Add object detection, tracking, mobile notifications, and search to any security camera.
Prepost (#132)
Rory Clear1e5d0f662cf0
diff --git a/clearcam.py b/clearcam.pyindex 16537ba..ed23720 100644--- a/clearcam.py+++ b/clearcam.py@@ -489,10 +489,8 @@ class VideoCapture:def run_inference(self, frame):frame = Tensor(frame)- pre = model.preprocess(frame)- preds = model(pre).numpy()+ preds = model(frame).numpy()thresh = (self.settings.get("threshold") if self.settings else 0.5) or 0.5 #todo clean!- preds = model.scale_boxes(pre.shape[:2], preds, frame.shape)online_targets = tracker.update(preds, thresh)if type(model) == RFDETR: # RF-DETR has different class_idsfor j in range(len(online_targets)): online_targets[j].class_id = detr_to_yolo[int(online_targets[j].class_id)]diff --git a/detection/rfdetr.py b/detection/rfdetr.pyindex fa1d969..0716bcd 100644--- a/detection/rfdetr.py+++ b/detection/rfdetr.py@@ -609,8 +609,9 @@ class RFDETR():load_state_dict(self, state_dict)@TinyJit- def __call__(self, processed_images):- predictions = self.predict(processed_images)+ def __call__(self, frame):+ pre = self.preprocess(frame)+ predictions = self.predict(pre)out_logits, out_bbox = predictionsprob = out_logits.sigmoid()topk_values, topk_indexes = Tensor.topk(prob.view(out_logits.shape[0], -1), 300, dim=1)@@ -619,6 +620,7 @@ class RFDETR():boxes = box_cxcywh_to_xyxy(out_bbox)boxes = Tensor.gather(boxes, 1, topk_boxes.unsqueeze(-1).repeat(1,1,4))ret = Tensor.cat(boxes.squeeze(0), topk_values.squeeze(0).unsqueeze(1), labels.squeeze(0).unsqueeze(1), dim=1)+ ret = self.scale_boxes(pre.shape[:2], ret, frame.shape)return retdef predict(self, samples, targets=None):@@ -636,7 +638,6 @@ class RFDETR():outputs_class = self.class_embed(hs)[-1]return outputs_class, outputs_coord[-1]- @TinyJitdef preprocess(self, img):img = img.cast(dtypes.float32)img /= 255.0@@ -648,7 +649,7 @@ class RFDETR():return imgdef scale_boxes(self, img1_shape, predictions, img0_shape):- predictions[:,:4] *= [img0_shape[1], img0_shape[0], img0_shape[1], img0_shape[0]]+ predictions[:,:4] *= Tensor([img0_shape[1], img0_shape[0], img0_shape[1], img0_shape[0]])return predictionsdef compute_iou_matrix(boxes):diff --git a/detection/yolov9.py b/detection/yolov9.pyindex 623cf02..fbad543 100644--- a/detection/yolov9.py+++ b/detection/yolov9.py@@ -372,8 +372,9 @@ class YOLOv9():load_state_dict(self, state_dict)@TinyJit- def __call__(self, x):- x = x.unsqueeze(0)+ def __call__(self, frame):+ pre = self.preprocess(frame)+ x = pre.unsqueeze(0)x = x.permute(0, 3, 1, 2)x = x / 255.0y = [] # outputs@@ -382,10 +383,10 @@ class YOLOv9():if m.f != -1: x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f]x = m(x)y.append(x)-- return postprocess(x[0])[0]+ preds = postprocess(x[0])[0]+ preds = self.scale_boxes(pre.shape[:2], preds, frame.shape)+ return preds- @TinyJitdef preprocess(self, image, new_shape=None, auto=True, scaleFill=False, scaleup=True, stride=32) -> Tensor:if new_shape is None: new_shape = self.resshape = image.shape[:2]@@ -403,21 +404,21 @@ class YOLOv9():return imagedef scale_boxes(self, img1_shape, predictions, img0_shape):- gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1])- pad = ((img1_shape[1] - img0_shape[1] * gain) / 2, (img1_shape[0] - img0_shape[0] * gain) / 2)- for pred in predictions:- boxes_np = pred[:4].numpy() if isinstance(pred[:4], Tensor) else pred[:4]- boxes_np[..., [0, 2]] -= pad[0]- boxes_np[..., [1, 3]] -= pad[1]- boxes_np[..., :4] /= gain- boxes_np = clip_boxes(boxes_np, img0_shape)- pred[:4] = boxes_np- return predictions+ gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1])+ pad_x = (img1_shape[1] - img0_shape[1] * gain) / 2+ pad_y = (img1_shape[0] - img0_shape[0] * gain) / 2+ boxes = predictions[:, :4].contiguous()+ boxes[:, [0, 2]] -= pad_x+ boxes[:, [1, 3]] -= pad_y+ boxes /= gain+ boxes = clip_boxes(boxes, img0_shape)+ predictions[:, :4] = boxes+ return predictionsdef clip_boxes(boxes, shape):- boxes[..., [0, 2]] = np.clip(boxes[..., [0, 2]], 0, shape[1]) # x1, x2- boxes[..., [1, 3]] = np.clip(boxes[..., [1, 3]], 0, shape[0]) # y1, y2- return boxes+ boxes[..., [0, 2]] = boxes[..., [0, 2]].clip(0, shape[1])+ boxes[..., [1, 3]] = boxes[..., [1, 3]].clip(0, shape[0])+ return boxesdef resize(img, new_size):img = img.permute(2,0,1)diff --git a/test/run_mot.py b/test/run_mot.pyindex ae7ed0a..ee3e340 100644--- a/test/run_mot.py+++ b/test/run_mot.py@@ -31,9 +31,7 @@ if __name__ == "__main__":if not ret: breakim = im0im = Tensor(im).cast(dtypes.float32)- im = model.preprocess(im)pred = model(im).numpy()- pred = model.scale_boxes(im.shape[:2], pred, im0.shape)online_targets = ocs_tracker.update(pred, 0.25)if type(model) == RFDETR: # RF-DETR has different class_idsfor j in range(len(online_targets)): online_targets[j].class_id = detr_to_yolo[int(online_targets[j].class_id)]