File size: 2,321 Bytes
c88379a 7d1537c c88379a 8db3578 c88379a d532c55 c88379a 7d1537c c88379a 8db3578 c88379a 7d1537c c88379a 79948e0 c88379a cb7cbf4 c88379a fd3835f c88379a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 |
# import requests
# import os, io
# import gradio as gr
# # from PIL import Image
# # API_URL = "https://api-inference.huggingface.co/models/facebook/detr-resnet-50-panoptic"
# SECRET_TOKEN = os.getenv("SECRET_TOKEN")
# API_URL = "https://api-inference.huggingface.co/models/facebook/detr-resnet-50-dc5-panoptic"
# headers = {"Authorization": f'Bearer {SECRET_TOKEN}'}
# def image_classifier(inp):
# return {'cat': 0.3, 'dog': 0.7}
# def query(filename):
# with open(filename, "rb") as f:
# data = f.read()
# response = requests.post(API_URL, headers=headers, data=data)
# return response.json()
# def rb(img):
# # initialiaze io to_bytes converter
# img_byte_arr = io.BytesIO()
# # define quality of saved array
# img.save(img_byte_arr, format='JPEG', subsampling=0, quality=100)
# # converts image array to bytesarray
# img_byte_arr = img_byte_arr.getvalue()
# response = requests.post(API_URL, headers=headers, data=img_byte_arr)
# return response.json()
# inputs = gr.inputs.Image(type="pil", label="Upload an image")
# demo = gr.Interface(fn=rb, inputs=inputs, outputs="json")
# demo.launch()
import io
import requests
from PIL import Image
import torch
import numpy
from transformers import DetrFeatureExtractor, DetrForSegmentation
from transformers.models.detr.feature_extraction_detr import rgb_to_id
url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)
feature_extractor = DetrFeatureExtractor.from_pretrained("facebook/detr-resnet-50-panoptic")
model = DetrForSegmentation.from_pretrained("facebook/detr-resnet-50-panoptic")
# prepare image for the model
inputs = feature_extractor(images=image, return_tensors="pt")
# forward pass
outputs = model(**inputs)
# use the `post_process_panoptic` method of `DetrFeatureExtractor` to convert to COCO format
processed_sizes = torch.as_tensor(inputs["pixel_values"].shape[-2:]).unsqueeze(0)
result = feature_extractor.post_process_panoptic(outputs, processed_sizes)[0]
# the segmentation is stored in a special-format png
panoptic_seg = Image.open(io.BytesIO(result["png_string"]))
panoptic_seg = numpy.array(panoptic_seg, dtype=numpy.uint8)
# retrieve the ids corresponding to each mask
panoptic_seg_id = rgb_to_id(panoptic_seg)
|