deep_sort_yolov3
deep_sort_yolov3 copied to clipboard
Qidian213
Real-time Multi-person tracker using YOLO v3 and deep_sort with tensorflow
The code is compatible with Python 2.7 and 3. The following dependencies are needed to run the tracker: NumPy sklean OpenCV Pillow The name should be sklearn, not sklean
i add these code to set the gpu fraction, the yolo part (yolo.py) class YOLO(object): def __init__(self): self.model_path = 'model_data/yolo.h5' #self.model_path = 'model_data/yolo_tiny.h5' self.anchors_path = 'model_data/yolo_anchors.txt' self.classes_path = 'model_data/coco_classes.txt' self.score...
File "C:\...\deep_sort_yolov3-master\demo.py", line 132, in main(YOLO()) File "C:\...\deep_sort_yolov3-master\demo.py", line 87, in main tracker.update(detections) File "C:\...\deep_sort_yolov3-master\deep_sort\tracker.py", line 69, in update self._match(detections) File "C:\...\deep_sort_yolov3-master\deep_sort\tracker.py", line 127, in _match detections, iou_track_candidates, unmatched_detections) File...
ValueError: Cannot feed value of shape (1, 416, 416, 3) for Tensor 'input_1:0', which has shape '(?, 608, 608, 3)'
When I run it on CPU, it works well but throws CUDNN related error message. I did not find any solution. Why is not running on GPU? The complete error...
can you please share the requirements.txt file containing all the packages and version list?
Hi @Qidian213 I want to convert frozen graph of this model to tensorRt Engine. Have you done this? if you have done please share the script other wise please provide...
How can I separate each different class to calculate the number?
请教在demo.py中，encoder = gdet.create_box_encoder(model_filename, batch_size=1)的batch_size有什么用？ 我设置不同的值，好像与速度关系不大。
