关于detector的train

[Carl-Lei]

我在python3.6训练时出现错误 Traceback (most recent call last): File "main.py", line 349, in main() File "main.py", line 168, in main train(train_loader, net, loss, epoch, optimizer, get_lr, args.save_freq, save_dir) File "main.py", line 180, in train for i, (data, target, coord) in enumerate(data_loader): File "C:\ProgramData\Anaconda3\lib\site-packages\torch\utils\data\dataloader.py", line 451, in iter return _DataLoaderIter(self) File "C:\ProgramData\Anaconda3\lib\site-packages\torch\utils\data\dataloader.py", line 247, in init self._put_indices() File "C:\ProgramData\Anaconda3\lib\site-packages\torch\utils\data\dataloader.py", line 295, in _put_indices indices = next(self.sample_iter, None) File "C:\ProgramData\Anaconda3\lib\site-packages\torch\utils\data\sampler.py", line 138, in iter for idx in self.sampler: File "C:\ProgramData\Anaconda3\lib\site-packages\torch\utils\data\sampler.py", line 51, in iter return iter(torch.randperm(len(self.data_source)).tolist()) TypeError: 'float' object cannot be interpreted as an integer 不知道这里的‘float’指的时哪个变量？这种情况下，怎么改啊？

[lfz]

Dataparalle 包住model的情况下没法debug，你把dataparallel 去掉

On 13 Jul 2018, at 2:44 PM, Carl-Lei <[email protected] mailto:[email protected]> wrote:

我在python3.6训练时出现错误 Traceback (most recent call last): File "main.py", line 349, in main() File "main.py", line 168, in main train(train_loader, net, loss, epoch, optimizer, get_lr, args.save_freq, save_dir) File "main.py", line 180, in train for i, (data, target, coord) in enumerate(data_loader): File "C:\ProgramData\Anaconda3\lib\site-packages\torch\utils\data\dataloader.py", line 451, in iter return _DataLoaderIter(self) File "C:\ProgramData\Anaconda3\lib\site-packages\torch\utils\data\dataloader.py", line 247, in init self._put_indices() File "C:\ProgramData\Anaconda3\lib\site-packages\torch\utils\data\dataloader.py", line 295, in _put_indices indices = next(self.sample_iter, None) File "C:\ProgramData\Anaconda3\lib\site-packages\torch\utils\data\sampler.py", line 138, in iter for idx in self.sampler: File "C:\ProgramData\Anaconda3\lib\site-packages\torch\utils\data\sampler.py", line 51, in iter return iter(torch.randperm(len(self.data_source)).tolist()) TypeError: 'float' object cannot be interpreted as an integer 不知道这里的‘float’指的时哪个变量？这种情况下，怎么改啊？

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/lfz/DSB2017/issues/94, or mute the thread https://github.com/notifications/unsubscribe-auth/AIigQ7dalUmhcp1GheAE0xwWDuyfA0zbks5uGEHngaJpZM4VOYXr.

[Carl-Lei]

我把第99行的net = DataParallel(net)注释掉，还是不行啊，报同样的错误

[Carl-Lei]

@lfz

[Carl-Lei]

这个问题好像解决了。是因为在DataBowl3Detector的类里面 def len(self): if self.phase == 'train': return len(self.bboxes)/(1-self.r_rand) 这里是要return一个整数吗？ @lfz

[Carl-Lei]

@lfz 这一句为什么会报错啊？input_size=(128,128,128), stride=4 这个取余的判断怎么会是False呢？ Traceback (most recent call last): File "D:/mydsb/dsb_test/training/detector/main.py", line 349, in main() File "D:/mydsb/dsb_test/training/detector/main.py", line 168, in main train(train_loader, net, loss, epoch, optimizer, get_lr, args.save_freq, save_dir) File "D:/mydsb/dsb_test/training/detector/main.py", line 180, in train for i, (data, target, coord) in enumerate(data_loader): File "C:\ProgramData\Anaconda3\lib\site-packages\torch\utils\data\dataloader.py", line 272, in next return self._process_next_batch(batch) File "C:\ProgramData\Anaconda3\lib\site-packages\torch\utils\data\dataloader.py", line 307, in _process_next_batch raise batch.exc_type(batch.exc_msg) AssertionError: Traceback (most recent call last): File "C:\ProgramData\Anaconda3\lib\site-packages\torch\utils\data\dataloader.py", line 57, in _worker_loop samples = collate_fn([dataset[i] for i in batch_indices]) File "C:\ProgramData\Anaconda3\lib\site-packages\torch\utils\data\dataloader.py", line 57, in samples = collate_fn([dataset[i] for i in batch_indices]) File "D:\mydsb\dsb_test\training\detector\data.py", line 96, in getitem label = self.label_mapping(sample.shape[1:], target, bboxes) File "D:\mydsb\dsb_test\training\detector\data.py", line 273, in call assert(int(input_size[i])% stride == 0) AssertionError

[shenlinyao]

def len(self):
if self.phase == 'train':
return len(self.bboxes)/(1-self.r_rand)

解决了吗，我也有这个问题，我把/改成//，好像也不行

[Carl-Lei]

@shenlinyao 我是强行转换为int类型的 return int(len(self.bboxes)/(1-self.r_rand))

[DaLei001]

@Carl-Lei 同样遇到了“assert(int(input_size[i])% stride == 0) AssertionError”的问题，请问你解决了这个问题了吗？

[lihaossu]

@DaLei001 请问 config里面的'luna_segment':'/work/DataBowl3/luna/seg-lungs-LUNA16/'的路径是什么？需要一些额外的数据吗？还是直接建立一个空的文件？

[chenggangdu]

@DaLei001 请问 config里面的'luna_segment':'/work/DataBowl3/luna/seg-lungs-LUNA16/'的路径是什么？需要一些额外的数据吗？还是直接建立一个空的文件？

这是LUNA的一个文件夹