import io import gradio as gr import matplotlib.pyplot as plt import requests, validators import torch import pathlib from PIL import Image from transformers import DetrFeatureExtractor, DetrForSegmentation, MaskFormerFeatureExtractor, MaskFormerForInstanceSegmentation from transformers.models.detr.feature_extraction_detr import rgb_to_id import os # colors for visualization COLORS = [ [0.000, 0.447, 0.741], [0.850, 0.325, 0.098], [0.929, 0.694, 0.125], [0.494, 0.184, 0.556], [0.466, 0.674, 0.188], [0.301, 0.745, 0.933] ] YOLOV8_LABELS = ['pedestrian', 'people', 'bicycle', 'car', 'van', 'truck', 'tricycle', 'awning-tricycle', 'bus', 'motor'] def make_prediction(img, feature_extractor, model): inputs = feature_extractor(img, return_tensors="pt") outputs = model(**inputs) img_size = torch.tensor([tuple(reversed(img.size))]) processed_outputs = feature_extractor.post_process(outputs, img_size) return processed_outputs def fig2img(fig): buf = io.BytesIO() fig.savefig(buf, bbox_inches="tight") buf.seek(0) img = Image.open(buf) return img def visualize_prediction(pil_img, output_dict, threshold=0.7, id2label=None): keep = output_dict["scores"] > threshold boxes = output_dict["boxes"][keep].tolist() scores = output_dict["scores"][keep].tolist() labels = output_dict["labels"][keep].tolist() if id2label is not None: labels = [id2label[x] for x in labels] # print("Labels " + str(labels)) plt.figure(figsize=(16, 10)) plt.imshow(pil_img) ax = plt.gca() colors = COLORS * 100 for score, (xmin, ymin, xmax, ymax), label, color in zip(scores, boxes, labels, colors): ax.add_patch(plt.Rectangle((xmin, ymin), xmax - xmin, ymax - ymin, fill=False, color=color, linewidth=3)) ax.text(xmin, ymin, f"{label}: {score:0.2f}", fontsize=15, bbox=dict(facecolor="yellow", alpha=0.5)) plt.axis("off") return fig2img(plt.gcf()) def segment_images(model_name,url_input,image_input,threshold): #### # Get Image Object if validators.url(url_input): image = Image.open(requests.get(url_input, stream=True).raw) elif image_input: image = image_input #### if "detr" in model_name: pass elif "maskformer" in model_name.lower(): # Load the processor and model processor = MaskFormerFeatureExtractor.from_pretrained(model_name) print(type(processor)) model = MaskFormerForInstanceSegmentation.from_pretrained(model_name) inputs = processor(images=image, return_tensors="pt") outputs = model(**inputs) print(type(outputs)) print(outputs) pass else: raise NameError("Model is not implemented") def set_example_image(example: list) -> dict: return gr.Image.update(value=example[0]) def set_example_url(example: list) -> dict: return gr.Textbox.update(value=example[0]) title = """

Image Segmentation with Various Models

""" description = """ Links to HuggingFace Models: - [facebook/detr-resnet-50-panoptic](https://huggingface.co/facebook/detr-resnet-50-panoptic) - [facebook/detr-resnet-101-panoptic](https://huggingface.co/facebook/detr-resnet-101-panoptic) - [facebook/maskformer-swin-large-coco](https://huggingface.co/facebook/maskformer-swin-large-coco) """ models = ["facebook/detr-resnet-50-panoptic","facebook/detr-resnet-101-panoptic","facebook/maskformer-swin-large-coco"] urls = ["https://c8.alamy.com/comp/J2AB4K/the-new-york-stock-exchange-on-the-wall-street-in-new-york-J2AB4K.jpg"] # twitter_link = """ # [![](https://img.shields.io/twitter/follow/nickmuchi?label=@nickmuchi&style=social)](https://twitter.com/nickmuchi) # """ css = ''' h1#title { text-align: center; } ''' demo = gr.Blocks(css=css) def changing(): # https://discuss.huggingface.co/t/how-to-programmatically-enable-or-disable-components/52350/4 return gr.Button.update(interactive=True), gr.Button.update(interactive=True) with demo: gr.Markdown(title) gr.Markdown(description) # gr.Markdown(twitter_link) options = gr.Dropdown(choices=models,label='Select Image Segmentation Model',show_label=True) slider_input = gr.Slider(minimum=0.2,maximum=1,value=0.7,label='Prediction Threshold') with gr.Tabs(): with gr.TabItem('Image URL'): with gr.Row(): url_input = gr.Textbox(lines=2,label='Enter valid image URL here..') img_output_from_url = gr.Image(shape=(650,650)) with gr.Row(): example_url = gr.Dataset(components=[url_input],samples=[[str(url)] for url in urls]) url_but = gr.Button('Detect', interactive=False) with gr.TabItem('Image Upload'): with gr.Row(): img_input = gr.Image(type='pil') img_output_from_upload= gr.Image(shape=(650,650)) with gr.Row(): example_images = gr.Dataset(components=[img_input], samples=[[path.as_posix()] for path in sorted(pathlib.Path('images').rglob('*.JPG'))]) # Can't get case_sensitive to work img_but = gr.Button('Detect', interactive=False) # output_text1 = gr.outputs.Textbox(label="Confidence Values") output_text1 = gr.components.Textbox(label="Confidence Values") # https://huggingface.co/spaces/vishnun/CLIPnCROP/blob/main/app.py -- Got .outputs. from this options.change(fn=changing, inputs=[], outputs=[img_but, url_but]) url_but.click(segment_images,inputs=[options,url_input,img_input,slider_input],outputs=[img_output_from_url, output_text1],queue=True) img_but.click(segment_images,inputs=[options,url_input,img_input,slider_input],outputs=[img_output_from_upload, output_text1],queue=True) # url_but.click(segment_images,inputs=[options,url_input,img_input,slider_input],outputs=[img_output_from_url, _],queue=True) # img_but.click(segment_images,inputs=[options,url_input,img_input,slider_input],outputs=[img_output_from_upload, _],queue=True) # url_but.click(segment_images,inputs=[options,url_input,img_input,slider_input],outputs=img_output_from_url,queue=True) # img_but.click(segment_images,inputs=[options,url_input,img_input,slider_input],outputs=img_output_from_upload,queue=True) example_images.click(fn=set_example_image,inputs=[example_images],outputs=[img_input]) example_url.click(fn=set_example_url,inputs=[example_url],outputs=[url_input]) # gr.Markdown("![visitor badge](https://visitor-badge.glitch.me/badge?page_id=nickmuchi-object-detection-with-detr-and-yolos)") # demo.launch(enable_queue=True) demo.launch() #removed (share=True)