fafdasdf
Browse files- FacePass.py +23 -0
- ReadMe.md +14 -0
- app.py +49 -0
- coco.names +80 -0
- configs/yolov3-tiny.cfg +182 -0
- database/__pycache__/retriever.cpython-312.pyc +0 -0
- database/__pycache__/utils.cpython-312.pyc +0 -0
- database/retriever.py +51 -0
- database/utils.py +7 -0
- logo.png +0 -0
- main.py +0 -0
- models/best.pt +3 -0
- models/vgg_face_dag.pth +3 -0
- refs.txt +8 -0
- requirements.txt +53 -0
- temp.jpg +0 -0
- vgg/__pycache__/vgg_face.cpython-312.pyc +0 -0
- vgg/vgg19.py +76 -0
- vgg/vgg_face.py +117 -0
- yolo/__pycache__/yoloFace.cpython-312.pyc +0 -0
- yolo/yolo.py +92 -0
- yolo/yoloFace.py +25 -0
FacePass.py
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from yolo.yoloFace import YOLO_FACE
|
2 |
+
from vgg.vgg_face import MODEL_FACE
|
3 |
+
from database.retriever import BruteForceStore
|
4 |
+
import cv2
|
5 |
+
|
6 |
+
|
7 |
+
DB = BruteForceStore()
|
8 |
+
|
9 |
+
def pipeline(img):
|
10 |
+
|
11 |
+
images = YOLO_FACE(img)
|
12 |
+
for patch in images:
|
13 |
+
embeddings = MODEL_FACE(patch)
|
14 |
+
if DB(embeddings): return "Welcome!"
|
15 |
+
|
16 |
+
return "Buzz off!!! petrichor me chor"
|
17 |
+
|
18 |
+
if __name__ == "__main__":
|
19 |
+
|
20 |
+
import cv2
|
21 |
+
|
22 |
+
img = cv2.imread('temp.jpg', cv2.IMREAD_UNCHANGED)
|
23 |
+
print(pipeline(img))
|
ReadMe.md
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
## How to run:
|
2 |
+
Be in root directory: FacePass/
|
3 |
+
1. pip install -r requirements.txt to install all requirements. Python 3.12 recommended
|
4 |
+
2. Create a folder named models and add your images into it
|
5 |
+
3. Download the models from the links given in refs.txt and add them in models
|
6 |
+
4. To run the program: python3 FacePass.py
|
7 |
+
|
8 |
+
## Additional Instruction:
|
9 |
+
When taking images to store in database please remove your glasses. Similarly when unlocking the facelock remove your glasses
|
10 |
+
|
11 |
+
## Future work:
|
12 |
+
1. Make a better database or use existing ones like FAISS
|
13 |
+
2. Make a user interface so that the adminstrator can registor new users into the database
|
14 |
+
3. For now the threshold value seems to be working fine but further tweaking and fine tuning is required
|
app.py
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
from yolo.yoloFace import YOLO_FACE
|
3 |
+
from vgg.vgg_face import MODEL_FACE
|
4 |
+
from database.retriever import BruteForceStore
|
5 |
+
import cv2
|
6 |
+
|
7 |
+
# Initialize the database
|
8 |
+
DB = BruteForceStore()
|
9 |
+
|
10 |
+
def pipeline(img):
|
11 |
+
images = YOLO_FACE(img)
|
12 |
+
for patch in images:
|
13 |
+
embeddings = MODEL_FACE(patch)
|
14 |
+
if DB(embeddings):
|
15 |
+
return "Welcome!"
|
16 |
+
return "Unauthorised"
|
17 |
+
|
18 |
+
# Define a Gradio interface
|
19 |
+
def process_image(image):
|
20 |
+
if image is None:
|
21 |
+
return "Please upload an image."
|
22 |
+
result = pipeline(image)
|
23 |
+
return result
|
24 |
+
|
25 |
+
# Gradio App
|
26 |
+
with gr.Blocks() as demo:
|
27 |
+
gr.Markdown("""
|
28 |
+
<div style="background: url('/home/asad/temp/app/FacePass/logo.png') no-repeat center center fixed; background-size: cover; height: 100%; padding: 20px; display: flex; flex-direction: column; justify-content: center; align-items: center;">
|
29 |
+
<h1 style="text-align: center; color: white;">
|
30 |
+
Face Verification App
|
31 |
+
</h1>
|
32 |
+
<h3 style="text-align: center; color: lightgrey;">
|
33 |
+
Upload your photo and let the app verify your identity!
|
34 |
+
</h3>
|
35 |
+
</div>
|
36 |
+
""")
|
37 |
+
|
38 |
+
with gr.Row():
|
39 |
+
with gr.Column(scale=1):
|
40 |
+
image_input = gr.Image(type="numpy", label="Upload Your Image")
|
41 |
+
with gr.Column(scale=1):
|
42 |
+
output_text = gr.Textbox(label="Verification Result", interactive=False)
|
43 |
+
|
44 |
+
with gr.Row():
|
45 |
+
submit_button = gr.Button("Verify")
|
46 |
+
submit_button.click(process_image, inputs=[image_input], outputs=[output_text])
|
47 |
+
|
48 |
+
if __name__ == "__main__":
|
49 |
+
demo.launch()
|
coco.names
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
person
|
2 |
+
bicycle
|
3 |
+
car
|
4 |
+
motorbike
|
5 |
+
aeroplane
|
6 |
+
bus
|
7 |
+
train
|
8 |
+
truck
|
9 |
+
boat
|
10 |
+
traffic light
|
11 |
+
fire hydrant
|
12 |
+
stop sign
|
13 |
+
parking meter
|
14 |
+
bench
|
15 |
+
bird
|
16 |
+
cat
|
17 |
+
dog
|
18 |
+
horse
|
19 |
+
sheep
|
20 |
+
cow
|
21 |
+
elephant
|
22 |
+
bear
|
23 |
+
zebra
|
24 |
+
giraffe
|
25 |
+
backpack
|
26 |
+
umbrella
|
27 |
+
handbag
|
28 |
+
tie
|
29 |
+
suitcase
|
30 |
+
frisbee
|
31 |
+
skis
|
32 |
+
snowboard
|
33 |
+
sports ball
|
34 |
+
kite
|
35 |
+
baseball bat
|
36 |
+
baseball glove
|
37 |
+
skateboard
|
38 |
+
surfboard
|
39 |
+
tennis racket
|
40 |
+
bottle
|
41 |
+
wine glass
|
42 |
+
cup
|
43 |
+
fork
|
44 |
+
knife
|
45 |
+
spoon
|
46 |
+
bowl
|
47 |
+
banana
|
48 |
+
apple
|
49 |
+
sandwich
|
50 |
+
orange
|
51 |
+
broccoli
|
52 |
+
carrot
|
53 |
+
hot dog
|
54 |
+
pizza
|
55 |
+
donut
|
56 |
+
cake
|
57 |
+
chair
|
58 |
+
sofa
|
59 |
+
pottedplant
|
60 |
+
bed
|
61 |
+
diningtable
|
62 |
+
toilet
|
63 |
+
tvmonitor
|
64 |
+
laptop
|
65 |
+
mouse
|
66 |
+
remote
|
67 |
+
keyboard
|
68 |
+
cell phone
|
69 |
+
microwave
|
70 |
+
oven
|
71 |
+
toaster
|
72 |
+
sink
|
73 |
+
refrigerator
|
74 |
+
book
|
75 |
+
clock
|
76 |
+
vase
|
77 |
+
scissors
|
78 |
+
teddy bear
|
79 |
+
hair drier
|
80 |
+
toothbrush
|
configs/yolov3-tiny.cfg
ADDED
@@ -0,0 +1,182 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
# Testing
|
3 |
+
batch=1
|
4 |
+
subdivisions=1
|
5 |
+
# Training
|
6 |
+
# batch=64
|
7 |
+
# subdivisions=2
|
8 |
+
width=416
|
9 |
+
height=416
|
10 |
+
channels=3
|
11 |
+
momentum=0.9
|
12 |
+
decay=0.0005
|
13 |
+
angle=0
|
14 |
+
saturation = 1.5
|
15 |
+
exposure = 1.5
|
16 |
+
hue=.1
|
17 |
+
|
18 |
+
learning_rate=0.001
|
19 |
+
burn_in=1000
|
20 |
+
max_batches = 500200
|
21 |
+
policy=steps
|
22 |
+
steps=400000,450000
|
23 |
+
scales=.1,.1
|
24 |
+
|
25 |
+
[convolutional]
|
26 |
+
batch_normalize=1
|
27 |
+
filters=16
|
28 |
+
size=3
|
29 |
+
stride=1
|
30 |
+
pad=1
|
31 |
+
activation=leaky
|
32 |
+
|
33 |
+
[maxpool]
|
34 |
+
size=2
|
35 |
+
stride=2
|
36 |
+
|
37 |
+
[convolutional]
|
38 |
+
batch_normalize=1
|
39 |
+
filters=32
|
40 |
+
size=3
|
41 |
+
stride=1
|
42 |
+
pad=1
|
43 |
+
activation=leaky
|
44 |
+
|
45 |
+
[maxpool]
|
46 |
+
size=2
|
47 |
+
stride=2
|
48 |
+
|
49 |
+
[convolutional]
|
50 |
+
batch_normalize=1
|
51 |
+
filters=64
|
52 |
+
size=3
|
53 |
+
stride=1
|
54 |
+
pad=1
|
55 |
+
activation=leaky
|
56 |
+
|
57 |
+
[maxpool]
|
58 |
+
size=2
|
59 |
+
stride=2
|
60 |
+
|
61 |
+
[convolutional]
|
62 |
+
batch_normalize=1
|
63 |
+
filters=128
|
64 |
+
size=3
|
65 |
+
stride=1
|
66 |
+
pad=1
|
67 |
+
activation=leaky
|
68 |
+
|
69 |
+
[maxpool]
|
70 |
+
size=2
|
71 |
+
stride=2
|
72 |
+
|
73 |
+
[convolutional]
|
74 |
+
batch_normalize=1
|
75 |
+
filters=256
|
76 |
+
size=3
|
77 |
+
stride=1
|
78 |
+
pad=1
|
79 |
+
activation=leaky
|
80 |
+
|
81 |
+
[maxpool]
|
82 |
+
size=2
|
83 |
+
stride=2
|
84 |
+
|
85 |
+
[convolutional]
|
86 |
+
batch_normalize=1
|
87 |
+
filters=512
|
88 |
+
size=3
|
89 |
+
stride=1
|
90 |
+
pad=1
|
91 |
+
activation=leaky
|
92 |
+
|
93 |
+
[maxpool]
|
94 |
+
size=2
|
95 |
+
stride=1
|
96 |
+
|
97 |
+
[convolutional]
|
98 |
+
batch_normalize=1
|
99 |
+
filters=1024
|
100 |
+
size=3
|
101 |
+
stride=1
|
102 |
+
pad=1
|
103 |
+
activation=leaky
|
104 |
+
|
105 |
+
###########
|
106 |
+
|
107 |
+
[convolutional]
|
108 |
+
batch_normalize=1
|
109 |
+
filters=256
|
110 |
+
size=1
|
111 |
+
stride=1
|
112 |
+
pad=1
|
113 |
+
activation=leaky
|
114 |
+
|
115 |
+
[convolutional]
|
116 |
+
batch_normalize=1
|
117 |
+
filters=512
|
118 |
+
size=3
|
119 |
+
stride=1
|
120 |
+
pad=1
|
121 |
+
activation=leaky
|
122 |
+
|
123 |
+
[convolutional]
|
124 |
+
size=1
|
125 |
+
stride=1
|
126 |
+
pad=1
|
127 |
+
filters=255
|
128 |
+
activation=linear
|
129 |
+
|
130 |
+
|
131 |
+
|
132 |
+
[yolo]
|
133 |
+
mask = 3,4,5
|
134 |
+
anchors = 10,14, 23,27, 37,58, 81,82, 135,169, 344,319
|
135 |
+
classes=80
|
136 |
+
num=6
|
137 |
+
jitter=.3
|
138 |
+
ignore_thresh = .7
|
139 |
+
truth_thresh = 1
|
140 |
+
random=1
|
141 |
+
|
142 |
+
[route]
|
143 |
+
layers = -4
|
144 |
+
|
145 |
+
[convolutional]
|
146 |
+
batch_normalize=1
|
147 |
+
filters=128
|
148 |
+
size=1
|
149 |
+
stride=1
|
150 |
+
pad=1
|
151 |
+
activation=leaky
|
152 |
+
|
153 |
+
[upsample]
|
154 |
+
stride=2
|
155 |
+
|
156 |
+
[route]
|
157 |
+
layers = -1, 8
|
158 |
+
|
159 |
+
[convolutional]
|
160 |
+
batch_normalize=1
|
161 |
+
filters=256
|
162 |
+
size=3
|
163 |
+
stride=1
|
164 |
+
pad=1
|
165 |
+
activation=leaky
|
166 |
+
|
167 |
+
[convolutional]
|
168 |
+
size=1
|
169 |
+
stride=1
|
170 |
+
pad=1
|
171 |
+
filters=255
|
172 |
+
activation=linear
|
173 |
+
|
174 |
+
[yolo]
|
175 |
+
mask = 0,1,2
|
176 |
+
anchors = 10,14, 23,27, 37,58, 81,82, 135,169, 344,319
|
177 |
+
classes=80
|
178 |
+
num=6
|
179 |
+
jitter=.3
|
180 |
+
ignore_thresh = .7
|
181 |
+
truth_thresh = 1
|
182 |
+
random=1
|
database/__pycache__/retriever.cpython-312.pyc
ADDED
Binary file (3.47 kB). View file
|
|
database/__pycache__/utils.cpython-312.pyc
ADDED
Binary file (666 Bytes). View file
|
|
database/retriever.py
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import os
|
2 |
+
from database.utils import similarity
|
3 |
+
import cv2
|
4 |
+
from vgg.vgg_face import MODEL_FACE
|
5 |
+
from yolo.yoloFace import YOLO_FACE
|
6 |
+
|
7 |
+
class Retriever:
|
8 |
+
"""Base Retriever class"""
|
9 |
+
def __init__(self, thres=0.7, folder_loc="database/images", *args, **kwargs):
|
10 |
+
self.thres = thres
|
11 |
+
self.folder_loc = folder_loc
|
12 |
+
def unlock_lock(self, *args, **kwargs): ...
|
13 |
+
def __call__(self, *args, **kwargs):
|
14 |
+
return self.unlock_lock(*args, **kwargs)
|
15 |
+
|
16 |
+
class Naive(Retriever):
|
17 |
+
def unlock_lock(self, emb):
|
18 |
+
"Kind of Dynamic but very slow"
|
19 |
+
for root, dirs, files in os.walk(self.folder_loc):
|
20 |
+
for file in files:
|
21 |
+
file_path = os.path.join(root, file)
|
22 |
+
image = cv2.imread(file_path)
|
23 |
+
for patch in YOLO_FACE(image):
|
24 |
+
embedding = MODEL_FACE(patch)
|
25 |
+
if similarity(emb, embedding) > self.thres:
|
26 |
+
return True
|
27 |
+
return False
|
28 |
+
|
29 |
+
class BruteForceStore(Retriever):
|
30 |
+
def __init__(self, *args, **kwargs):
|
31 |
+
"""
|
32 |
+
Watch dog integration required later
|
33 |
+
Only Use when the number of images are less
|
34 |
+
"""
|
35 |
+
super().__init__(*args, **kwargs)
|
36 |
+
self.embeddings = []
|
37 |
+
for root, dirs, files in os.walk(self.folder_loc):
|
38 |
+
for file in files:
|
39 |
+
file_path = os.path.join(root, file)
|
40 |
+
image = cv2.imread(file_path)
|
41 |
+
for patch in YOLO_FACE(image):
|
42 |
+
embedding = MODEL_FACE(patch)
|
43 |
+
self.embeddings.append(embedding)
|
44 |
+
|
45 |
+
def unlock_lock(self, emb):
|
46 |
+
"""Only Use when the number of images are less"""
|
47 |
+
for embedding in self.embeddings:
|
48 |
+
print(f"similarity : {similarity(emb, embedding)}")
|
49 |
+
if similarity(emb, embedding) > self.thres:
|
50 |
+
return True
|
51 |
+
return False
|
database/utils.py
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import numpy as np
|
2 |
+
|
3 |
+
def similarity(v1:np.ndarray, v2:np.ndarray):
|
4 |
+
num = (v1 @ v2.T).item()
|
5 |
+
denom = np.linalg.norm(v1) * np.linalg.norm(v2)
|
6 |
+
print(num/denom)
|
7 |
+
return num/denom
|
logo.png
ADDED
![]() |
main.py
ADDED
File without changes
|
models/best.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca9fa06b00e315bcebddff31c899cbed65b44fe548da08ad87d67d629fa760e4
|
3 |
+
size 6197752
|
models/vgg_face_dag.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f070b241e3faf17a08c78f8700d334413230bac5de7fbcfd01b3cf05ce10de1a
|
3 |
+
size 580015466
|
refs.txt
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
references:
|
2 |
+
https://github.com/noorkhokhar99/face-detection-yolov8/blob/main/test_web.py
|
3 |
+
https://www.robots.ox.ac.uk/~albanie/pytorch-models.html
|
4 |
+
|
5 |
+
|
6 |
+
download links:
|
7 |
+
vgg_face: http://www.robots.ox.ac.uk/~albanie/models/pytorch-mcn/vgg_face_dag.pth
|
8 |
+
yolo_face: https://github.com/noorkhokhar99/face-detection-yolov8/blob/main/best.pt
|
requirements.txt
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
certifi==2024.12.14
|
2 |
+
charset-normalizer==3.4.0
|
3 |
+
contourpy==1.3.1
|
4 |
+
cycler==0.12.1
|
5 |
+
filelock==3.16.1
|
6 |
+
fonttools==4.55.3
|
7 |
+
fsspec==2024.10.0
|
8 |
+
idna==3.10
|
9 |
+
Jinja2==3.1.4
|
10 |
+
kiwisolver==1.4.7
|
11 |
+
MarkupSafe==3.0.2
|
12 |
+
matplotlib==3.10.0
|
13 |
+
mpmath==1.3.0
|
14 |
+
networkx==3.4.2
|
15 |
+
numpy==2.2.0
|
16 |
+
nvidia-cublas-cu12==12.4.5.8
|
17 |
+
nvidia-cuda-cupti-cu12==12.4.127
|
18 |
+
nvidia-cuda-nvrtc-cu12==12.4.127
|
19 |
+
nvidia-cuda-runtime-cu12==12.4.127
|
20 |
+
nvidia-cudnn-cu12==9.1.0.70
|
21 |
+
nvidia-cufft-cu12==11.2.1.3
|
22 |
+
nvidia-curand-cu12==10.3.5.147
|
23 |
+
nvidia-cusolver-cu12==11.6.1.9
|
24 |
+
nvidia-cusparse-cu12==12.3.1.170
|
25 |
+
nvidia-nccl-cu12==2.21.5
|
26 |
+
nvidia-nvjitlink-cu12==12.4.127
|
27 |
+
nvidia-nvtx-cu12==12.4.127
|
28 |
+
opencv-python==4.10.0.84
|
29 |
+
packaging==24.2
|
30 |
+
pandas==2.2.3
|
31 |
+
pillow==11.0.0
|
32 |
+
psutil==6.1.0
|
33 |
+
py-cpuinfo==9.0.0
|
34 |
+
pyparsing==3.2.0
|
35 |
+
python-dateutil==2.9.0.post0
|
36 |
+
pytz==2024.2
|
37 |
+
PyYAML==6.0.2
|
38 |
+
requests==2.32.3
|
39 |
+
scipy==1.14.1
|
40 |
+
seaborn==0.13.2
|
41 |
+
setuptools==75.6.0
|
42 |
+
six==1.17.0
|
43 |
+
sympy==1.13.1
|
44 |
+
torch==2.5.1
|
45 |
+
torchvision==0.20.1
|
46 |
+
tqdm==4.67.1
|
47 |
+
triton==3.1.0
|
48 |
+
typing_extensions==4.12.2
|
49 |
+
tzdata==2024.2
|
50 |
+
ultralytics==8.3.51
|
51 |
+
ultralytics-thop==2.0.13
|
52 |
+
urllib3==2.2.3
|
53 |
+
gradio
|
temp.jpg
ADDED
![]() |
vgg/__pycache__/vgg_face.cpython-312.pyc
ADDED
Binary file (7.76 kB). View file
|
|
vgg/vgg19.py
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import torch
|
2 |
+
from torch import nn
|
3 |
+
|
4 |
+
KERNEL_SIZE = (3,3)
|
5 |
+
|
6 |
+
class VGG19(nn.Module):
|
7 |
+
def __init__(self, *args, **kwargs) -> None:
|
8 |
+
super().__init__(*args, **kwargs)
|
9 |
+
self.features = nn.Sequential(
|
10 |
+
nn.Conv2d(3, 64, KERNEL_SIZE, 1, 1),
|
11 |
+
nn.ReLU(),
|
12 |
+
nn.Conv2d(64, 64, KERNEL_SIZE, 1, 1),
|
13 |
+
nn.ReLU(),
|
14 |
+
|
15 |
+
nn.MaxPool2d(2),
|
16 |
+
|
17 |
+
nn.Conv2d(64, 128, KERNEL_SIZE, 1, 1),
|
18 |
+
nn.ReLU(),
|
19 |
+
nn.Conv2d(128, 128, KERNEL_SIZE, 1, 1),
|
20 |
+
nn.ReLU(),
|
21 |
+
|
22 |
+
nn.MaxPool2d(2),
|
23 |
+
|
24 |
+
nn.Conv2d(128, 256, KERNEL_SIZE, 1, 1),
|
25 |
+
nn.ReLU(),
|
26 |
+
nn.Conv2d(256, 256, KERNEL_SIZE, 1, 1),
|
27 |
+
nn.ReLU(),
|
28 |
+
nn.Conv2d(256, 256, KERNEL_SIZE, 1, 1),
|
29 |
+
nn.ReLU(),
|
30 |
+
nn.Conv2d(256, 256, KERNEL_SIZE, 1, 1),
|
31 |
+
nn.ReLU(),
|
32 |
+
|
33 |
+
nn.MaxPool2d(2),
|
34 |
+
|
35 |
+
nn.Conv2d(256, 512, KERNEL_SIZE, 1, 1),
|
36 |
+
nn.ReLU(),
|
37 |
+
nn.Conv2d(512, 512, KERNEL_SIZE, 1, 1),
|
38 |
+
nn.ReLU(),
|
39 |
+
nn.Conv2d(512, 512, KERNEL_SIZE, 1, 1),
|
40 |
+
nn.ReLU(),
|
41 |
+
nn.Conv2d(512, 512, KERNEL_SIZE, 1, 1),
|
42 |
+
nn.ReLU(),
|
43 |
+
|
44 |
+
nn.MaxPool2d(2),
|
45 |
+
|
46 |
+
nn.Conv2d(512, 512, KERNEL_SIZE, 1, 1),
|
47 |
+
nn.ReLU(),
|
48 |
+
nn.Conv2d(512, 512, KERNEL_SIZE, 1, 1),
|
49 |
+
nn.ReLU(),
|
50 |
+
nn.Conv2d(512, 512, KERNEL_SIZE, 1, 1),
|
51 |
+
nn.ReLU(),
|
52 |
+
nn.Conv2d(512, 512, KERNEL_SIZE, 1, 1),
|
53 |
+
nn.ReLU(),
|
54 |
+
|
55 |
+
nn.MaxPool2d(2)
|
56 |
+
)
|
57 |
+
self.classifier = nn.Sequential(
|
58 |
+
nn.Linear(49*512, 4096),
|
59 |
+
nn.ReLU(),
|
60 |
+
nn.Dropout(),
|
61 |
+
nn.Linear(4096, 4096),
|
62 |
+
nn.ReLU(),
|
63 |
+
nn.Dropout(),
|
64 |
+
nn.Linear(4096, 1000),
|
65 |
+
)
|
66 |
+
def forward(self, x:torch.Tensor):
|
67 |
+
x = self.features(x)
|
68 |
+
return self.classifier(x)
|
69 |
+
def embeddings(self, x:torch.Tensor):
|
70 |
+
return self.features(x).flatten().detach().numpy()
|
71 |
+
__call__ = embeddings
|
72 |
+
|
73 |
+
MODEL_19 = VGG19()
|
74 |
+
MODEL_19.load_state_dict(torch.load("models/vgg19-dcbb9e9d.pth"), strict=True)
|
75 |
+
if __name__ == "__main__":
|
76 |
+
print(MODEL_19.state_dict().keys())
|
vgg/vgg_face.py
ADDED
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import torch
|
2 |
+
from torch import nn
|
3 |
+
from warnings import filterwarnings
|
4 |
+
from torchvision.transforms import ToTensor, Resize, Normalize, Compose
|
5 |
+
|
6 |
+
filterwarnings("ignore")
|
7 |
+
|
8 |
+
DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
9 |
+
KERNEL_SIZE = (3,3)
|
10 |
+
|
11 |
+
class VGGFACE(nn.Module):
|
12 |
+
def __init__(self, *args, **kwargs) -> None:
|
13 |
+
super().__init__(*args, **kwargs)
|
14 |
+
self.conv1_1 = nn.Conv2d(3, 64, KERNEL_SIZE, 1, 1)
|
15 |
+
self.conv1_2 = nn.Conv2d(64, 64, KERNEL_SIZE, 1, 1)
|
16 |
+
|
17 |
+
self.conv2_1 = nn.Conv2d(64, 128, KERNEL_SIZE, 1, 1)
|
18 |
+
self.conv2_2 = nn.Conv2d(128, 128, KERNEL_SIZE, 1, 1)
|
19 |
+
|
20 |
+
self.conv3_1 = nn.Conv2d(128, 256, KERNEL_SIZE, 1, 1)
|
21 |
+
self.conv3_2 = nn.Conv2d(256, 256, KERNEL_SIZE, 1, 1)
|
22 |
+
self.conv3_3 = nn.Conv2d(256, 256, KERNEL_SIZE, 1, 1)
|
23 |
+
|
24 |
+
self.conv4_1 = nn.Conv2d(256, 512, KERNEL_SIZE, 1, 1)
|
25 |
+
self.conv4_2 = nn.Conv2d(512, 512, KERNEL_SIZE, 1, 1)
|
26 |
+
self.conv4_3 = nn.Conv2d(512, 512, KERNEL_SIZE, 1, 1)
|
27 |
+
|
28 |
+
self.conv5_1 = nn.Conv2d(512, 512, KERNEL_SIZE, 1, 1)
|
29 |
+
self.conv5_2 = nn.Conv2d(512, 512, KERNEL_SIZE, 1, 1)
|
30 |
+
self.conv5_3 = nn.Conv2d(512, 512, KERNEL_SIZE, 1, 1)
|
31 |
+
|
32 |
+
self.fc6 = nn.Linear(49*512, 4096)
|
33 |
+
self.fc7 = nn.Linear(4096, 4096)
|
34 |
+
self.fc8 = nn.Linear(4096, 2622)
|
35 |
+
self.relu = nn.ReLU()
|
36 |
+
self.maxpool = nn.MaxPool2d(2)
|
37 |
+
|
38 |
+
self._features = [
|
39 |
+
self.conv1_1, self.relu,
|
40 |
+
self.conv1_2, self.relu,
|
41 |
+
self.maxpool,
|
42 |
+
self.conv2_1, self.relu,
|
43 |
+
self.conv2_2, self.relu,
|
44 |
+
self.maxpool,
|
45 |
+
self.conv3_1, self.relu,
|
46 |
+
self.conv3_2, self.relu,
|
47 |
+
self.conv3_3, self.relu,
|
48 |
+
self.maxpool,
|
49 |
+
self.conv4_1, self.relu,
|
50 |
+
self.conv4_2, self.relu,
|
51 |
+
self.conv4_3, self.relu,
|
52 |
+
self.maxpool,
|
53 |
+
self.conv5_1, self.relu,
|
54 |
+
self.conv5_2, self.relu,
|
55 |
+
self.conv5_3, self.relu,
|
56 |
+
self.maxpool,
|
57 |
+
nn.Flatten(start_dim=0)
|
58 |
+
]
|
59 |
+
|
60 |
+
self._classifier = [
|
61 |
+
self.fc6, self.relu,
|
62 |
+
self.fc7, self.relu,
|
63 |
+
self.fc8
|
64 |
+
]
|
65 |
+
|
66 |
+
self._embedder = [
|
67 |
+
self.conv1_1, self.relu,
|
68 |
+
self.conv1_2, self.relu,
|
69 |
+
self.maxpool,
|
70 |
+
self.conv2_1, self.relu,
|
71 |
+
self.conv2_2, self.relu,
|
72 |
+
self.maxpool,
|
73 |
+
self.conv3_1, self.relu,
|
74 |
+
self.conv3_2, self.relu,
|
75 |
+
self.conv3_3, self.relu,
|
76 |
+
self.maxpool,
|
77 |
+
self.conv4_1, self.relu,
|
78 |
+
self.conv4_2, self.relu,
|
79 |
+
self.conv4_3, self.relu,
|
80 |
+
self.maxpool,
|
81 |
+
self.conv5_1, self.relu,
|
82 |
+
self.conv5_2, self.relu,
|
83 |
+
self.conv5_3, self.relu,
|
84 |
+
self.maxpool,
|
85 |
+
nn.Flatten(start_dim=0),
|
86 |
+
self.fc6,
|
87 |
+
]
|
88 |
+
self.transform = Compose([ToTensor() ,Resize((224, 224)), Normalize(mean=(93.59396362304688/255, 104.76238250732422/255, 129.186279296875/255), std=(1, 1, 1))])
|
89 |
+
def features(self, x):
|
90 |
+
x = self.transform(x)
|
91 |
+
x = x.to(DEVICE)
|
92 |
+
for layer in self._features:
|
93 |
+
x = layer(x)
|
94 |
+
return x
|
95 |
+
def classifier(self, x):
|
96 |
+
for layer in self._classifier:
|
97 |
+
x = layer(x)
|
98 |
+
return x
|
99 |
+
def embedder(self, x):
|
100 |
+
x = self.transform(x)
|
101 |
+
x = x.to(DEVICE)
|
102 |
+
for layer in self._embedder:
|
103 |
+
x = layer(x)
|
104 |
+
return x
|
105 |
+
def forward(self, x:torch.Tensor):
|
106 |
+
x = self.features(x)
|
107 |
+
return self.classifier(x)
|
108 |
+
def embeddings(self, x:torch.Tensor):
|
109 |
+
return self.embedder(x).cpu().flatten().detach().numpy()
|
110 |
+
__call__ = embeddings
|
111 |
+
|
112 |
+
MODEL_FACE = VGGFACE()
|
113 |
+
MODEL_FACE.load_state_dict(torch.load("models/vgg_face_dag.pth"), strict=True)
|
114 |
+
MODEL_FACE.to(DEVICE)
|
115 |
+
|
116 |
+
if __name__ == "__main__":
|
117 |
+
print(MODEL_FACE.state_dict().keys())
|
yolo/__pycache__/yoloFace.cpython-312.pyc
ADDED
Binary file (2.18 kB). View file
|
|
yolo/yolo.py
ADDED
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import cv2
|
2 |
+
import numpy as np
|
3 |
+
|
4 |
+
# need to change these offsets later
|
5 |
+
X1_OFFSET, X2_OFFSET = 0,0
|
6 |
+
Y1_OFFSET, Y2_OFFSET = 0,0
|
7 |
+
|
8 |
+
class YOLO:
|
9 |
+
def __init__(self):
|
10 |
+
self.net = cv2.dnn.readNet("models/yolov3-tiny.weights", "configs/yolov3-tiny.cfg")
|
11 |
+
self.layer_names = self.net.getLayerNames()
|
12 |
+
self.output_layers = [self.layer_names[i - 1] for i in self.net.getUnconnectedOutLayers()]
|
13 |
+
self.classes = []
|
14 |
+
with open("coco.names", "r") as f:
|
15 |
+
self.classes = [line.strip() for line in f.readlines()]
|
16 |
+
def get_patches(self, img):
|
17 |
+
patches = []
|
18 |
+
for (x1, y1), (x2, y2), color, confidence, label in self.forward(img):
|
19 |
+
if (x1 == x2 or y1 == y2):
|
20 |
+
continue
|
21 |
+
print((x1, y1), (x2, y2))
|
22 |
+
patches.append(img[y1:y2, x1:x2])
|
23 |
+
return patches
|
24 |
+
def forward(self, img):
|
25 |
+
height, width, channels = img.shape
|
26 |
+
|
27 |
+
# Prepare the image for YOLO
|
28 |
+
blob = cv2.dnn.blobFromImage(img, 0.00392, (416, 416), (0, 0, 0), True, crop=False)
|
29 |
+
self.net.setInput(blob)
|
30 |
+
|
31 |
+
# Run the forward pass
|
32 |
+
outs = self.net.forward(self.output_layers)
|
33 |
+
|
34 |
+
# Processing the output
|
35 |
+
class_ids = []
|
36 |
+
confidences = []
|
37 |
+
boxes = []
|
38 |
+
for out in outs:
|
39 |
+
for detection in out:
|
40 |
+
scores = detection[5:] # center x, center y, width, height, object confidence score, class confidence scores...
|
41 |
+
class_id = np.argmax(scores)
|
42 |
+
class_confidence = scores[class_id]
|
43 |
+
object_confidence = detection[4]
|
44 |
+
if object_confidence > 0.5:
|
45 |
+
# Get the coordinates for the bounding box
|
46 |
+
center_x = int(detection[0] * width)
|
47 |
+
center_y = int(detection[1] * height)
|
48 |
+
w = int(detection[2] * width)
|
49 |
+
h = int(detection[3] * height)
|
50 |
+
|
51 |
+
# Rectangle coordinates
|
52 |
+
x = int(center_x - w / 2)
|
53 |
+
y = int(center_y - h / 2)
|
54 |
+
if x < 0 or y < 0:
|
55 |
+
continue
|
56 |
+
boxes.append([x, y, w, h])
|
57 |
+
confidences.append(float(class_confidence))
|
58 |
+
class_ids.append(class_id)
|
59 |
+
|
60 |
+
# Apply non-max suppression to remove overlapping boxes
|
61 |
+
indexes = cv2.dnn.NMSBoxes(boxes, confidences, 0.5, 0.4)
|
62 |
+
for i in range(len(boxes)):
|
63 |
+
if i in indexes:
|
64 |
+
x, y, w, h = boxes[i]
|
65 |
+
label = str(self.classes[class_ids[i]])
|
66 |
+
confidence = confidences[i]
|
67 |
+
color = (0, 255, 0) # Green box
|
68 |
+
if label == "person":
|
69 |
+
yield (x + X1_OFFSET, y + Y1_OFFSET), (x + w + X2_OFFSET, y + h + Y2_OFFSET), color, confidence, label
|
70 |
+
__call__ = get_patches
|
71 |
+
|
72 |
+
def display(yolo_model:YOLO):
|
73 |
+
cam = cv2.VideoCapture(0)
|
74 |
+
while True:
|
75 |
+
ret, img = cam.read()
|
76 |
+
if not ret:
|
77 |
+
print("unable to record")
|
78 |
+
continue
|
79 |
+
for (x1, y1), (x2, y2), color, confidence, label in yolo_model.forward(img):
|
80 |
+
print(x1, y1, x2, y2)
|
81 |
+
cv2.rectangle(img, (x1, y1), (x2, y2), color, 2)
|
82 |
+
cv2.putText(img, f"{label} {confidence:.2f}", (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)
|
83 |
+
cv2.imshow("Camera Feed", img)
|
84 |
+
if cv2.waitKey(1) & 0xFF == ord('q'):
|
85 |
+
break
|
86 |
+
# Show the image
|
87 |
+
cam.release()
|
88 |
+
cv2.destroyAllWindows()
|
89 |
+
|
90 |
+
if __name__ == "__main__":
|
91 |
+
yolo_model = YOLO()
|
92 |
+
display(yolo_model=yolo_model)
|
yolo/yoloFace.py
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import cv2
|
2 |
+
from ultralytics import YOLO
|
3 |
+
|
4 |
+
X1_OFFSET, Y1_OFFSET, X2_OFFSET, Y2_OFFSET = 0, 0, 0, 0 # need to tinker with later
|
5 |
+
COLOR = (0, 255, 0)
|
6 |
+
|
7 |
+
class YOLOFace:
|
8 |
+
|
9 |
+
def __init__(self):
|
10 |
+
self.net = YOLO("models/best.pt")
|
11 |
+
def get_patches(self, img):
|
12 |
+
patches = []
|
13 |
+
for (x1, y1), (x2, y2) in self.forward(img):
|
14 |
+
cv2.rectangle(img, (x1, y1), (x2, y2), COLOR, 2)
|
15 |
+
if (x1 == x2 or y1 == y2):
|
16 |
+
continue
|
17 |
+
patches.append(img[y1:y2, x1:x2])
|
18 |
+
return patches
|
19 |
+
def forward(self, img):
|
20 |
+
boxes = self.net.predict(img, verbose=False)[0].boxes.xyxy.cpu().detach().numpy()
|
21 |
+
for x1, y1, x2, y2 in boxes:
|
22 |
+
yield (int(x1.item()+X1_OFFSET), int(y1.item()+Y1_OFFSET)), (int(x2.item()+X2_OFFSET), int(y2.item()+Y2_OFFSET))
|
23 |
+
__call__ = get_patches
|
24 |
+
|
25 |
+
YOLO_FACE = YOLOFace()
|