jayphone17forReal comments

Results 8 comments of


                                            jayphone17forReal

how to use tensorboard to visual for yolox?

when you start your training, system will automatically generate a folder named `YOLOX_outputs`, `cd YOLOX/YOLOX_outputs` and then `tensorboard --logdir yolox_voc_s/ --port 6006` to start visualizing the training process. Hope you...

KeyError: 'Traceback (most recent call last):\n File "E:\\anaconda\\anaconda\\envs\\pytorch\\lib\\site-packages\\torch\\utils\\data\\dataloader.py", line 138, in _worker_loop\n samples = collate_fn([dataset[i] for i in batch_indices])\n File "E:\\anaconda\\anaconda\\envs\\pytorch\\lib\\site-packages\\torch\\utils\\data\\dataloader.py", line 138, in <listcomp>\n samples = collate_fn([dataset[i] for i in batch_indices])\n File "F:\\ssd.pytorch-master\\data\\voc0712.py", line 111, in getitem\n im, gt, h, w = self.pull_item(index)\n File "F:\\ssd.pytorch-master\\data\\voc0712.py", line 126, in pull_item\n target = self.target_transform(target, width, height)\n File "F:\\ssd.pytorch-master\\data\\voc0712.py", line 68, in call\n label_idx = self.class_to_ind[name]\nKeyError: \'pointer_instrument\'\n'

same issue, have you solved it ? thanks a lot

KeyError: 'Traceback (most recent call last):\n File "E:\\anaconda\\anaconda\\envs\\pytorch\\lib\\site-packages\\torch\\utils\\data\\dataloader.py", line 138, in _worker_loop\n samples = collate_fn([dataset[i] for i in batch_indices])\n File "E:\\anaconda\\anaconda\\envs\\pytorch\\lib\\site-packages\\torch\\utils\\data\\dataloader.py", line 138, in <listcomp>\n samples = collate_fn([dataset[i] for i in batch_indices])\n File "F:\\ssd.pytorch-master\\data\\voc0712.py", line 111, in getitem\n im, gt, h, w = self.pull_item(index)\n File "F:\\ssd.pytorch-master\\data\\voc0712.py", line 126, in pull_item\n target = self.target_transform(target, width, height)\n File "F:\\ssd.pytorch-master\\data\\voc0712.py", line 68, in call\n label_idx = self.class_to_ind[name]\nKeyError: \'pointer_instrument\'\n'

Loading base network... Initializing weights... Loading the dataset... Training SSD on: SMOKE Using the specified args: Namespace(basenet='vgg16_reducedfc.pth', batch_size=8, cuda=True, dataset='VOC', dataset_root='E:/ssd.pytorch/data/VOCdevkit/VOCsmoke/', gamma=0.1, lr=1e-05, momentum=0.9, num_workers=4, resume=None, s4, resume=None, save_folder='E:/ssd.pytorch/weights/', start_iter=0,...

KeyError: 'Traceback (most recent call last):\n File "E:\\anaconda\\anaconda\\envs\\pytorch\\lib\\site-packages\\torch\\utils\\data\\dataloader.py", line 138, in _worker_loop\n samples = collate_fn([dataset[i] for i in batch_indices])\n File "E:\\anaconda\\anaconda\\envs\\pytorch\\lib\\site-packages\\torch\\utils\\data\\dataloader.py", line 138, in <listcomp>\n samples = collate_fn([dataset[i] for i in batch_indices])\n File "F:\\ssd.pytorch-master\\data\\voc0712.py", line 111, in getitem\n im, gt, h, w = self.pull_item(index)\n File "F:\\ssd.pytorch-master\\data\\voc0712.py", line 126, in pull_item\n target = self.target_transform(target, width, height)\n File "F:\\ssd.pytorch-master\\data\\voc0712.py", line 68, in call\n label_idx = self.class_to_ind[name]\nKeyError: \'pointer_instrument\'\n'

and the line 156 is : try: images, targets = next(batch_iterator) except StopIteration: batch_iterator = iter(data_loader) images, targets = next(batch_iterator)

jayphone17forReal

how to use tensorboard to visual for yolox?

KeyError: Caught KeyError in DataLoader worker process 0.

KeyError: Caught KeyError in DataLoader worker process 0.

热力图

Multi-GPU training hangs