博主自己用PascalVOC训练的权重成功了吗？

[ouyang11111]

我用PascalVOC训练的权重 失败了 boxes = outputs[:,0:4]

[ouyang11111]

I can run only in your own .pth while trained myself's (pascalVOC) it failed

return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] Traceback (most recent call last): File "/home/55/yolox-deepsort-main/000.py", line 50, in main() File "/home/55/yolox-deepsort-main/000.py", line 24, in main result = det.feedCap(im) #BGR #this wrong File "/home/55/yolox-deepsort-main/BaseDetector.py", line 35, in feedCap im, faces, face_bboxes = update_tracker(self, im) File "/home/55/yolox-deepsort-main/tracker.py", line 41, in updatetracker , bboxes = target_detector.detect(image) #wrong take place in here File "/home/55/yolox-deepsort-main/AIDetector_pytorch.py", line 121, in detect boxes = outputs[:, 0:4] #every channel get 4 value TypeError: 'NoneType' object is not subscriptable

[EchoYGemini]

我训练自己的voc权重也不行QAQ 但报错跟你不一样

Traceback (most recent call last): File "D:/pythonProject3/yolox-deepsort-main2/demo.py", line 62, in main() File "D:/pythonProject3/yolox-deepsort-main2/demo.py", line 12, in main det = Detector() File "D:\pythonProject3\yolox-deepsort-main2\AIDetector_pytorch.py", line 45, in init self.init_model() File "D:\pythonProject3\yolox-deepsort-main2\AIDetector_pytorch.py", line 74, in init_model model.load_state_dict(ckpt["model"]) File "D:\Develop\python\Anaconda3\envs\Pychramproject2\lib\site-packages\torch\nn\modules\module.py", line 1051, in load_state_dict raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format( RuntimeError: Error(s) in loading state_dict for YOLOX: size mismatch for head.cls_preds.0.weight: copying a param with shape torch.Size([1, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([80, 128, 1, 1]). size mismatch for head.cls_preds.0.bias: copying a param with shape torch.Size([1]) from checkpoint, the shape in current model is torch.Size([80]). size mismatch for head.cls_preds.1.weight: copying a param with shape torch.Size([1, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([80, 128, 1, 1]). size mismatch for head.cls_preds.1.bias: copying a param with shape torch.Size([1]) from checkpoint, the shape in current model is torch.Size([80]). size mismatch for head.cls_preds.2.weight: copying a param with shape torch.Size([1, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([80, 128, 1, 1]). size mismatch for head.cls_preds.2.bias: copying a param with shape torch.Size([1]) from checkpoint, the shape in current model is torch.Size([80]).