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 AutoFeatureExtractor, DetrForObjectDetection, YolosForObjectDetection 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] ] 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[0] def fig2img(fig): buf = io.BytesIO() fig.savefig(buf) 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] 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()) models = ["facebook/detr-resnet-50", "facebook/detr-resnet-101", 'hustvl/yolos-small', 'hustvl/yolos-tiny'] def detect_objects(image_input,threshold): labels = [] #Extract model and feature extractor feature_extractor_1 = AutoFeatureExtractor.from_pretrained("facebook/detr-resnet-50") feature_extractor_2 = AutoFeatureExtractor.from_pretrained("facebook/detr-resnet-101") feature_extractor_3 = AutoFeatureExtractor.from_pretrained('hustvl/yolos-small') feature_extractor_4 = AutoFeatureExtractor.from_pretrained('hustvl/yolos-tiny') model_1 = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50") model_2 = YolosForObjectDetection.from_pretrained('hustvl/yolos-small') model_3 = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-101") model_4 = YolosForObjectDetection.from_pretrained('hustvl/yolos-tiny') #Make prediction processed_outputs_1 = make_prediction(image_input, feature_extractor_1, model_1) processed_outputs_2 = make_prediction(image_input, feature_extractor_2, model_2) processed_outputs_3 = make_prediction(image_input, feature_extractor_3, model_3) processed_outputs_4 = make_prediction(image_input, feature_extractor_4, model_4) #Visualize prediction viz_img_1 = visualize_prediction(image_input, processed_outputs_1, threshold, model_1.config.id2label) viz_img_2 = visualize_prediction(image_input, processed_outputs_2, threshold, model_2.config.id2label) viz_img_3 = visualize_prediction(image_input, processed_outputs_3, threshold, model_3.config.id2label) viz_img_4 = visualize_prediction(image_input, processed_outputs_4, threshold, model_4.config.id2label) return viz_img_1,viz_img_2,viz_img_3,viz_img_4 title = """