try: import detectron2 except: import os os.system('pip install git+https://github.com/facebookresearch/detectron2.git') from matplotlib.pyplot import axis import gradio as gr import requests import numpy as np from torch import nn import requests import cv2 import torch import detectron2 from detectron2 import model_zoo from detectron2.engine import DefaultPredictor from detectron2.config import get_cfg from detectron2.utils.visualizer import Visualizer from detectron2.data import MetadataCatalog from detectron2.utils.visualizer import ColorMode from detectron2.structures import Instances from detectron2.structures import Boxes damage_model_path = 'damage/model_final.pth' scratch_model_path = 'scratch/model_final.pth' parts_model_path = 'parts/model_final.pth' if torch.cuda.is_available(): device = 'cuda' else: device = 'cpu' cfg_scratches = get_cfg() cfg_scratches.merge_from_file(model_zoo.get_config_file("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml")) cfg_scratches.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.8 cfg_scratches.MODEL.ROI_HEADS.NUM_CLASSES = 1 cfg_scratches.MODEL.WEIGHTS = scratch_model_path cfg_scratches.MODEL.DEVICE = device predictor_scratches = DefaultPredictor(cfg_scratches) metadata_scratch = MetadataCatalog.get("car_dataset_val") metadata_scratch.thing_classes = ["scratch"] cfg_damage = get_cfg() cfg_damage.merge_from_file(model_zoo.get_config_file("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml")) cfg_damage.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.7 cfg_damage.MODEL.ROI_HEADS.NUM_CLASSES = 1 cfg_damage.MODEL.WEIGHTS = damage_model_path cfg_damage.MODEL.DEVICE = device predictor_damage = DefaultPredictor(cfg_damage) metadata_damage = MetadataCatalog.get("car_damage_dataset_val") metadata_damage.thing_classes = ["damage"] cfg_parts = get_cfg() cfg_parts.merge_from_file(model_zoo.get_config_file("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml")) cfg_parts.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.75 cfg_parts.MODEL.ROI_HEADS.NUM_CLASSES = 19 cfg_parts.MODEL.WEIGHTS = parts_model_path cfg_parts.MODEL.DEVICE = device predictor_parts = DefaultPredictor(cfg_parts) metadata_parts = MetadataCatalog.get("car_parts_dataset_val") metadata_parts.thing_classes = ['_background_', 'back_bumper', 'back_glass', 'back_left_door', 'back_left_light', 'back_right_door', 'back_right_light', 'front_bumper', 'front_glass', 'front_left_door', 'front_left_light', 'front_right_door', 'front_right_light', 'hood', 'left_mirror', 'right_mirror', 'tailgate', 'trunk', 'wheel'] def merge_segment(pred_segm): merge_dict = {} for i in range(len(pred_segm)): merge_dict[i] = [] for j in range(i+1,len(pred_segm)): if torch.sum(pred_segm[i]*pred_segm[j])>0: merge_dict[i].append(j) to_delete = [] for key in merge_dict: for element in merge_dict[key]: to_delete.append(element) for element in to_delete: merge_dict.pop(element,None) empty_delete = [] for key in merge_dict: if merge_dict[key] == []: empty_delete.append(key) for element in empty_delete: merge_dict.pop(element,None) for key in merge_dict: for element in merge_dict[key]: pred_segm[key]+=pred_segm[element] except_elem = list(set(to_delete)) new_indexes = list(range(len(pred_segm))) for elem in except_elem: new_indexes.remove(elem) return pred_segm[new_indexes] def inference(image): img = np.array(image) outputs_damage = predictor_damage(img) outputs_parts = predictor_parts(img) outputs_scratch = predictor_scratches(img) out_dict = outputs_damage["instances"].to("cpu").get_fields() merged_damage_masks = merge_segment(out_dict['pred_masks']) scratch_data = outputs_scratch["instances"].get_fields() scratch_masks = scratch_data['pred_masks'] damage_data = outputs_damage["instances"].get_fields() damage_masks = damage_data['pred_masks'] parts_data = outputs_parts["instances"].get_fields() parts_masks = parts_data['pred_masks'] parts_classes = parts_data['pred_classes'] new_inst = detectron2.structures.Instances((1024,1024)) new_inst.set('pred_masks',merge_segment(out_dict['pred_masks'])) parts_damage_dict = {} parts_list_damages = [] for part in parts_classes: parts_damage_dict[metadata_parts.thing_classes[part]] = [] for mask in scratch_masks: for i in range(len(parts_masks)): if torch.sum(parts_masks[i]*mask)>0: parts_damage_dict[metadata_parts.thing_classes[parts_classes[i]]].append('scratch') parts_list_damages.append(f'{metadata_parts.thing_classes[parts_classes[i]]} has scratch') print(f'{metadata_parts.thing_classes[parts_classes[i]]} has scratch') for mask in merged_damage_masks: for i in range(len(parts_masks)): if torch.sum(parts_masks[i]*mask)>0: parts_damage_dict[metadata_parts.thing_classes[parts_classes[i]]].append('damage') parts_list_damages.append(f'{metadata_parts.thing_classes[parts_classes[i]]} has damage') print(f'{metadata_parts.thing_classes[parts_classes[i]]} has damage') # Define the colors for the scratch and damage masks scratch_color = (0, 0, 255) # red damage_color = (0, 255, 255) # yellow # Convert the scratch and damage masks to numpy arrays scratch_masks_arr = np.array(scratch_masks) damage_masks_arr = np.array(damage_masks) # Resize the scratch and damage masks to match the size of the original image scratch_mask_resized = cv2.resize(scratch_masks_arr[0].astype(np.uint8), (img.shape[1], img.shape[0])) damage_mask_resized = cv2.resize(damage_masks_arr[0].astype(np.uint8), (img.shape[1], img.shape[0])) # Merge the scratch and damage masks into a single binary mask merged_mask = np.zeros_like(scratch_mask_resized) merged_mask[(scratch_mask_resized> 0) | (damage_mask_resized > 0)] = 255 # Overlay the merged mask on top of the original image overlay = img.copy() overlay[merged_mask == 255] = (0, 255, 0) # green color for the merged mask overlay[damage_mask_resized == 255] = damage_color # yellow color for the damage mask #output = cv2.addWeighted(overlay, 0.5, img, 0.5, 0) # Merge the instance predictions from both predictors image_np = np.array(image) height, width, channels = image_np.shape # Get the predicted boxes from the scratches predictor pred_boxes_scratch = outputs_scratch["instances"].pred_boxes.tensor # Get the predicted boxes from the damage predictor pred_boxes_damage = outputs_damage["instances"].pred_boxes.tensor # Concatenate the predicted boxes along the batch dimension merged_boxes = torch.cat([pred_boxes_scratch, pred_boxes_damage], dim=0) # Create a new Instances object with the merged boxes merged_instances = Instances((image_np.shape[0], image_np.shape[1])) merged_instances.pred_boxes = Boxes(merged_boxes) # Visualize the Masks v_d = Visualizer(img[:, :, ::-1], metadata=metadata_damage, scale=0.5, instance_mode=ColorMode.SEGMENTATION # remove the colors of unsegmented pixels. This option is only available for segmentation models ) v_d = Visualizer(img,scale=1.2) out_d = v_d.draw_instance_predictions(new_inst) img1 = out_d.get_image()[:, :, ::-1] v_s = Visualizer(img[:, :, ::-1], metadata=metadata_scratch, scale=0.5, instance_mode=ColorMode.SEGMENTATION # remove the colors of unsegmented pixels. This option is only available for segmentation models ) v_s = Visualizer(img,scale=1.2) out_s = v_s.draw_instance_predictions(outputs_scratch["instances"]) img2 = out_s.get_image()[:, :, ::-1] v_p = Visualizer(img[:, :, ::-1], metadata=metadata_parts, scale=0.5, instance_mode=ColorMode.SEGMENTATION # remove the colors of unsegmented pixels. This option is only available for segmentation models ) v_p = Visualizer(img,scale=1.2) out_p = v_p.draw_instance_predictions(outputs_parts["instances"]) img3 = out_p.get_image()[:, :, ::-1] # Visualize the overlay v_m = Visualizer(overlay[:, :, ::-1], metadata=metadata_damage, scale=1.2, instance_mode=ColorMode.SEGMENTATION # display the overlay in black and white ) # Draw the overlay with instance predictions overlay_with_predictions = v_m.draw_instance_predictions(merged_instances.to("cpu")).get_image()[:, :, ::-1] #v_m = Visualizer(overlay,scale=1.2) out = v_m.draw_instance_predictions(merged_instances) output = out.get_image()[:, :, ::-1] return img1, img2, img3, parts_list_damages, output with gr.Blocks() as demo: with gr.Row(): with gr.Column(): gr.Markdown("## Inputs") image = gr.Image(type="pil",label="Input") submit_button = gr.Button(value="Submit", label="Submit") with gr.Column(): gr.Markdown("## Outputs") with gr.Tab('Image of damages'): im1 = gr.Image(type='numpy',label='Image of damages') with gr.Tab('Image of scratches'): im2 = gr.Image(type='numpy',label='Image of scratches') with gr.Tab('Image of parts'): im3 = gr.Image(type='numpy',label='Image of car parts') with gr.Tab('Information about damaged parts'): intersections = gr.Textbox(label='Information about type of damages on each part') with gr.Tab('Image of overlayed damage parts'): overlayed = gr.Image(type='numpy',label='Image of overlayed damage parts') #actions submit_button.click( fn=inference, inputs = [image], outputs = [im1,im2,im3,intersections, overlayed] ) if __name__ == "__main__": demo.launch()