Add detection python files

detect_pipeline.py

@@ -0,0 +1,6 @@
+from transformers import pipeline
+
+detector = pipeline(model="facebook/detr-resnet-50", revision="no_timm")
+result = detector("http://images.cocodataset.org/val2017/000000039769.jpg")
+print(result)
+# x, y  are expressed relative to the top left hand corner.

detect_torch.py

@@ -0,0 +1,115 @@
+# Main file
+
+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);
+
+# 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
+# Convert center of bounding box to relative image coordinates
+# from (cx, cy, w, h) to (x0, y0, x1, y1)
+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)
+
+# convert predictions to absolute image coordinates
+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 plot_results(pil_img, prob, boxes):
+    plt.figure(figsize=(8,5))
+    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')
+    plt.show()
+
+
+def detect(im, model, transform):
+    # mean-std normalize the input image (batch-size: 1)
+    img = transform(im).unsqueeze(0)
+
+    # demo model only support by default images with aspect ratio between 0.5 and 2
+    # if you want to use images with an aspect ratio outside this range
+    # rescale your image so that the maximum size is at most 1333 for best results
+    assert img.shape[-2] <= 1600 and img.shape[
+        -1] <= 1600, 'demo model only supports images up to 1600 pixels on each side'
+
+    # propagate through the model
+    outputs = model(img)
+
+    # keep only predictions with 0.9+ 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 probas[keep], bboxes_scaled
+
+def load_model():
+    model = torch.hub.load('facebookresearch/detr', 'detr_resnet50', pretrained=True)
+    model.eval();
+    return model
+
+def main():
+    url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
+    im = Image.open(requests.get(url, stream=True).raw)
+    model = load_model()
+    scores, boxes = detect(im, model, transform)
+    print('len(scores)',len(scores))
+    print('scores[0].shape', scores[0].shape)
+    print('scores', scores)
+    print('len(boxes)',len(boxes))
+    print('boxes',boxes)
+    plot_results(im, scores, boxes)
+
+if __name__ == "__main__":
+    main()
+

detect_transformers.py

@@ -0,0 +1,26 @@
+from transformers import DetrImageProcessor, DetrForObjectDetection
+import torch
+from PIL import Image
+import requests
+
+url = "http://images.cocodataset.org/val2017/000000039769.jpg"
+image = Image.open(requests.get(url, stream=True).raw)
+
+# you can specify the revision tag if you don't want the timm dependency
+processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50", revision="no_timm")
+model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50", revision="no_timm")
+
+inputs = processor(images=image, return_tensors="pt")
+outputs = model(**inputs)
+
+# convert outputs (bounding boxes and class logits) to COCO API
+# let's only keep detections with score > 0.9
+target_sizes = torch.tensor([image.size[::-1]])
+results = processor.post_process_object_detection(outputs, target_sizes=target_sizes, threshold=0.9)[0]
+
+for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
+    box = [round(i, 2) for i in box.tolist()]
+    print(
+            f"Detected {model.config.id2label[label.item()]} with confidence "
+            f"{round(score.item(), 3)} at location {box}"
+    )