import os os.system('pip install detectron2 -f https://dl.fbaipublicfiles.com/detectron2/wheels/cu102/torch1.9/index.html') os.system('pip install torch==1.9.0 torchvision==0.10.0') import gradio as gr # check pytorch installation: import torch, torchvision print(torch.__version__, torch.cuda.is_available()) assert torch.__version__.startswith("1.9") # please manually install torch 1.9 if Colab changes its default version import detectron2 from detectron2.utils.logger import setup_logger import numpy as np import os, json, random from detectron2 import model_zoo from detectron2.engine import DefaultPredictor from detectron2.config import get_cfg from PIL import Image from pathlib import Path from matplotlib import pyplot as plt cfg = get_cfg() cfg.MODEL.DEVICE='cpu' cfg.INPUT.MASK_FORMAT='bitmask' cfg.MODEL.ROI_HEADS.NUM_CLASSES = 3 cfg.TEST.DETECTIONS_PER_IMAGE = 1000 cfg.merge_from_file(model_zoo.get_config_file("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml")) cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.5 # set threshold for this model cfg.MODEL.WEIGHTS = "model_final.pth" predictor = DefaultPredictor(cfg) def inference(img): class_names = ['astro', 'cort', 'sh-sy5y'] im = np.asarray(Image.open(img).convert('RGB')) outputs = predictor(im) pred_classes = outputs['instances'].pred_classes.cpu().numpy().tolist() take = outputs['instances'].scores >= 0.5 #Threshold pred_masks = outputs['instances'].pred_masks[take].cpu().numpy() pred_class = max(set(pred_classes), key=pred_classes.count) mask = np.stack(pred_masks) mask = np.any(mask == 1, axis=0) p = plt.imshow(im,cmap='gray') p = plt.imshow(mask, alpha=0.4) p = plt.xticks(fontsize=8) p = plt.yticks(fontsize=8) p = plt.title("cell type: " + class_names[pred_class]) return plt title = "Sartorius Cell Instance Segmentation" description = "Sartorius Cell Instance Segmentation Demo: Current Kaggle competition - kaggle.com/c/sartorius-cell-instance-segmentation" article = "

Detectron2: A PyTorch-based modular object detection library | Github Repo

" examples = [['0030fd0e6378.png']] gr.Interface(inference, inputs=gr.inputs.Image(type="filepath"), outputs=gr.outputs.Image('plot') ,enable_queue=True, title=title, description=description, article=article, examples=examples).launch(debug=False)