Add object detection, tracking, mobile notifications, and search to any security camera.
start mot test
roryclear091b2fa6a80e
diff --git a/test/test.py b/test/test.pyindex 3340b3d..268a9c4 100644--- a/test/test.py+++ b/test/test.py@@ -66,38 +66,6 @@ def test_bytetracker():np.testing.assert_allclose(output[j].class_id, output2[j].class_id)assert total_time2 <= (total_time * 1.0), "slower"--def test_tracker():- class_labels = fetch('https://raw.githubusercontent.com/pjreddie/darknet/master/data/coco.names').read_text().split("\n")- color_dict = {label: tuple((((i+1) * 50) % 256, ((i+1) * 100) % 256, ((i+1) * 150) % 256)) for i, label in enumerate(class_labels)}- yolo_variant = "t"- yolo_infer = YOLOv9(*SIZES[yolo_variant]) if yolo_variant in SIZES else YOLOv9()- class Args:- def __init__(self):- self.track_buffer = 60- self.mot20 = False- self.match_thresh = 0.9- tracker = BYTETracker(Args())-- cap = cv2.VideoCapture("test/videos/MOT16-03.mp4")- out = cv2.VideoWriter('output.mp4', cv2.VideoWriter_fourcc(*'mp4v'), 30, (960, 540))- while cap.isOpened():- ret, f = cap.read()- if not ret: break- frame = Tensor(f)- pre = preprocess(frame)- preds = do_inf(pre, yolo_infer)[0].numpy()- preds = scale_boxes(pre.shape[:2], preds, frame.shape)- tracker_preds = tracker.update(preds, [1280,1280], [1280,1280], 0.25) # thresh 0.25- preds = []- for x in tracker_preds:- preds.append(np.array([x.tlwh[0],x.tlwh[1],(x.tlwh[0]+x.tlwh[2]),(x.tlwh[1]+x.tlwh[3]),x.score,x.class_id,x.track_id]))- annotated_frame = draw_predictions(f, preds, class_labels, color_dict)- out.write(annotated_frame)- cap.release()- out.release()--test_tracker()-#test_bytetracker()-#test_linear_sum_assigment()-#test_linear_sum_assigment_speed()\ No newline at end of file+test_bytetracker()+test_linear_sum_assigment()+test_linear_sum_assigment_speed()\ No newline at end of filediff --git a/test/test_outputs.py b/test/test_outputs.pynew file mode 100644index 0000000..cc960ad--- /dev/null+++ b/test/test_outputs.py@@ -0,0 +1,63 @@+from detection.yolov9 import YOLOv9, SIZES, safe_load, load_state_dict, Sequential, Silence, Conv, RepNCSPELAN4, AConv,\+ADown, CBLinear, CBFuse, SPPELAN, Upsample, Concat, DDetect, postprocess, fetch, rescale_bounding_boxes, draw_bounding_boxes_and_save+import cv2+from tinygrad import Tensor+from tinygrad.dtype import dtypes+import numpy as np+from pathlib import Path++def letterbox(im, new_shape=(1280, 1280), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True, stride=32):+ shape = im.shape[:2]+ if isinstance(new_shape, int): new_shape = (new_shape, new_shape)+ r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])+ if not scaleup: r = min(r, 1.0)++ ratio = r, r+ new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))+ dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1]+ if auto:+ dw, dh = np.mod(dw, stride), np.mod(dh, stride)+ elif scaleFill: # stretch+ dw, dh = 0.0, 0.0+ new_unpad = (new_shape[1], new_shape[0])+ ratio = new_shape[1] / shape[1], new_shape[0] / shape[0]++ dw /= 2+ dh /= 2++ if shape[::-1] != new_unpad: im = cv2.resize(im, new_unpad, interpolation=cv2.INTER_LINEAR)+ top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))+ left, right = int(round(dw - 0.1)), int(round(dw + 0.1))+ im = cv2.copyMakeBorder(im, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color)+ return im, ratio, (dw, dh)++if __name__ == "__main__":+ for size in ["t", "s", "m", "c", "e"]:+ weights = f'./yolov9-{size}-tiny.pkl'+ imgsz = (640,640)+ model = YOLOv9(*SIZES[size]) if size in SIZES else YOLOv9()+ state_dict = safe_load(fetch(f'https://huggingface.co/roryclear/yolov9/resolve/main/yolov9-{size}.safetensors'))+ load_state_dict(model, state_dict)+ source = "test/videos/MOT16-03.mp4"+ cap = cv2.VideoCapture(source)+ ret, im0 = cap.read()+ success, buffer = cv2.imencode(".jpg", im0)+ if not success: raise RuntimeError("Failed to encode frame")+ source = buffer++ cap.release()+ im = letterbox(im0, new_shape=(1280, 1280), stride=32, auto=True)[0]+ im = im.transpose((2, 0, 1))[::-1]+ im = np.ascontiguousarray(im)+ im = Tensor(im).cast(dtypes.float32)+ im /= 255+ if len(im.shape) == 3: im = im[None]++ pred = model(im)+ pred = pred.numpy()[0]+ pred = pred[pred[:, 4] >= 0.25]+ class_labels = fetch('https://raw.githubusercontent.com/pjreddie/darknet/master/data/coco.names').read_text().split("\n")+ pred = rescale_bounding_boxes(pred, from_size=(im.shape[2:][::-1]), to_size=im0.shape[:2][::-1])+ Path('./outputs').mkdir(parents=True, exist_ok=True)+ draw_bounding_boxes_and_save(source, f"outputs/out_{size}.jpg", pred, class_labels)+