app.py

# 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)