运行‘train.py’报错

[qlmx]

运行‘train.py’报错

[fwt1226]

已解决 图像维度问题
但是第一个epoch快跑完的时候出现内存泄漏：
（batch_size已修改为8）

RuntimeError: CUDA out of memory. Tried to allocate 20.25 MiB (GPU 0; 10.91 GiB total capacity; 9.48 GiB already allocated; 20.88 MiB free; 111.09 MiB cached)

train_batch/val_batch都改成4就能跑了

[QLMX]

需要结合你的机器调整验证集合的batch_size fwt1226 ***@***.***> 于2021年11月3日周三 下午5:06写道：

…

已解决 图像维度问题 但是第一个epoch快跑完的时候出现内存泄漏： RuntimeError: CUDA out of memory. Tried to allocate 20.25 MiB (GPU 0; 10.91 GiB total capacity; 9.48 GiB already allocated; 20.88 MiB free; 111.09 MiB cached) — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub <#29 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AF2A46CTHAIDQILWQCGJMQLUKD3R7ANCNFSM5HH2DOAQ> . Triage notifications on the go with GitHub Mobile for iOS <https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675> or Android <https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub>.

[fwt1226]

需要结合你的机器调整验证集合的batch_size fwt1226 @.***> 于2021年11月3日周三 下午5:06写道：
…
已解决 图像维度问题 但是第一个epoch快跑完的时候出现内存泄漏： RuntimeError: CUDA out of memory. Tried to allocate 20.25 MiB (GPU 0; 10.91 GiB total capacity; 9.48 GiB already allocated; 20.88 MiB free; 111.09 MiB cached) — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub <#29 (comment)>, or unsubscribe https://github.com/notifications/unsubscribe-auth/AF2A46CTHAIDQILWQCGJMQLUKD3R7ANCNFSM5HH2DOAQ . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub.

您好 我最终的验证准确率最高还是只能达到88 需要怎么调整呢？

[QLMX]

是不是图片格式不对，你可以先全量检测一下图片是否有问题 fwt1226 ***@***.***> 于2021年11月3日周三 上午9:52写道：

…

运行到某些图片时会中断，报以下错误： Traceback (most recent call last): File "/home/ubuntu/Desktop/huawei-garbage/train.py", line 260, in main() File "/home/ubuntu/Desktop/huawei-garbage/train.py", line 110, in main train_loss, train_acc, train_5 = train(train_loader, model, criterion, optimizer, epoch, use_cuda) File "/home/ubuntu/Desktop/huawei-garbage/train.py", line 163, in train for batch_idx, (inputs, targets) in enumerate(train_loader): File "/home/ubuntu/Desktop/huawei-garbage/venv/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 637, in *next* return self._process_next_batch(batch) File "/home/ubuntu/Desktop/huawei-garbage/venv/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 658, in _process_next_batch raise batch.exc_type(batch.exc_msg) AttributeError: Traceback (most recent call last): File "/home/ubuntu/Desktop/huawei-garbage/venv/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 138, in _worker_loop samples = collate_fn([dataset[i] for i in batch_indices]) File "/home/ubuntu/Desktop/huawei-garbage/venv/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 138, in samples = collate_fn([dataset[i] for i in batch_indices]) File "/home/ubuntu/Desktop/huawei-garbage/dataset.py", line 60, in *getitem* if img.layers == 1: File "/home/ubuntu/Desktop/huawei-garbage/venv/lib/python3.6/site-packages/PIL/Image.py", line 546, in *getattr* raise AttributeError(name) AttributeError: layers 请问是什么原因呢？ — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub <#29>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AF2A46HQTLYO6CCUVWADSRLUKCIWDANCNFSM5HH2DOAQ> . Triage notifications on the go with GitHub Mobile for iOS <https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675> or Android <https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub>.

[fwt1226]

是不是图片格式不对，你可以先全量检测一下图片是否有问题 fwt1226 @.***> 于2021年11月3日周三 上午9:52写道：
…

不好意思 全量检测是什么意思0.0

[QLMX]

就是检测一下你的图片格式，尺寸是不是有问题