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()) def detect_objects(model_name,url_input,image_input,threshold): #Extract model and feature extractor feature_extractor = AutoFeatureExtractor.from_pretrained(model_name) model = DetrForObjectDetection.from_pretrained(model_name) image = image_input #Make prediction processed_outputs = make_prediction(image, feature_extractor, model) print(processed_outputs) #Visualize prediction viz_img = visualize_prediction(image, processed_outputs, threshold, model.config.id2label) return viz_img xxresult=0 def detect_objects2(model_name,url_input,image_input,threshold,type2): #Extract model and feature extractor feature_extractor = AutoFeatureExtractor.from_pretrained(model_name) model = DetrForObjectDetection.from_pretrained(model_name) image = image_input #Make prediction processed_outputs = make_prediction(image, feature_extractor, model) print(processed_outputs) #Visualize prediction viz_img = visualize_prediction(image, processed_outputs, threshold, model.config.id2label) keep = processed_outputs["scores"] > threshold det_lab = processed_outputs["labels"][keep].tolist() det_lab.count(1) if det_lab.count(1) > 0: total_text="Trench is Detected \n Image is Not Blurry \n" else: total_text="Trench is NOT Detected \n Image is Blurry \n" print(type2) print(type(type2)) if det_lab.count(4) > 0: total_text+="Measuring Tape (Vertical) for measuring Depth is Detected \n" else: total_text+="Measuring Tape (Vertical) for measuring Depth is NOT Detected \n" if det_lab.count(5) > 0: total_text+="Measuring Tape (Horizontal) for measuring Width is Detected \n" else: total_text+="Measuring Tape (Horizontal) for measuring Width is NOT Detected \n" return total_text def tott(model_name,url_input,image_input,threshold,type2): #Extract model and feature extractor feature_extractor = AutoFeatureExtractor.from_pretrained(model_name) model = DetrForObjectDetection.from_pretrained(model_name) image = image_input #Make prediction processed_outputs = make_prediction(image, feature_extractor, model) keep = processed_outputs["scores"] > threshold det_lab = processed_outputs["labels"][keep].tolist() xxresult=0 if det_lab.count(1) == 0: xxresult=1 if det_lab.count(4) == 0: if type2=="Trench Depth Measurement": xxresult=1 if det_lab.count(5) == 0: if type2=="Trench Width Measurement": xxresult=1 if xxresult==0: return "The photo is ACCEPTED" else: return "The photo is NOT ACCEPTED" 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 = """