Spaces:
Runtime error
Runtime error
| from PIL import Image | |
| import requests | |
| import matplotlib.pyplot as plt | |
| import torch | |
| from torch import nn | |
| from torchvision.models import resnet50 | |
| import torchvision.transforms as T | |
| torch.set_grad_enabled(False); | |
| import gradio as gr | |
| import io | |
| model = torch.hub.load('facebookresearch/detr', 'detr_resnet50', pretrained=True) | |
| # Images | |
| torch.hub.download_url_to_file('https://images.pexels.com/photos/461717/pexels-photo-461717.jpeg', 'horse.jpeg') | |
| torch.hub.download_url_to_file('https://images.pexels.com/photos/5967799/pexels-photo-5967799.jpeg', 'turtle.jpeg') | |
| # COCO classes | |
| CLASSES = [ | |
| 'N/A', 'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', | |
| 'train', 'truck', 'boat', 'traffic light', 'fire hydrant', 'N/A', | |
| 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', | |
| 'sheep', 'cow', 'elephant', 'bear', 'zebra', 'giraffe', 'N/A', 'backpack', | |
| 'umbrella', 'N/A', 'N/A', 'handbag', 'tie', 'suitcase', 'frisbee', 'skis', | |
| 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', | |
| 'skateboard', 'surfboard', 'tennis racket', 'bottle', 'N/A', 'wine glass', | |
| 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple', 'sandwich', | |
| 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', | |
| 'chair', 'couch', 'potted plant', 'bed', 'N/A', 'dining table', 'N/A', | |
| 'N/A', 'toilet', 'N/A', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', | |
| 'cell phone', 'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'N/A', | |
| 'book', 'clock', 'vase', 'scissors', 'teddy bear', 'hair drier', | |
| 'toothbrush' | |
| ] | |
| # 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]] | |
| # standard PyTorch mean-std input image normalization | |
| transform = T.Compose([ | |
| T.Resize(800), | |
| T.ToTensor(), | |
| T.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]) | |
| ]) | |
| # for output bounding box post-processing | |
| def box_cxcywh_to_xyxy(x): | |
| x_c, y_c, w, h = x.unbind(1) | |
| b = [(x_c - 0.5 * w), (y_c - 0.5 * h), | |
| (x_c + 0.5 * w), (y_c + 0.5 * h)] | |
| return torch.stack(b, dim=1) | |
| def rescale_bboxes(out_bbox, size): | |
| img_w, img_h = size | |
| b = box_cxcywh_to_xyxy(out_bbox) | |
| b = b * torch.tensor([img_w, img_h, img_w, img_h], dtype=torch.float32) | |
| return b | |
| def fig2img(fig): | |
| """Convert a Matplotlib figure to a PIL Image and return it""" | |
| buf = io.BytesIO() | |
| fig.savefig(buf) | |
| buf.seek(0) | |
| return Image.open(buf) | |
| def plot_results(pil_img, prob, boxes): | |
| plt.figure(figsize=(16,10)) | |
| plt.imshow(pil_img) | |
| ax = plt.gca() | |
| colors = COLORS * 100 | |
| for p, (xmin, ymin, xmax, ymax), c in zip(prob, boxes.tolist(), colors): | |
| ax.add_patch(plt.Rectangle((xmin, ymin), xmax - xmin, ymax - ymin, | |
| fill=False, color=c, linewidth=3)) | |
| cl = p.argmax() | |
| text = f'{CLASSES[cl]}: {p[cl]:0.2f}' | |
| ax.text(xmin, ymin, text, fontsize=15, | |
| bbox=dict(facecolor='yellow', alpha=0.5)) | |
| plt.axis('off') | |
| return fig2img(plt) | |
| def detr(im): | |
| # mean-std normalize the input image (batch-size: 1) | |
| img = transform(im).unsqueeze(0) | |
| # propagate through the model | |
| outputs = model(img) | |
| # keep only predictions with 0.7+ confidence | |
| probas = outputs['pred_logits'].softmax(-1)[0, :, :-1] | |
| keep = probas.max(-1).values > 0.9 | |
| # convert boxes from [0; 1] to image scales | |
| bboxes_scaled = rescale_bboxes(outputs['pred_boxes'][0, keep], im.size) | |
| return plot_results(im, probas[keep], bboxes_scaled) | |
| inputs = gr.inputs.Image(type='pil', label="Original Image", shape=(600,600)) | |
| outputs = gr.outputs.Image(type="pil",label="Output Image") | |
| examples = [ | |
| ['horse.jpeg'], | |
| ['turtle.jpeg'] | |
| ] | |
| title = "AIBC DETR demo" | |
| description = "aibc object detection demo" | |
| article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2005.12872'>End-to-End Object Detection with Transformers</a> | <a href='https://github.com/facebookresearch/detr'>Github Repo</a></p>" | |
| gr.Interface(detr, inputs, outputs, title=title, description=description, article=article, examples=examples).launch() | |