examples
examples copied to clipboard
pytorch
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
In the language model example, it seems that during the evaluation, the code starts from computing the loss of the second word. Thus, skipping the loss of the first word....
I have trained a best model by imagenet,but code repo has given does not have test option,so how can I use the model have trained to classifier pictures with labels?
Using --resume fails after 1 epoch with Pytorch 1.0 release with error below. I tried this with resnet50 and resnet18 ``` Traceback (most recent call last): File "main.py", line 398,...
I'm getting a crash in the mnist example at the end of the 1st epoch when I run with any num_workers > 0 I'm running the python code in PyCharm...
It is a common sense that, during evaluation, the model is not trained by the dev dataset. However, I noticed a strange different behavior between the two results: (1) train...
`python main.py -a inception_v3 ./imagenet/cat2dog --batch-size 16 --print-freq 1 --pretrained;` => using pre-trained model 'inception_v3' Traceback (most recent call last): File "main.py", line 314, in main() File "main.py", line 157,...
As pointed out in https://github.com/pytorch/examples/issues/164, the imagenet training gets almost zero gpu utilization, I'm using `python main.py -a resnet18 /home/wangtao/imagenet/ILSVRC/Data/CLS-LOC` ``` Epoch: [0][1760/5005] Time 1.599 (2.648) Data 1.296 (2.388) Loss...
Example code (mnist) does not work under torch.utils.bottleneck. This is solved by changing the value num_workers from 1 to 0. It needs to check other examples also. Reference https://github.com/pytorch/pytorch/issues/6313 https://discuss.pytorch.org/t/cannot-measure-cuda-usage-on-mnist-example/21600/2
Hi, I am wondering if there is a theoretical reason for using BCE as a reconstruction loss for variation auto-encoders ? Can't we simply use MSE or norm-based reconstruction loss...
