
|
154 |
+
}
|
155 |
+
}
|
156 |
+
layer {
|
157 |
+
name: "layer_64_1_scale2_h"
|
158 |
+
type: "Scale"
|
159 |
+
bottom: "layer_64_1_conv1_h"
|
160 |
+
top: "layer_64_1_conv1_h"
|
161 |
+
param {
|
162 |
+
lr_mult: 1.0
|
163 |
+
decay_mult: 1.0
|
164 |
+
}
|
165 |
+
param {
|
166 |
+
lr_mult: 2.0
|
167 |
+
decay_mult: 1.0
|
168 |
+
}
|
169 |
+
scale_param {
|
170 |
+
bias_term: true
|
171 |
+
}
|
172 |
+
}
|
173 |
+
layer {
|
174 |
+
name: "layer_64_1_relu2"
|
175 |
+
type: "ReLU"
|
176 |
+
bottom: "layer_64_1_conv1_h"
|
177 |
+
top: "layer_64_1_conv1_h"
|
178 |
+
}
|
179 |
+
layer {
|
180 |
+
name: "layer_64_1_conv2_h"
|
181 |
+
type: "Convolution"
|
182 |
+
bottom: "layer_64_1_conv1_h"
|
183 |
+
top: "layer_64_1_conv2_h"
|
184 |
+
param {
|
185 |
+
lr_mult: 1.0
|
186 |
+
decay_mult: 1.0
|
187 |
+
}
|
188 |
+
convolution_param {
|
189 |
+
num_output: 32
|
190 |
+
bias_term: false
|
191 |
+
pad: 1
|
192 |
+
kernel_size: 3
|
193 |
+
stride: 1
|
194 |
+
weight_filler {
|
195 |
+
type: "msra"
|
196 |
+
}
|
197 |
+
bias_filler {
|
198 |
+
type: "constant"
|
199 |
+
value: 0.0
|
200 |
+
}
|
201 |
+
}
|
202 |
+
}
|
203 |
+
layer {
|
204 |
+
name: "layer_64_1_sum"
|
205 |
+
type: "Eltwise"
|
206 |
+
bottom: "layer_64_1_conv2_h"
|
207 |
+
bottom: "conv1_pool"
|
208 |
+
top: "layer_64_1_sum"
|
209 |
+
}
|
210 |
+
layer {
|
211 |
+
name: "layer_128_1_bn1_h"
|
212 |
+
type: "BatchNorm"
|
213 |
+
bottom: "layer_64_1_sum"
|
214 |
+
top: "layer_128_1_bn1_h"
|
215 |
+
param {
|
216 |
+
lr_mult: 0.0
|
217 |
+
}
|
218 |
+
param {
|
219 |
+
lr_mult: 0.0
|
220 |
+
}
|
221 |
+
param {
|
222 |
+
lr_mult: 0.0
|
223 |
+
}
|
224 |
+
}
|
225 |
+
layer {
|
226 |
+
name: "layer_128_1_scale1_h"
|
227 |
+
type: "Scale"
|
228 |
+
bottom: "layer_128_1_bn1_h"
|
229 |
+
top: "layer_128_1_bn1_h"
|
230 |
+
param {
|
231 |
+
lr_mult: 1.0
|
232 |
+
decay_mult: 1.0
|
233 |
+
}
|
234 |
+
param {
|
235 |
+
lr_mult: 2.0
|
236 |
+
decay_mult: 1.0
|
237 |
+
}
|
238 |
+
scale_param {
|
239 |
+
bias_term: true
|
240 |
+
}
|
241 |
+
}
|
242 |
+
layer {
|
243 |
+
name: "layer_128_1_relu1"
|
244 |
+
type: "ReLU"
|
245 |
+
bottom: "layer_128_1_bn1_h"
|
246 |
+
top: "layer_128_1_bn1_h"
|
247 |
+
}
|
248 |
+
layer {
|
249 |
+
name: "layer_128_1_conv1_h"
|
250 |
+
type: "Convolution"
|
251 |
+
bottom: "layer_128_1_bn1_h"
|
252 |
+
top: "layer_128_1_conv1_h"
|
253 |
+
param {
|
254 |
+
lr_mult: 1.0
|
255 |
+
decay_mult: 1.0
|
256 |
+
}
|
257 |
+
convolution_param {
|
258 |
+
num_output: 128
|
259 |
+
bias_term: false
|
260 |
+
pad: 1
|
261 |
+
kernel_size: 3
|
262 |
+
stride: 2
|
263 |
+
weight_filler {
|
264 |
+
type: "msra"
|
265 |
+
}
|
266 |
+
bias_filler {
|
267 |
+
type: "constant"
|
268 |
+
value: 0.0
|
269 |
+
}
|
270 |
+
}
|
271 |
+
}
|
272 |
+
layer {
|
273 |
+
name: "layer_128_1_bn2"
|
274 |
+
type: "BatchNorm"
|
275 |
+
bottom: "layer_128_1_conv1_h"
|
276 |
+
top: "layer_128_1_conv1_h"
|
277 |
+
param {
|
278 |
+
lr_mult: 0.0
|
279 |
+
}
|
280 |
+
param {
|
281 |
+
lr_mult: 0.0
|
282 |
+
}
|
283 |
+
param {
|
284 |
+
lr_mult: 0.0
|
285 |
+
}
|
286 |
+
}
|
287 |
+
layer {
|
288 |
+
name: "layer_128_1_scale2"
|
289 |
+
type: "Scale"
|
290 |
+
bottom: "layer_128_1_conv1_h"
|
291 |
+
top: "layer_128_1_conv1_h"
|
292 |
+
param {
|
293 |
+
lr_mult: 1.0
|
294 |
+
decay_mult: 1.0
|
295 |
+
}
|
296 |
+
param {
|
297 |
+
lr_mult: 2.0
|
298 |
+
decay_mult: 1.0
|
299 |
+
}
|
300 |
+
scale_param {
|
301 |
+
bias_term: true
|
302 |
+
}
|
303 |
+
}
|
304 |
+
layer {
|
305 |
+
name: "layer_128_1_relu2"
|
306 |
+
type: "ReLU"
|
307 |
+
bottom: "layer_128_1_conv1_h"
|
308 |
+
top: "layer_128_1_conv1_h"
|
309 |
+
}
|
310 |
+
layer {
|
311 |
+
name: "layer_128_1_conv2"
|
312 |
+
type: "Convolution"
|
313 |
+
bottom: "layer_128_1_conv1_h"
|
314 |
+
top: "layer_128_1_conv2"
|
315 |
+
param {
|
316 |
+
lr_mult: 1.0
|
317 |
+
decay_mult: 1.0
|
318 |
+
}
|
319 |
+
convolution_param {
|
320 |
+
num_output: 128
|
321 |
+
bias_term: false
|
322 |
+
pad: 1
|
323 |
+
kernel_size: 3
|
324 |
+
stride: 1
|
325 |
+
weight_filler {
|
326 |
+
type: "msra"
|
327 |
+
}
|
328 |
+
bias_filler {
|
329 |
+
type: "constant"
|
330 |
+
value: 0.0
|
331 |
+
}
|
332 |
+
}
|
333 |
+
}
|
334 |
+
layer {
|
335 |
+
name: "layer_128_1_conv_expand_h"
|
336 |
+
type: "Convolution"
|
337 |
+
bottom: "layer_128_1_bn1_h"
|
338 |
+
top: "layer_128_1_conv_expand_h"
|
339 |
+
param {
|
340 |
+
lr_mult: 1.0
|
341 |
+
decay_mult: 1.0
|
342 |
+
}
|
343 |
+
convolution_param {
|
344 |
+
num_output: 128
|
345 |
+
bias_term: false
|
346 |
+
pad: 0
|
347 |
+
kernel_size: 1
|
348 |
+
stride: 2
|
349 |
+
weight_filler {
|
350 |
+
type: "msra"
|
351 |
+
}
|
352 |
+
bias_filler {
|
353 |
+
type: "constant"
|
354 |
+
value: 0.0
|
355 |
+
}
|
356 |
+
}
|
357 |
+
}
|
358 |
+
layer {
|
359 |
+
name: "layer_128_1_sum"
|
360 |
+
type: "Eltwise"
|
361 |
+
bottom: "layer_128_1_conv2"
|
362 |
+
bottom: "layer_128_1_conv_expand_h"
|
363 |
+
top: "layer_128_1_sum"
|
364 |
+
}
|
365 |
+
layer {
|
366 |
+
name: "layer_256_1_bn1"
|
367 |
+
type: "BatchNorm"
|
368 |
+
bottom: "layer_128_1_sum"
|
369 |
+
top: "layer_256_1_bn1"
|
370 |
+
param {
|
371 |
+
lr_mult: 0.0
|
372 |
+
}
|
373 |
+
param {
|
374 |
+
lr_mult: 0.0
|
375 |
+
}
|
376 |
+
param {
|
377 |
+
lr_mult: 0.0
|
378 |
+
}
|
379 |
+
}
|
380 |
+
layer {
|
381 |
+
name: "layer_256_1_scale1"
|
382 |
+
type: "Scale"
|
383 |
+
bottom: "layer_256_1_bn1"
|
384 |
+
top: "layer_256_1_bn1"
|
385 |
+
param {
|
386 |
+
lr_mult: 1.0
|
387 |
+
decay_mult: 1.0
|
388 |
+
}
|
389 |
+
param {
|
390 |
+
lr_mult: 2.0
|
391 |
+
decay_mult: 1.0
|
392 |
+
}
|
393 |
+
scale_param {
|
394 |
+
bias_term: true
|
395 |
+
}
|
396 |
+
}
|
397 |
+
layer {
|
398 |
+
name: "layer_256_1_relu1"
|
399 |
+
type: "ReLU"
|
400 |
+
bottom: "layer_256_1_bn1"
|
401 |
+
top: "layer_256_1_bn1"
|
402 |
+
}
|
403 |
+
layer {
|
404 |
+
name: "layer_256_1_conv1"
|
405 |
+
type: "Convolution"
|
406 |
+
bottom: "layer_256_1_bn1"
|
407 |
+
top: "layer_256_1_conv1"
|
408 |
+
param {
|
409 |
+
lr_mult: 1.0
|
410 |
+
decay_mult: 1.0
|
411 |
+
}
|
412 |
+
convolution_param {
|
413 |
+
num_output: 256
|
414 |
+
bias_term: false
|
415 |
+
pad: 1
|
416 |
+
kernel_size: 3
|
417 |
+
stride: 2
|
418 |
+
weight_filler {
|
419 |
+
type: "msra"
|
420 |
+
}
|
421 |
+
bias_filler {
|
422 |
+
type: "constant"
|
423 |
+
value: 0.0
|
424 |
+
}
|
425 |
+
}
|
426 |
+
}
|
427 |
+
layer {
|
428 |
+
name: "layer_256_1_bn2"
|
429 |
+
type: "BatchNorm"
|
430 |
+
bottom: "layer_256_1_conv1"
|
431 |
+
top: "layer_256_1_conv1"
|
432 |
+
param {
|
433 |
+
lr_mult: 0.0
|
434 |
+
}
|
435 |
+
param {
|
436 |
+
lr_mult: 0.0
|
437 |
+
}
|
438 |
+
param {
|
439 |
+
lr_mult: 0.0
|
440 |
+
}
|
441 |
+
}
|
442 |
+
layer {
|
443 |
+
name: "layer_256_1_scale2"
|
444 |
+
type: "Scale"
|
445 |
+
bottom: "layer_256_1_conv1"
|
446 |
+
top: "layer_256_1_conv1"
|
447 |
+
param {
|
448 |
+
lr_mult: 1.0
|
449 |
+
decay_mult: 1.0
|
450 |
+
}
|
451 |
+
param {
|
452 |
+
lr_mult: 2.0
|
453 |
+
decay_mult: 1.0
|
454 |
+
}
|
455 |
+
scale_param {
|
456 |
+
bias_term: true
|
457 |
+
}
|
458 |
+
}
|
459 |
+
layer {
|
460 |
+
name: "layer_256_1_relu2"
|
461 |
+
type: "ReLU"
|
462 |
+
bottom: "layer_256_1_conv1"
|
463 |
+
top: "layer_256_1_conv1"
|
464 |
+
}
|
465 |
+
layer {
|
466 |
+
name: "layer_256_1_conv2"
|
467 |
+
type: "Convolution"
|
468 |
+
bottom: "layer_256_1_conv1"
|
469 |
+
top: "layer_256_1_conv2"
|
470 |
+
param {
|
471 |
+
lr_mult: 1.0
|
472 |
+
decay_mult: 1.0
|
473 |
+
}
|
474 |
+
convolution_param {
|
475 |
+
num_output: 256
|
476 |
+
bias_term: false
|
477 |
+
pad: 1
|
478 |
+
kernel_size: 3
|
479 |
+
stride: 1
|
480 |
+
weight_filler {
|
481 |
+
type: "msra"
|
482 |
+
}
|
483 |
+
bias_filler {
|
484 |
+
type: "constant"
|
485 |
+
value: 0.0
|
486 |
+
}
|
487 |
+
}
|
488 |
+
}
|
489 |
+
layer {
|
490 |
+
name: "layer_256_1_conv_expand"
|
491 |
+
type: "Convolution"
|
492 |
+
bottom: "layer_256_1_bn1"
|
493 |
+
top: "layer_256_1_conv_expand"
|
494 |
+
param {
|
495 |
+
lr_mult: 1.0
|
496 |
+
decay_mult: 1.0
|
497 |
+
}
|
498 |
+
convolution_param {
|
499 |
+
num_output: 256
|
500 |
+
bias_term: false
|
501 |
+
pad: 0
|
502 |
+
kernel_size: 1
|
503 |
+
stride: 2
|
504 |
+
weight_filler {
|
505 |
+
type: "msra"
|
506 |
+
}
|
507 |
+
bias_filler {
|
508 |
+
type: "constant"
|
509 |
+
value: 0.0
|
510 |
+
}
|
511 |
+
}
|
512 |
+
}
|
513 |
+
layer {
|
514 |
+
name: "layer_256_1_sum"
|
515 |
+
type: "Eltwise"
|
516 |
+
bottom: "layer_256_1_conv2"
|
517 |
+
bottom: "layer_256_1_conv_expand"
|
518 |
+
top: "layer_256_1_sum"
|
519 |
+
}
|
520 |
+
layer {
|
521 |
+
name: "layer_512_1_bn1"
|
522 |
+
type: "BatchNorm"
|
523 |
+
bottom: "layer_256_1_sum"
|
524 |
+
top: "layer_512_1_bn1"
|
525 |
+
param {
|
526 |
+
lr_mult: 0.0
|
527 |
+
}
|
528 |
+
param {
|
529 |
+
lr_mult: 0.0
|
530 |
+
}
|
531 |
+
param {
|
532 |
+
lr_mult: 0.0
|
533 |
+
}
|
534 |
+
}
|
535 |
+
layer {
|
536 |
+
name: "layer_512_1_scale1"
|
537 |
+
type: "Scale"
|
538 |
+
bottom: "layer_512_1_bn1"
|
539 |
+
top: "layer_512_1_bn1"
|
540 |
+
param {
|
541 |
+
lr_mult: 1.0
|
542 |
+
decay_mult: 1.0
|
543 |
+
}
|
544 |
+
param {
|
545 |
+
lr_mult: 2.0
|
546 |
+
decay_mult: 1.0
|
547 |
+
}
|
548 |
+
scale_param {
|
549 |
+
bias_term: true
|
550 |
+
}
|
551 |
+
}
|
552 |
+
layer {
|
553 |
+
name: "layer_512_1_relu1"
|
554 |
+
type: "ReLU"
|
555 |
+
bottom: "layer_512_1_bn1"
|
556 |
+
top: "layer_512_1_bn1"
|
557 |
+
}
|
558 |
+
layer {
|
559 |
+
name: "layer_512_1_conv1_h"
|
560 |
+
type: "Convolution"
|
561 |
+
bottom: "layer_512_1_bn1"
|
562 |
+
top: "layer_512_1_conv1_h"
|
563 |
+
param {
|
564 |
+
lr_mult: 1.0
|
565 |
+
decay_mult: 1.0
|
566 |
+
}
|
567 |
+
convolution_param {
|
568 |
+
num_output: 128
|
569 |
+
bias_term: false
|
570 |
+
pad: 1
|
571 |
+
kernel_size: 3
|
572 |
+
stride: 1 # 2
|
573 |
+
weight_filler {
|
574 |
+
type: "msra"
|
575 |
+
}
|
576 |
+
bias_filler {
|
577 |
+
type: "constant"
|
578 |
+
value: 0.0
|
579 |
+
}
|
580 |
+
}
|
581 |
+
}
|
582 |
+
layer {
|
583 |
+
name: "layer_512_1_bn2_h"
|
584 |
+
type: "BatchNorm"
|
585 |
+
bottom: "layer_512_1_conv1_h"
|
586 |
+
top: "layer_512_1_conv1_h"
|
587 |
+
param {
|
588 |
+
lr_mult: 0.0
|
589 |
+
}
|
590 |
+
param {
|
591 |
+
lr_mult: 0.0
|
592 |
+
}
|
593 |
+
param {
|
594 |
+
lr_mult: 0.0
|
595 |
+
}
|
596 |
+
}
|
597 |
+
layer {
|
598 |
+
name: "layer_512_1_scale2_h"
|
599 |
+
type: "Scale"
|
600 |
+
bottom: "layer_512_1_conv1_h"
|
601 |
+
top: "layer_512_1_conv1_h"
|
602 |
+
param {
|
603 |
+
lr_mult: 1.0
|
604 |
+
decay_mult: 1.0
|
605 |
+
}
|
606 |
+
param {
|
607 |
+
lr_mult: 2.0
|
608 |
+
decay_mult: 1.0
|
609 |
+
}
|
610 |
+
scale_param {
|
611 |
+
bias_term: true
|
612 |
+
}
|
613 |
+
}
|
614 |
+
layer {
|
615 |
+
name: "layer_512_1_relu2"
|
616 |
+
type: "ReLU"
|
617 |
+
bottom: "layer_512_1_conv1_h"
|
618 |
+
top: "layer_512_1_conv1_h"
|
619 |
+
}
|
620 |
+
layer {
|
621 |
+
name: "layer_512_1_conv2_h"
|
622 |
+
type: "Convolution"
|
623 |
+
bottom: "layer_512_1_conv1_h"
|
624 |
+
top: "layer_512_1_conv2_h"
|
625 |
+
param {
|
626 |
+
lr_mult: 1.0
|
627 |
+
decay_mult: 1.0
|
628 |
+
}
|
629 |
+
convolution_param {
|
630 |
+
num_output: 256
|
631 |
+
bias_term: false
|
632 |
+
pad: 2 # 1
|
633 |
+
kernel_size: 3
|
634 |
+
stride: 1
|
635 |
+
dilation: 2
|
636 |
+
weight_filler {
|
637 |
+
type: "msra"
|
638 |
+
}
|
639 |
+
bias_filler {
|
640 |
+
type: "constant"
|
641 |
+
value: 0.0
|
642 |
+
}
|
643 |
+
}
|
644 |
+
}
|
645 |
+
layer {
|
646 |
+
name: "layer_512_1_conv_expand_h"
|
647 |
+
type: "Convolution"
|
648 |
+
bottom: "layer_512_1_bn1"
|
649 |
+
top: "layer_512_1_conv_expand_h"
|
650 |
+
param {
|
651 |
+
lr_mult: 1.0
|
652 |
+
decay_mult: 1.0
|
653 |
+
}
|
654 |
+
convolution_param {
|
655 |
+
num_output: 256
|
656 |
+
bias_term: false
|
657 |
+
pad: 0
|
658 |
+
kernel_size: 1
|
659 |
+
stride: 1 # 2
|
660 |
+
weight_filler {
|
661 |
+
type: "msra"
|
662 |
+
}
|
663 |
+
bias_filler {
|
664 |
+
type: "constant"
|
665 |
+
value: 0.0
|
666 |
+
}
|
667 |
+
}
|
668 |
+
}
|
669 |
+
layer {
|
670 |
+
name: "layer_512_1_sum"
|
671 |
+
type: "Eltwise"
|
672 |
+
bottom: "layer_512_1_conv2_h"
|
673 |
+
bottom: "layer_512_1_conv_expand_h"
|
674 |
+
top: "layer_512_1_sum"
|
675 |
+
}
|
676 |
+
layer {
|
677 |
+
name: "last_bn_h"
|
678 |
+
type: "BatchNorm"
|
679 |
+
bottom: "layer_512_1_sum"
|
680 |
+
top: "layer_512_1_sum"
|
681 |
+
param {
|
682 |
+
lr_mult: 0.0
|
683 |
+
}
|
684 |
+
param {
|
685 |
+
lr_mult: 0.0
|
686 |
+
}
|
687 |
+
param {
|
688 |
+
lr_mult: 0.0
|
689 |
+
}
|
690 |
+
}
|
691 |
+
layer {
|
692 |
+
name: "last_scale_h"
|
693 |
+
type: "Scale"
|
694 |
+
bottom: "layer_512_1_sum"
|
695 |
+
top: "layer_512_1_sum"
|
696 |
+
param {
|
697 |
+
lr_mult: 1.0
|
698 |
+
decay_mult: 1.0
|
699 |
+
}
|
700 |
+
param {
|
701 |
+
lr_mult: 2.0
|
702 |
+
decay_mult: 1.0
|
703 |
+
}
|
704 |
+
scale_param {
|
705 |
+
bias_term: true
|
706 |
+
}
|
707 |
+
}
|
708 |
+
layer {
|
709 |
+
name: "last_relu"
|
710 |
+
type: "ReLU"
|
711 |
+
bottom: "layer_512_1_sum"
|
712 |
+
top: "fc7"
|
713 |
+
}
|
714 |
+
|
715 |
+
layer {
|
716 |
+
name: "conv6_1_h"
|
717 |
+
type: "Convolution"
|
718 |
+
bottom: "fc7"
|
719 |
+
top: "conv6_1_h"
|
720 |
+
param {
|
721 |
+
lr_mult: 1
|
722 |
+
decay_mult: 1
|
723 |
+
}
|
724 |
+
param {
|
725 |
+
lr_mult: 2
|
726 |
+
decay_mult: 0
|
727 |
+
}
|
728 |
+
convolution_param {
|
729 |
+
num_output: 128
|
730 |
+
pad: 0
|
731 |
+
kernel_size: 1
|
732 |
+
stride: 1
|
733 |
+
weight_filler {
|
734 |
+
type: "xavier"
|
735 |
+
}
|
736 |
+
bias_filler {
|
737 |
+
type: "constant"
|
738 |
+
value: 0
|
739 |
+
}
|
740 |
+
}
|
741 |
+
}
|
742 |
+
layer {
|
743 |
+
name: "conv6_1_relu"
|
744 |
+
type: "ReLU"
|
745 |
+
bottom: "conv6_1_h"
|
746 |
+
top: "conv6_1_h"
|
747 |
+
}
|
748 |
+
layer {
|
749 |
+
name: "conv6_2_h"
|
750 |
+
type: "Convolution"
|
751 |
+
bottom: "conv6_1_h"
|
752 |
+
top: "conv6_2_h"
|
753 |
+
param {
|
754 |
+
lr_mult: 1
|
755 |
+
decay_mult: 1
|
756 |
+
}
|
757 |
+
param {
|
758 |
+
lr_mult: 2
|
759 |
+
decay_mult: 0
|
760 |
+
}
|
761 |
+
convolution_param {
|
762 |
+
num_output: 256
|
763 |
+
pad: 1
|
764 |
+
kernel_size: 3
|
765 |
+
stride: 2
|
766 |
+
weight_filler {
|
767 |
+
type: "xavier"
|
768 |
+
}
|
769 |
+
bias_filler {
|
770 |
+
type: "constant"
|
771 |
+
value: 0
|
772 |
+
}
|
773 |
+
}
|
774 |
+
}
|
775 |
+
layer {
|
776 |
+
name: "conv6_2_relu"
|
777 |
+
type: "ReLU"
|
778 |
+
bottom: "conv6_2_h"
|
779 |
+
top: "conv6_2_h"
|
780 |
+
}
|
781 |
+
layer {
|
782 |
+
name: "conv7_1_h"
|
783 |
+
type: "Convolution"
|
784 |
+
bottom: "conv6_2_h"
|
785 |
+
top: "conv7_1_h"
|
786 |
+
param {
|
787 |
+
lr_mult: 1
|
788 |
+
decay_mult: 1
|
789 |
+
}
|
790 |
+
param {
|
791 |
+
lr_mult: 2
|
792 |
+
decay_mult: 0
|
793 |
+
}
|
794 |
+
convolution_param {
|
795 |
+
num_output: 64
|
796 |
+
pad: 0
|
797 |
+
kernel_size: 1
|
798 |
+
stride: 1
|
799 |
+
weight_filler {
|
800 |
+
type: "xavier"
|
801 |
+
}
|
802 |
+
bias_filler {
|
803 |
+
type: "constant"
|
804 |
+
value: 0
|
805 |
+
}
|
806 |
+
}
|
807 |
+
}
|
808 |
+
layer {
|
809 |
+
name: "conv7_1_relu"
|
810 |
+
type: "ReLU"
|
811 |
+
bottom: "conv7_1_h"
|
812 |
+
top: "conv7_1_h"
|
813 |
+
}
|
814 |
+
layer {
|
815 |
+
name: "conv7_2_h"
|
816 |
+
type: "Convolution"
|
817 |
+
bottom: "conv7_1_h"
|
818 |
+
top: "conv7_2_h"
|
819 |
+
param {
|
820 |
+
lr_mult: 1
|
821 |
+
decay_mult: 1
|
822 |
+
}
|
823 |
+
param {
|
824 |
+
lr_mult: 2
|
825 |
+
decay_mult: 0
|
826 |
+
}
|
827 |
+
convolution_param {
|
828 |
+
num_output: 128
|
829 |
+
pad: 1
|
830 |
+
kernel_size: 3
|
831 |
+
stride: 2
|
832 |
+
weight_filler {
|
833 |
+
type: "xavier"
|
834 |
+
}
|
835 |
+
bias_filler {
|
836 |
+
type: "constant"
|
837 |
+
value: 0
|
838 |
+
}
|
839 |
+
}
|
840 |
+
}
|
841 |
+
layer {
|
842 |
+
name: "conv7_2_relu"
|
843 |
+
type: "ReLU"
|
844 |
+
bottom: "conv7_2_h"
|
845 |
+
top: "conv7_2_h"
|
846 |
+
}
|
847 |
+
layer {
|
848 |
+
name: "conv8_1_h"
|
849 |
+
type: "Convolution"
|
850 |
+
bottom: "conv7_2_h"
|
851 |
+
top: "conv8_1_h"
|
852 |
+
param {
|
853 |
+
lr_mult: 1
|
854 |
+
decay_mult: 1
|
855 |
+
}
|
856 |
+
param {
|
857 |
+
lr_mult: 2
|
858 |
+
decay_mult: 0
|
859 |
+
}
|
860 |
+
convolution_param {
|
861 |
+
num_output: 64
|
862 |
+
pad: 0
|
863 |
+
kernel_size: 1
|
864 |
+
stride: 1
|
865 |
+
weight_filler {
|
866 |
+
type: "xavier"
|
867 |
+
}
|
868 |
+
bias_filler {
|
869 |
+
type: "constant"
|
870 |
+
value: 0
|
871 |
+
}
|
872 |
+
}
|
873 |
+
}
|
874 |
+
layer {
|
875 |
+
name: "conv8_1_relu"
|
876 |
+
type: "ReLU"
|
877 |
+
bottom: "conv8_1_h"
|
878 |
+
top: "conv8_1_h"
|
879 |
+
}
|
880 |
+
layer {
|
881 |
+
name: "conv8_2_h"
|
882 |
+
type: "Convolution"
|
883 |
+
bottom: "conv8_1_h"
|
884 |
+
top: "conv8_2_h"
|
885 |
+
param {
|
886 |
+
lr_mult: 1
|
887 |
+
decay_mult: 1
|
888 |
+
}
|
889 |
+
param {
|
890 |
+
lr_mult: 2
|
891 |
+
decay_mult: 0
|
892 |
+
}
|
893 |
+
convolution_param {
|
894 |
+
num_output: 128
|
895 |
+
pad: 1
|
896 |
+
kernel_size: 3
|
897 |
+
stride: 1
|
898 |
+
weight_filler {
|
899 |
+
type: "xavier"
|
900 |
+
}
|
901 |
+
bias_filler {
|
902 |
+
type: "constant"
|
903 |
+
value: 0
|
904 |
+
}
|
905 |
+
}
|
906 |
+
}
|
907 |
+
layer {
|
908 |
+
name: "conv8_2_relu"
|
909 |
+
type: "ReLU"
|
910 |
+
bottom: "conv8_2_h"
|
911 |
+
top: "conv8_2_h"
|
912 |
+
}
|
913 |
+
layer {
|
914 |
+
name: "conv9_1_h"
|
915 |
+
type: "Convolution"
|
916 |
+
bottom: "conv8_2_h"
|
917 |
+
top: "conv9_1_h"
|
918 |
+
param {
|
919 |
+
lr_mult: 1
|
920 |
+
decay_mult: 1
|
921 |
+
}
|
922 |
+
param {
|
923 |
+
lr_mult: 2
|
924 |
+
decay_mult: 0
|
925 |
+
}
|
926 |
+
convolution_param {
|
927 |
+
num_output: 64
|
928 |
+
pad: 0
|
929 |
+
kernel_size: 1
|
930 |
+
stride: 1
|
931 |
+
weight_filler {
|
932 |
+
type: "xavier"
|
933 |
+
}
|
934 |
+
bias_filler {
|
935 |
+
type: "constant"
|
936 |
+
value: 0
|
937 |
+
}
|
938 |
+
}
|
939 |
+
}
|
940 |
+
layer {
|
941 |
+
name: "conv9_1_relu"
|
942 |
+
type: "ReLU"
|
943 |
+
bottom: "conv9_1_h"
|
944 |
+
top: "conv9_1_h"
|
945 |
+
}
|
946 |
+
layer {
|
947 |
+
name: "conv9_2_h"
|
948 |
+
type: "Convolution"
|
949 |
+
bottom: "conv9_1_h"
|
950 |
+
top: "conv9_2_h"
|
951 |
+
param {
|
952 |
+
lr_mult: 1
|
953 |
+
decay_mult: 1
|
954 |
+
}
|
955 |
+
param {
|
956 |
+
lr_mult: 2
|
957 |
+
decay_mult: 0
|
958 |
+
}
|
959 |
+
convolution_param {
|
960 |
+
num_output: 128
|
961 |
+
pad: 1
|
962 |
+
kernel_size: 3
|
963 |
+
stride: 1
|
964 |
+
weight_filler {
|
965 |
+
type: "xavier"
|
966 |
+
}
|
967 |
+
bias_filler {
|
968 |
+
type: "constant"
|
969 |
+
value: 0
|
970 |
+
}
|
971 |
+
}
|
972 |
+
}
|
973 |
+
layer {
|
974 |
+
name: "conv9_2_relu"
|
975 |
+
type: "ReLU"
|
976 |
+
bottom: "conv9_2_h"
|
977 |
+
top: "conv9_2_h"
|
978 |
+
}
|
979 |
+
layer {
|
980 |
+
name: "conv4_3_norm"
|
981 |
+
type: "Normalize"
|
982 |
+
bottom: "layer_256_1_bn1"
|
983 |
+
top: "conv4_3_norm"
|
984 |
+
norm_param {
|
985 |
+
across_spatial: false
|
986 |
+
scale_filler {
|
987 |
+
type: "constant"
|
988 |
+
value: 20
|
989 |
+
}
|
990 |
+
channel_shared: false
|
991 |
+
}
|
992 |
+
}
|
993 |
+
layer {
|
994 |
+
name: "conv4_3_norm_mbox_loc"
|
995 |
+
type: "Convolution"
|
996 |
+
bottom: "conv4_3_norm"
|
997 |
+
top: "conv4_3_norm_mbox_loc"
|
998 |
+
param {
|
999 |
+
lr_mult: 1
|
1000 |
+
decay_mult: 1
|
1001 |
+
}
|
1002 |
+
param {
|
1003 |
+
lr_mult: 2
|
1004 |
+
decay_mult: 0
|
1005 |
+
}
|
1006 |
+
convolution_param {
|
1007 |
+
num_output: 16
|
1008 |
+
pad: 1
|
1009 |
+
kernel_size: 3
|
1010 |
+
stride: 1
|
1011 |
+
weight_filler {
|
1012 |
+
type: "xavier"
|
1013 |
+
}
|
1014 |
+
bias_filler {
|
1015 |
+
type: "constant"
|
1016 |
+
value: 0
|
1017 |
+
}
|
1018 |
+
}
|
1019 |
+
}
|
1020 |
+
layer {
|
1021 |
+
name: "conv4_3_norm_mbox_loc_perm"
|
1022 |
+
type: "Permute"
|
1023 |
+
bottom: "conv4_3_norm_mbox_loc"
|
1024 |
+
top: "conv4_3_norm_mbox_loc_perm"
|
1025 |
+
permute_param {
|
1026 |
+
order: 0
|
1027 |
+
order: 2
|
1028 |
+
order: 3
|
1029 |
+
order: 1
|
1030 |
+
}
|
1031 |
+
}
|
1032 |
+
layer {
|
1033 |
+
name: "conv4_3_norm_mbox_loc_flat"
|
1034 |
+
type: "Flatten"
|
1035 |
+
bottom: "conv4_3_norm_mbox_loc_perm"
|
1036 |
+
top: "conv4_3_norm_mbox_loc_flat"
|
1037 |
+
flatten_param {
|
1038 |
+
axis: 1
|
1039 |
+
}
|
1040 |
+
}
|
1041 |
+
layer {
|
1042 |
+
name: "conv4_3_norm_mbox_conf"
|
1043 |
+
type: "Convolution"
|
1044 |
+
bottom: "conv4_3_norm"
|
1045 |
+
top: "conv4_3_norm_mbox_conf"
|
1046 |
+
param {
|
1047 |
+
lr_mult: 1
|
1048 |
+
decay_mult: 1
|
1049 |
+
}
|
1050 |
+
param {
|
1051 |
+
lr_mult: 2
|
1052 |
+
decay_mult: 0
|
1053 |
+
}
|
1054 |
+
convolution_param {
|
1055 |
+
num_output: 8 # 84
|
1056 |
+
pad: 1
|
1057 |
+
kernel_size: 3
|
1058 |
+
stride: 1
|
1059 |
+
weight_filler {
|
1060 |
+
type: "xavier"
|
1061 |
+
}
|
1062 |
+
bias_filler {
|
1063 |
+
type: "constant"
|
1064 |
+
value: 0
|
1065 |
+
}
|
1066 |
+
}
|
1067 |
+
}
|
1068 |
+
layer {
|
1069 |
+
name: "conv4_3_norm_mbox_conf_perm"
|
1070 |
+
type: "Permute"
|
1071 |
+
bottom: "conv4_3_norm_mbox_conf"
|
1072 |
+
top: "conv4_3_norm_mbox_conf_perm"
|
1073 |
+
permute_param {
|
1074 |
+
order: 0
|
1075 |
+
order: 2
|
1076 |
+
order: 3
|
1077 |
+
order: 1
|
1078 |
+
}
|
1079 |
+
}
|
1080 |
+
layer {
|
1081 |
+
name: "conv4_3_norm_mbox_conf_flat"
|
1082 |
+
type: "Flatten"
|
1083 |
+
bottom: "conv4_3_norm_mbox_conf_perm"
|
1084 |
+
top: "conv4_3_norm_mbox_conf_flat"
|
1085 |
+
flatten_param {
|
1086 |
+
axis: 1
|
1087 |
+
}
|
1088 |
+
}
|
1089 |
+
layer {
|
1090 |
+
name: "conv4_3_norm_mbox_priorbox"
|
1091 |
+
type: "PriorBox"
|
1092 |
+
bottom: "conv4_3_norm"
|
1093 |
+
bottom: "data"
|
1094 |
+
top: "conv4_3_norm_mbox_priorbox"
|
1095 |
+
prior_box_param {
|
1096 |
+
min_size: 30.0
|
1097 |
+
max_size: 60.0
|
1098 |
+
aspect_ratio: 2
|
1099 |
+
flip: true
|
1100 |
+
clip: false
|
1101 |
+
variance: 0.1
|
1102 |
+
variance: 0.1
|
1103 |
+
variance: 0.2
|
1104 |
+
variance: 0.2
|
1105 |
+
step: 8
|
1106 |
+
offset: 0.5
|
1107 |
+
}
|
1108 |
+
}
|
1109 |
+
layer {
|
1110 |
+
name: "fc7_mbox_loc"
|
1111 |
+
type: "Convolution"
|
1112 |
+
bottom: "fc7"
|
1113 |
+
top: "fc7_mbox_loc"
|
1114 |
+
param {
|
1115 |
+
lr_mult: 1
|
1116 |
+
decay_mult: 1
|
1117 |
+
}
|
1118 |
+
param {
|
1119 |
+
lr_mult: 2
|
1120 |
+
decay_mult: 0
|
1121 |
+
}
|
1122 |
+
convolution_param {
|
1123 |
+
num_output: 24
|
1124 |
+
pad: 1
|
1125 |
+
kernel_size: 3
|
1126 |
+
stride: 1
|
1127 |
+
weight_filler {
|
1128 |
+
type: "xavier"
|
1129 |
+
}
|
1130 |
+
bias_filler {
|
1131 |
+
type: "constant"
|
1132 |
+
value: 0
|
1133 |
+
}
|
1134 |
+
}
|
1135 |
+
}
|
1136 |
+
layer {
|
1137 |
+
name: "fc7_mbox_loc_perm"
|
1138 |
+
type: "Permute"
|
1139 |
+
bottom: "fc7_mbox_loc"
|
1140 |
+
top: "fc7_mbox_loc_perm"
|
1141 |
+
permute_param {
|
1142 |
+
order: 0
|
1143 |
+
order: 2
|
1144 |
+
order: 3
|
1145 |
+
order: 1
|
1146 |
+
}
|
1147 |
+
}
|
1148 |
+
layer {
|
1149 |
+
name: "fc7_mbox_loc_flat"
|
1150 |
+
type: "Flatten"
|
1151 |
+
bottom: "fc7_mbox_loc_perm"
|
1152 |
+
top: "fc7_mbox_loc_flat"
|
1153 |
+
flatten_param {
|
1154 |
+
axis: 1
|
1155 |
+
}
|
1156 |
+
}
|
1157 |
+
layer {
|
1158 |
+
name: "fc7_mbox_conf"
|
1159 |
+
type: "Convolution"
|
1160 |
+
bottom: "fc7"
|
1161 |
+
top: "fc7_mbox_conf"
|
1162 |
+
param {
|
1163 |
+
lr_mult: 1
|
1164 |
+
decay_mult: 1
|
1165 |
+
}
|
1166 |
+
param {
|
1167 |
+
lr_mult: 2
|
1168 |
+
decay_mult: 0
|
1169 |
+
}
|
1170 |
+
convolution_param {
|
1171 |
+
num_output: 12 # 126
|
1172 |
+
pad: 1
|
1173 |
+
kernel_size: 3
|
1174 |
+
stride: 1
|
1175 |
+
weight_filler {
|
1176 |
+
type: "xavier"
|
1177 |
+
}
|
1178 |
+
bias_filler {
|
1179 |
+
type: "constant"
|
1180 |
+
value: 0
|
1181 |
+
}
|
1182 |
+
}
|
1183 |
+
}
|
1184 |
+
layer {
|
1185 |
+
name: "fc7_mbox_conf_perm"
|
1186 |
+
type: "Permute"
|
1187 |
+
bottom: "fc7_mbox_conf"
|
1188 |
+
top: "fc7_mbox_conf_perm"
|
1189 |
+
permute_param {
|
1190 |
+
order: 0
|
1191 |
+
order: 2
|
1192 |
+
order: 3
|
1193 |
+
order: 1
|
1194 |
+
}
|
1195 |
+
}
|
1196 |
+
layer {
|
1197 |
+
name: "fc7_mbox_conf_flat"
|
1198 |
+
type: "Flatten"
|
1199 |
+
bottom: "fc7_mbox_conf_perm"
|
1200 |
+
top: "fc7_mbox_conf_flat"
|
1201 |
+
flatten_param {
|
1202 |
+
axis: 1
|
1203 |
+
}
|
1204 |
+
}
|
1205 |
+
layer {
|
1206 |
+
name: "fc7_mbox_priorbox"
|
1207 |
+
type: "PriorBox"
|
1208 |
+
bottom: "fc7"
|
1209 |
+
bottom: "data"
|
1210 |
+
top: "fc7_mbox_priorbox"
|
1211 |
+
prior_box_param {
|
1212 |
+
min_size: 60.0
|
1213 |
+
max_size: 111.0
|
1214 |
+
aspect_ratio: 2
|
1215 |
+
aspect_ratio: 3
|
1216 |
+
flip: true
|
1217 |
+
clip: false
|
1218 |
+
variance: 0.1
|
1219 |
+
variance: 0.1
|
1220 |
+
variance: 0.2
|
1221 |
+
variance: 0.2
|
1222 |
+
step: 16
|
1223 |
+
offset: 0.5
|
1224 |
+
}
|
1225 |
+
}
|
1226 |
+
layer {
|
1227 |
+
name: "conv6_2_mbox_loc"
|
1228 |
+
type: "Convolution"
|
1229 |
+
bottom: "conv6_2_h"
|
1230 |
+
top: "conv6_2_mbox_loc"
|
1231 |
+
param {
|
1232 |
+
lr_mult: 1
|
1233 |
+
decay_mult: 1
|
1234 |
+
}
|
1235 |
+
param {
|
1236 |
+
lr_mult: 2
|
1237 |
+
decay_mult: 0
|
1238 |
+
}
|
1239 |
+
convolution_param {
|
1240 |
+
num_output: 24
|
1241 |
+
pad: 1
|
1242 |
+
kernel_size: 3
|
1243 |
+
stride: 1
|
1244 |
+
weight_filler {
|
1245 |
+
type: "xavier"
|
1246 |
+
}
|
1247 |
+
bias_filler {
|
1248 |
+
type: "constant"
|
1249 |
+
value: 0
|
1250 |
+
}
|
1251 |
+
}
|
1252 |
+
}
|
1253 |
+
layer {
|
1254 |
+
name: "conv6_2_mbox_loc_perm"
|
1255 |
+
type: "Permute"
|
1256 |
+
bottom: "conv6_2_mbox_loc"
|
1257 |
+
top: "conv6_2_mbox_loc_perm"
|
1258 |
+
permute_param {
|
1259 |
+
order: 0
|
1260 |
+
order: 2
|
1261 |
+
order: 3
|
1262 |
+
order: 1
|
1263 |
+
}
|
1264 |
+
}
|
1265 |
+
layer {
|
1266 |
+
name: "conv6_2_mbox_loc_flat"
|
1267 |
+
type: "Flatten"
|
1268 |
+
bottom: "conv6_2_mbox_loc_perm"
|
1269 |
+
top: "conv6_2_mbox_loc_flat"
|
1270 |
+
flatten_param {
|
1271 |
+
axis: 1
|
1272 |
+
}
|
1273 |
+
}
|
1274 |
+
layer {
|
1275 |
+
name: "conv6_2_mbox_conf"
|
1276 |
+
type: "Convolution"
|
1277 |
+
bottom: "conv6_2_h"
|
1278 |
+
top: "conv6_2_mbox_conf"
|
1279 |
+
param {
|
1280 |
+
lr_mult: 1
|
1281 |
+
decay_mult: 1
|
1282 |
+
}
|
1283 |
+
param {
|
1284 |
+
lr_mult: 2
|
1285 |
+
decay_mult: 0
|
1286 |
+
}
|
1287 |
+
convolution_param {
|
1288 |
+
num_output: 12 # 126
|
1289 |
+
pad: 1
|
1290 |
+
kernel_size: 3
|
1291 |
+
stride: 1
|
1292 |
+
weight_filler {
|
1293 |
+
type: "xavier"
|
1294 |
+
}
|
1295 |
+
bias_filler {
|
1296 |
+
type: "constant"
|
1297 |
+
value: 0
|
1298 |
+
}
|
1299 |
+
}
|
1300 |
+
}
|
1301 |
+
layer {
|
1302 |
+
name: "conv6_2_mbox_conf_perm"
|
1303 |
+
type: "Permute"
|
1304 |
+
bottom: "conv6_2_mbox_conf"
|
1305 |
+
top: "conv6_2_mbox_conf_perm"
|
1306 |
+
permute_param {
|
1307 |
+
order: 0
|
1308 |
+
order: 2
|
1309 |
+
order: 3
|
1310 |
+
order: 1
|
1311 |
+
}
|
1312 |
+
}
|
1313 |
+
layer {
|
1314 |
+
name: "conv6_2_mbox_conf_flat"
|
1315 |
+
type: "Flatten"
|
1316 |
+
bottom: "conv6_2_mbox_conf_perm"
|
1317 |
+
top: "conv6_2_mbox_conf_flat"
|
1318 |
+
flatten_param {
|
1319 |
+
axis: 1
|
1320 |
+
}
|
1321 |
+
}
|
1322 |
+
layer {
|
1323 |
+
name: "conv6_2_mbox_priorbox"
|
1324 |
+
type: "PriorBox"
|
1325 |
+
bottom: "conv6_2_h"
|
1326 |
+
bottom: "data"
|
1327 |
+
top: "conv6_2_mbox_priorbox"
|
1328 |
+
prior_box_param {
|
1329 |
+
min_size: 111.0
|
1330 |
+
max_size: 162.0
|
1331 |
+
aspect_ratio: 2
|
1332 |
+
aspect_ratio: 3
|
1333 |
+
flip: true
|
1334 |
+
clip: false
|
1335 |
+
variance: 0.1
|
1336 |
+
variance: 0.1
|
1337 |
+
variance: 0.2
|
1338 |
+
variance: 0.2
|
1339 |
+
step: 32
|
1340 |
+
offset: 0.5
|
1341 |
+
}
|
1342 |
+
}
|
1343 |
+
layer {
|
1344 |
+
name: "conv7_2_mbox_loc"
|
1345 |
+
type: "Convolution"
|
1346 |
+
bottom: "conv7_2_h"
|
1347 |
+
top: "conv7_2_mbox_loc"
|
1348 |
+
param {
|
1349 |
+
lr_mult: 1
|
1350 |
+
decay_mult: 1
|
1351 |
+
}
|
1352 |
+
param {
|
1353 |
+
lr_mult: 2
|
1354 |
+
decay_mult: 0
|
1355 |
+
}
|
1356 |
+
convolution_param {
|
1357 |
+
num_output: 24
|
1358 |
+
pad: 1
|
1359 |
+
kernel_size: 3
|
1360 |
+
stride: 1
|
1361 |
+
weight_filler {
|
1362 |
+
type: "xavier"
|
1363 |
+
}
|
1364 |
+
bias_filler {
|
1365 |
+
type: "constant"
|
1366 |
+
value: 0
|
1367 |
+
}
|
1368 |
+
}
|
1369 |
+
}
|
1370 |
+
layer {
|
1371 |
+
name: "conv7_2_mbox_loc_perm"
|
1372 |
+
type: "Permute"
|
1373 |
+
bottom: "conv7_2_mbox_loc"
|
1374 |
+
top: "conv7_2_mbox_loc_perm"
|
1375 |
+
permute_param {
|
1376 |
+
order: 0
|
1377 |
+
order: 2
|
1378 |
+
order: 3
|
1379 |
+
order: 1
|
1380 |
+
}
|
1381 |
+
}
|
1382 |
+
layer {
|
1383 |
+
name: "conv7_2_mbox_loc_flat"
|
1384 |
+
type: "Flatten"
|
1385 |
+
bottom: "conv7_2_mbox_loc_perm"
|
1386 |
+
top: "conv7_2_mbox_loc_flat"
|
1387 |
+
flatten_param {
|
1388 |
+
axis: 1
|
1389 |
+
}
|
1390 |
+
}
|
1391 |
+
layer {
|
1392 |
+
name: "conv7_2_mbox_conf"
|
1393 |
+
type: "Convolution"
|
1394 |
+
bottom: "conv7_2_h"
|
1395 |
+
top: "conv7_2_mbox_conf"
|
1396 |
+
param {
|
1397 |
+
lr_mult: 1
|
1398 |
+
decay_mult: 1
|
1399 |
+
}
|
1400 |
+
param {
|
1401 |
+
lr_mult: 2
|
1402 |
+
decay_mult: 0
|
1403 |
+
}
|
1404 |
+
convolution_param {
|
1405 |
+
num_output: 12 # 126
|
1406 |
+
pad: 1
|
1407 |
+
kernel_size: 3
|
1408 |
+
stride: 1
|
1409 |
+
weight_filler {
|
1410 |
+
type: "xavier"
|
1411 |
+
}
|
1412 |
+
bias_filler {
|
1413 |
+
type: "constant"
|
1414 |
+
value: 0
|
1415 |
+
}
|
1416 |
+
}
|
1417 |
+
}
|
1418 |
+
layer {
|
1419 |
+
name: "conv7_2_mbox_conf_perm"
|
1420 |
+
type: "Permute"
|
1421 |
+
bottom: "conv7_2_mbox_conf"
|
1422 |
+
top: "conv7_2_mbox_conf_perm"
|
1423 |
+
permute_param {
|
1424 |
+
order: 0
|
1425 |
+
order: 2
|
1426 |
+
order: 3
|
1427 |
+
order: 1
|
1428 |
+
}
|
1429 |
+
}
|
1430 |
+
layer {
|
1431 |
+
name: "conv7_2_mbox_conf_flat"
|
1432 |
+
type: "Flatten"
|
1433 |
+
bottom: "conv7_2_mbox_conf_perm"
|
1434 |
+
top: "conv7_2_mbox_conf_flat"
|
1435 |
+
flatten_param {
|
1436 |
+
axis: 1
|
1437 |
+
}
|
1438 |
+
}
|
1439 |
+
layer {
|
1440 |
+
name: "conv7_2_mbox_priorbox"
|
1441 |
+
type: "PriorBox"
|
1442 |
+
bottom: "conv7_2_h"
|
1443 |
+
bottom: "data"
|
1444 |
+
top: "conv7_2_mbox_priorbox"
|
1445 |
+
prior_box_param {
|
1446 |
+
min_size: 162.0
|
1447 |
+
max_size: 213.0
|
1448 |
+
aspect_ratio: 2
|
1449 |
+
aspect_ratio: 3
|
1450 |
+
flip: true
|
1451 |
+
clip: false
|
1452 |
+
variance: 0.1
|
1453 |
+
variance: 0.1
|
1454 |
+
variance: 0.2
|
1455 |
+
variance: 0.2
|
1456 |
+
step: 64
|
1457 |
+
offset: 0.5
|
1458 |
+
}
|
1459 |
+
}
|
1460 |
+
layer {
|
1461 |
+
name: "conv8_2_mbox_loc"
|
1462 |
+
type: "Convolution"
|
1463 |
+
bottom: "conv8_2_h"
|
1464 |
+
top: "conv8_2_mbox_loc"
|
1465 |
+
param {
|
1466 |
+
lr_mult: 1
|
1467 |
+
decay_mult: 1
|
1468 |
+
}
|
1469 |
+
param {
|
1470 |
+
lr_mult: 2
|
1471 |
+
decay_mult: 0
|
1472 |
+
}
|
1473 |
+
convolution_param {
|
1474 |
+
num_output: 16
|
1475 |
+
pad: 1
|
1476 |
+
kernel_size: 3
|
1477 |
+
stride: 1
|
1478 |
+
weight_filler {
|
1479 |
+
type: "xavier"
|
1480 |
+
}
|
1481 |
+
bias_filler {
|
1482 |
+
type: "constant"
|
1483 |
+
value: 0
|
1484 |
+
}
|
1485 |
+
}
|
1486 |
+
}
|
1487 |
+
layer {
|
1488 |
+
name: "conv8_2_mbox_loc_perm"
|
1489 |
+
type: "Permute"
|
1490 |
+
bottom: "conv8_2_mbox_loc"
|
1491 |
+
top: "conv8_2_mbox_loc_perm"
|
1492 |
+
permute_param {
|
1493 |
+
order: 0
|
1494 |
+
order: 2
|
1495 |
+
order: 3
|
1496 |
+
order: 1
|
1497 |
+
}
|
1498 |
+
}
|
1499 |
+
layer {
|
1500 |
+
name: "conv8_2_mbox_loc_flat"
|
1501 |
+
type: "Flatten"
|
1502 |
+
bottom: "conv8_2_mbox_loc_perm"
|
1503 |
+
top: "conv8_2_mbox_loc_flat"
|
1504 |
+
flatten_param {
|
1505 |
+
axis: 1
|
1506 |
+
}
|
1507 |
+
}
|
1508 |
+
layer {
|
1509 |
+
name: "conv8_2_mbox_conf"
|
1510 |
+
type: "Convolution"
|
1511 |
+
bottom: "conv8_2_h"
|
1512 |
+
top: "conv8_2_mbox_conf"
|
1513 |
+
param {
|
1514 |
+
lr_mult: 1
|
1515 |
+
decay_mult: 1
|
1516 |
+
}
|
1517 |
+
param {
|
1518 |
+
lr_mult: 2
|
1519 |
+
decay_mult: 0
|
1520 |
+
}
|
1521 |
+
convolution_param {
|
1522 |
+
num_output: 8 # 84
|
1523 |
+
pad: 1
|
1524 |
+
kernel_size: 3
|
1525 |
+
stride: 1
|
1526 |
+
weight_filler {
|
1527 |
+
type: "xavier"
|
1528 |
+
}
|
1529 |
+
bias_filler {
|
1530 |
+
type: "constant"
|
1531 |
+
value: 0
|
1532 |
+
}
|
1533 |
+
}
|
1534 |
+
}
|
1535 |
+
layer {
|
1536 |
+
name: "conv8_2_mbox_conf_perm"
|
1537 |
+
type: "Permute"
|
1538 |
+
bottom: "conv8_2_mbox_conf"
|
1539 |
+
top: "conv8_2_mbox_conf_perm"
|
1540 |
+
permute_param {
|
1541 |
+
order: 0
|
1542 |
+
order: 2
|
1543 |
+
order: 3
|
1544 |
+
order: 1
|
1545 |
+
}
|
1546 |
+
}
|
1547 |
+
layer {
|
1548 |
+
name: "conv8_2_mbox_conf_flat"
|
1549 |
+
type: "Flatten"
|
1550 |
+
bottom: "conv8_2_mbox_conf_perm"
|
1551 |
+
top: "conv8_2_mbox_conf_flat"
|
1552 |
+
flatten_param {
|
1553 |
+
axis: 1
|
1554 |
+
}
|
1555 |
+
}
|
1556 |
+
layer {
|
1557 |
+
name: "conv8_2_mbox_priorbox"
|
1558 |
+
type: "PriorBox"
|
1559 |
+
bottom: "conv8_2_h"
|
1560 |
+
bottom: "data"
|
1561 |
+
top: "conv8_2_mbox_priorbox"
|
1562 |
+
prior_box_param {
|
1563 |
+
min_size: 213.0
|
1564 |
+
max_size: 264.0
|
1565 |
+
aspect_ratio: 2
|
1566 |
+
flip: true
|
1567 |
+
clip: false
|
1568 |
+
variance: 0.1
|
1569 |
+
variance: 0.1
|
1570 |
+
variance: 0.2
|
1571 |
+
variance: 0.2
|
1572 |
+
step: 100
|
1573 |
+
offset: 0.5
|
1574 |
+
}
|
1575 |
+
}
|
1576 |
+
layer {
|
1577 |
+
name: "conv9_2_mbox_loc"
|
1578 |
+
type: "Convolution"
|
1579 |
+
bottom: "conv9_2_h"
|
1580 |
+
top: "conv9_2_mbox_loc"
|
1581 |
+
param {
|
1582 |
+
lr_mult: 1
|
1583 |
+
decay_mult: 1
|
1584 |
+
}
|
1585 |
+
param {
|
1586 |
+
lr_mult: 2
|
1587 |
+
decay_mult: 0
|
1588 |
+
}
|
1589 |
+
convolution_param {
|
1590 |
+
num_output: 16
|
1591 |
+
pad: 1
|
1592 |
+
kernel_size: 3
|
1593 |
+
stride: 1
|
1594 |
+
weight_filler {
|
1595 |
+
type: "xavier"
|
1596 |
+
}
|
1597 |
+
bias_filler {
|
1598 |
+
type: "constant"
|
1599 |
+
value: 0
|
1600 |
+
}
|
1601 |
+
}
|
1602 |
+
}
|
1603 |
+
layer {
|
1604 |
+
name: "conv9_2_mbox_loc_perm"
|
1605 |
+
type: "Permute"
|
1606 |
+
bottom: "conv9_2_mbox_loc"
|
1607 |
+
top: "conv9_2_mbox_loc_perm"
|
1608 |
+
permute_param {
|
1609 |
+
order: 0
|
1610 |
+
order: 2
|
1611 |
+
order: 3
|
1612 |
+
order: 1
|
1613 |
+
}
|
1614 |
+
}
|
1615 |
+
layer {
|
1616 |
+
name: "conv9_2_mbox_loc_flat"
|
1617 |
+
type: "Flatten"
|
1618 |
+
bottom: "conv9_2_mbox_loc_perm"
|
1619 |
+
top: "conv9_2_mbox_loc_flat"
|
1620 |
+
flatten_param {
|
1621 |
+
axis: 1
|
1622 |
+
}
|
1623 |
+
}
|
1624 |
+
layer {
|
1625 |
+
name: "conv9_2_mbox_conf"
|
1626 |
+
type: "Convolution"
|
1627 |
+
bottom: "conv9_2_h"
|
1628 |
+
top: "conv9_2_mbox_conf"
|
1629 |
+
param {
|
1630 |
+
lr_mult: 1
|
1631 |
+
decay_mult: 1
|
1632 |
+
}
|
1633 |
+
param {
|
1634 |
+
lr_mult: 2
|
1635 |
+
decay_mult: 0
|
1636 |
+
}
|
1637 |
+
convolution_param {
|
1638 |
+
num_output: 8 # 84
|
1639 |
+
pad: 1
|
1640 |
+
kernel_size: 3
|
1641 |
+
stride: 1
|
1642 |
+
weight_filler {
|
1643 |
+
type: "xavier"
|
1644 |
+
}
|
1645 |
+
bias_filler {
|
1646 |
+
type: "constant"
|
1647 |
+
value: 0
|
1648 |
+
}
|
1649 |
+
}
|
1650 |
+
}
|
1651 |
+
layer {
|
1652 |
+
name: "conv9_2_mbox_conf_perm"
|
1653 |
+
type: "Permute"
|
1654 |
+
bottom: "conv9_2_mbox_conf"
|
1655 |
+
top: "conv9_2_mbox_conf_perm"
|
1656 |
+
permute_param {
|
1657 |
+
order: 0
|
1658 |
+
order: 2
|
1659 |
+
order: 3
|
1660 |
+
order: 1
|
1661 |
+
}
|
1662 |
+
}
|
1663 |
+
layer {
|
1664 |
+
name: "conv9_2_mbox_conf_flat"
|
1665 |
+
type: "Flatten"
|
1666 |
+
bottom: "conv9_2_mbox_conf_perm"
|
1667 |
+
top: "conv9_2_mbox_conf_flat"
|
1668 |
+
flatten_param {
|
1669 |
+
axis: 1
|
1670 |
+
}
|
1671 |
+
}
|
1672 |
+
layer {
|
1673 |
+
name: "conv9_2_mbox_priorbox"
|
1674 |
+
type: "PriorBox"
|
1675 |
+
bottom: "conv9_2_h"
|
1676 |
+
bottom: "data"
|
1677 |
+
top: "conv9_2_mbox_priorbox"
|
1678 |
+
prior_box_param {
|
1679 |
+
min_size: 264.0
|
1680 |
+
max_size: 315.0
|
1681 |
+
aspect_ratio: 2
|
1682 |
+
flip: true
|
1683 |
+
clip: false
|
1684 |
+
variance: 0.1
|
1685 |
+
variance: 0.1
|
1686 |
+
variance: 0.2
|
1687 |
+
variance: 0.2
|
1688 |
+
step: 300
|
1689 |
+
offset: 0.5
|
1690 |
+
}
|
1691 |
+
}
|
1692 |
+
layer {
|
1693 |
+
name: "mbox_loc"
|
1694 |
+
type: "Concat"
|
1695 |
+
bottom: "conv4_3_norm_mbox_loc_flat"
|
1696 |
+
bottom: "fc7_mbox_loc_flat"
|
1697 |
+
bottom: "conv6_2_mbox_loc_flat"
|
1698 |
+
bottom: "conv7_2_mbox_loc_flat"
|
1699 |
+
bottom: "conv8_2_mbox_loc_flat"
|
1700 |
+
bottom: "conv9_2_mbox_loc_flat"
|
1701 |
+
top: "mbox_loc"
|
1702 |
+
concat_param {
|
1703 |
+
axis: 1
|
1704 |
+
}
|
1705 |
+
}
|
1706 |
+
layer {
|
1707 |
+
name: "mbox_conf"
|
1708 |
+
type: "Concat"
|
1709 |
+
bottom: "conv4_3_norm_mbox_conf_flat"
|
1710 |
+
bottom: "fc7_mbox_conf_flat"
|
1711 |
+
bottom: "conv6_2_mbox_conf_flat"
|
1712 |
+
bottom: "conv7_2_mbox_conf_flat"
|
1713 |
+
bottom: "conv8_2_mbox_conf_flat"
|
1714 |
+
bottom: "conv9_2_mbox_conf_flat"
|
1715 |
+
top: "mbox_conf"
|
1716 |
+
concat_param {
|
1717 |
+
axis: 1
|
1718 |
+
}
|
1719 |
+
}
|
1720 |
+
layer {
|
1721 |
+
name: "mbox_priorbox"
|
1722 |
+
type: "Concat"
|
1723 |
+
bottom: "conv4_3_norm_mbox_priorbox"
|
1724 |
+
bottom: "fc7_mbox_priorbox"
|
1725 |
+
bottom: "conv6_2_mbox_priorbox"
|
1726 |
+
bottom: "conv7_2_mbox_priorbox"
|
1727 |
+
bottom: "conv8_2_mbox_priorbox"
|
1728 |
+
bottom: "conv9_2_mbox_priorbox"
|
1729 |
+
top: "mbox_priorbox"
|
1730 |
+
concat_param {
|
1731 |
+
axis: 2
|
1732 |
+
}
|
1733 |
+
}
|
1734 |
+
|
1735 |
+
layer {
|
1736 |
+
name: "mbox_conf_reshape"
|
1737 |
+
type: "Reshape"
|
1738 |
+
bottom: "mbox_conf"
|
1739 |
+
top: "mbox_conf_reshape"
|
1740 |
+
reshape_param {
|
1741 |
+
shape {
|
1742 |
+
dim: 0
|
1743 |
+
dim: -1
|
1744 |
+
dim: 2
|
1745 |
+
}
|
1746 |
+
}
|
1747 |
+
}
|
1748 |
+
layer {
|
1749 |
+
name: "mbox_conf_softmax"
|
1750 |
+
type: "Softmax"
|
1751 |
+
bottom: "mbox_conf_reshape"
|
1752 |
+
top: "mbox_conf_softmax"
|
1753 |
+
softmax_param {
|
1754 |
+
axis: 2
|
1755 |
+
}
|
1756 |
+
}
|
1757 |
+
layer {
|
1758 |
+
name: "mbox_conf_flatten"
|
1759 |
+
type: "Flatten"
|
1760 |
+
bottom: "mbox_conf_softmax"
|
1761 |
+
top: "mbox_conf_flatten"
|
1762 |
+
flatten_param {
|
1763 |
+
axis: 1
|
1764 |
+
}
|
1765 |
+
}
|
1766 |
+
|
1767 |
+
layer {
|
1768 |
+
name: "detection_out"
|
1769 |
+
type: "DetectionOutput"
|
1770 |
+
bottom: "mbox_loc"
|
1771 |
+
bottom: "mbox_conf_flatten"
|
1772 |
+
bottom: "mbox_priorbox"
|
1773 |
+
top: "detection_out"
|
1774 |
+
include {
|
1775 |
+
phase: TEST
|
1776 |
+
}
|
1777 |
+
detection_output_param {
|
1778 |
+
num_classes: 2
|
1779 |
+
share_location: true
|
1780 |
+
background_label_id: 0
|
1781 |
+
nms_param {
|
1782 |
+
nms_threshold: 0.3
|
1783 |
+
top_k: 400
|
1784 |
+
}
|
1785 |
+
code_type: CENTER_SIZE
|
1786 |
+
keep_top_k: 200
|
1787 |
+
confidence_threshold: 0.01
|
1788 |
+
}
|
1789 |
+
}
|
download_models.py
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import os
|
2 |
+
import re
|
3 |
+
import cv2
|
4 |
+
import numpy as np
|
5 |
+
import io
|
6 |
+
import sys
|
7 |
+
import numpy as np
|
8 |
+
import timm
|
9 |
+
import pyiqa
|
10 |
+
import torch
|
11 |
+
from transformers import DonutProcessor, VisionEncoderDecoderModel
|
12 |
+
|
13 |
+
|
14 |
+
device = "cuda" if torch.cuda.is_available() else "cpu"
|
15 |
+
|
16 |
+
licence_model = torch.hub.load(
|
17 |
+
"ultralytics/yolov5", "custom", path="Licenseplate_model.pt", device="cpu", force_reload=True
|
18 |
+
)
|
19 |
+
licence_model.cpu()
|
20 |
+
|
21 |
+
detector = cv2.dnn.DetectionModel("res10_300x300_ssd_iter_140000_fp16.caffemodel", "deploy.prototxt")
|
22 |
+
|
23 |
+
processor = DonutProcessor.from_pretrained("naver-clova-ix/donut-base-finetuned-docvqa")
|
24 |
+
doc_qa_model = VisionEncoderDecoderModel.from_pretrained("naver-clova-ix/donut-base-finetuned-docvqa")
|
25 |
+
|
26 |
+
device = "cuda" if torch.cuda.is_available() else "cpu"
|
27 |
+
doc_qa_model.to(device)
|
28 |
+
|
29 |
+
model = torch.hub.load(
|
30 |
+
"ultralytics/yolov5", "custom", path="best.pt", device="cpu", force_reload=True
|
31 |
+
)
|
32 |
+
model.cpu()
|
33 |
+
|
34 |
+
classes = [
|
35 |
+
"gas-distribution-meter",
|
36 |
+
"gas-distribution-piping",
|
37 |
+
"gas-distribution-regulator",
|
38 |
+
"gas-distribution-valve"
|
39 |
+
]
|
40 |
+
|
41 |
+
class_to_idx = {'gas-distribution-meter': 0,
|
42 |
+
'gas-distribution-piping': 1,
|
43 |
+
'gas-distribution-regulator': 2,
|
44 |
+
'gas-distribution-valve': 3}
|
45 |
+
|
46 |
+
idx_to_classes = {v:k for k,v in class_to_idx.items()}
|
47 |
+
modelname = "resnet50d"
|
48 |
+
model_weights = "best_classifer_model.pt"
|
49 |
+
num_classes = len(classes)
|
50 |
+
|
51 |
+
classifier_model = timm.create_model(
|
52 |
+
"resnet50d", pretrained=True, num_classes=num_classes, drop_path_rate=0.05
|
53 |
+
)
|
54 |
+
classifier_model.load_state_dict(torch.load(model_weights, map_location=torch.device('cpu'))["model_state_dict"])
|
55 |
+
|
56 |
+
musiq_metric = pyiqa.create_metric('musiq-koniq', device=torch.device('cpu'))
|
requirements.txt
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# YOLOv5 requirements
|
2 |
+
# Usage: pip install -r requirements.txt
|
3 |
+
|
4 |
+
# Base ------------------------------------------------------------------------
|
5 |
+
gitpython
|
6 |
+
ipython # interactive notebook
|
7 |
+
matplotlib>=3.2.2
|
8 |
+
numpy>=1.18.5
|
9 |
+
opencv-python>=4.1.1
|
10 |
+
Pillow>=7.1.2
|
11 |
+
psutil # system resources
|
12 |
+
PyYAML>=5.3.1
|
13 |
+
requests>=2.23.0
|
14 |
+
scipy>=1.4.1
|
15 |
+
thop>=0.1.1 # FLOPs computation
|
16 |
+
torch>=1.7.0 # see https://pytorch.org/get-started/locally (recommended)
|
17 |
+
torchvision>=0.8.1
|
18 |
+
tqdm>=4.64.0
|
19 |
+
# protobuf<=3.20.1 # https://github.com/ultralytics/yolov5/issues/8012
|
20 |
+
fastapi
|
21 |
+
python-multipart
|
22 |
+
uvicorn
|
23 |
+
timm==0.5.4
|
24 |
+
pytorch-accelerated
|
25 |
+
tensorflow-hub
|
26 |
+
pyiqa
|
27 |
+
protobuf==3.20.*
|
28 |
+
transformers
|
29 |
+
sentencepiece
|
30 |
+
sentence-transformers
|
31 |
+
# Logging ---------------------------------------------------------------------
|
32 |
+
tensorboard>=2.4.1
|
33 |
+
# clearml>=1.2.0
|
34 |
+
# comet
|
35 |
+
|
36 |
+
# Plotting --------------------------------------------------------------------
|
37 |
+
pandas>=1.1.4
|
38 |
+
seaborn>=0.11.0
|
39 |
+
pinecone-client
|
40 |
+
python-dotenv
|
41 |
+
# Export ----------------------------------------------------------------------
|
42 |
+
coremltools>=6.0 # CoreML export
|
43 |
+
onnx>=1.12.0 # ONNX export
|
44 |
+
onnx-simplifier>=0.4.1 # ONNX simplifier
|
45 |
+
# nvidia-pyindex # TensorRT export
|
46 |
+
# nvidia-tensorrt # TensorRT export
|
47 |
+
scikit-learn<=1.1.2 # CoreML quantization
|
48 |
+
tensorflow>=2.4.1 # TF exports (-cpu, -aarch64, -macos)
|
49 |
+
# tensorflowjs>=3.9.0 # TF.js export
|
50 |
+
# openvino-dev # OpenVINO export
|
51 |
+
|
52 |
+
# Deploy ----------------------------------------------------------------------
|
53 |
+
# tritonclient[all]~=2.24.0
|
54 |
+
|
55 |
+
# Extras ----------------------------------------------------------------------
|
56 |
+
# mss # screenshots
|
57 |
+
albumentations>=1.0.3
|
58 |
+
pycocotools>=2.0.6 # COCO mAP
|
59 |
+
# roboflow
|
60 |
+
ultralytics # HUB https://hub.ultralytics.com
|
res10_300x300_ssd_iter_140000_fp16.caffemodel
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:510ffd2471bd81e3fcc88a5beb4eae4fb445ccf8333ebc54e7302b83f4158a76
|
3 |
+
size 5351047
|
run_cmds.txt
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
docker build -t abhi001vj/object_detection_backend .
|
2 |
+
sudo kill -9 $(sudo lsof -t -i:8000)
|
3 |
+
docker run -p 8000:8000 abhi001vj/object_detection_backend
|
4 |
+
|
5 |
+
uvicorn app:app --port 8000 --reload
|