训练的问题？

[mr-xiao-zuo]

单独训练LaSOT数据集，修改了config.py中的C.DATASET.NAMES=('LaSOT')和config.yaml中的DATASET:NAMES: - 'LaSOT'之后，执行train.py，报如下错误，请问什么原因造成的呢？ Traceback (most recent call last): File "/home/dl/code/SiamCAR-master/tools/train.py", line 315, in main() File "/home/dl/code/SiamCAR-master/tools/train.py", line 310, in main train(train_loader, dist_model, optimizer, lr_scheduler, tb_writer) File "/home/dl/code/SiamCAR-master/tools/train.py", line 171, in train for idx, data in enumerate(train_loader): File "/home/dl/anaconda3/envs/siamcar/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 819, in next return self._process_data(data) File "/home/dl/anaconda3/envs/siamcar/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 846, in _process_data data.reraise() File "/home/dl/anaconda3/envs/siamcar/lib/python3.6/site-packages/torch/_utils.py", line 369, in reraise raise self.exc_type(msg) AttributeError: Caught AttributeError in DataLoader worker process 0. Original Traceback (most recent call last): File "/home/dl/anaconda3/envs/siamcar/lib/python3.6/site-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop data = fetcher.fetch(index) File "/home/dl/anaconda3/envs/siamcar/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/home/dl/anaconda3/envs/siamcar/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 44, in data = [self.dataset[idx] for idx in possibly_batched_index] File "/home/dl/code/SiamCAR-master/pysot/datasets/dataset.py", line 248, in getitem__ template_box = self._get_bbox(template_image, template[1]) File "/home/dl/code/SiamCAR-master/pysot/datasets/dataset.py", line 207, in _get_bbox imh, imw = image.shape[:2] AttributeError: 'NoneType' object has no attribute 'shape'

Process finished with exit code 1

[WangJun-ZJUT]

Thank you for your question. This problem is usually caused by a wrong path. We suggest that you should check the path of datasets .

[Bennett-H]

您好,我想问一下,为什么我训练出来的模型没有代码给定的效果那么好?

[eilo1234]

您好,我想问一下,为什么我训练出来的模型没有代码给定的效果那么好?

我也遇到了这个问题，请问你后来有解决吗？

[mr-xiao-zuo]

您好,我想问一下,为什么我训练出来的模型没有代码给定的效果那么好?

我也遇到了这个问题，请问你后来有解决吗？

请问你解决这个问题了吗？

[mr-xiao-zuo]

您好,我想问一下,为什么我训练出来的模型没有代码给定的效果那么好?

您训练到最后总的损失是多少呢？

[Giveupfree]

同问，GOT10K版本和作者的差了10个点左右，会不会作者的结果有问题

[Mionger]

你好，请问您这个问题解决了吗，应该怎么处理呢

[chenxlin222]

您好，想请教个问题：如果只用got-10k训练，需要修改__C.DATASET.GOT.NUM_USE (100000)， C.DATASET.VIDEOS_PER_EPOCH (600000)，C.TRAIN.EPOCH (20)这些参数吗？如果不修改的话，就会有20*600000数据量，训练时间太太太长了，如果修改，应该改成多少比较合适呢？