examples
examples copied to clipboard
pytorch
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
https://github.com/pytorch/examples/tree/master/time_sequence_prediction After a few steps, the loss suddenly jumps up and stays high: loss: 0.00101216329969 loss: 0.195070432582 the pdf0 is OK, pdf1 is OK but from pdf2 the graph becomes...
in order to test the performance conveniently, especially distributed training, it would be great to add an option to allow mock data input, which means directly random some data in...
I tried reducing the batch size to 4. It does not throw the error when using CPU. I ran the code with 15 epochs. 
For the super resolve run, I get this error ``` $ python super_resolve.py --input_image dataset/BSDS300/images/test/16077.jpg --model model_epoch_30.pth --output_filename out.png Namespace(cuda=False, input_image='dataset/BSDS300/images/test/16077.jpg', model='model_epoch_30.pth', output_filename='out.png') Traceback (most recent call last): File "super_resolve.py",...
In this file: https://github.com/pytorch/examples/blob/master/word_language_model/generate.py What does this input mean in the generation? input = torch.randint(ntokens, (1, 1), dtype=torch.long).to(device) As I understand it in a rnn-based language model, the last output...
I tried to train a model with the default settings but I received this "freeze_support" error. It tells me that freeze_support error needs to be omitted. I'm not sure where...
it is hard to understand the variable names in the dcgan example would it be possible to add more clear names and descriptions? this way we could more easily fiddle...
my os: windows 10 libtorch 1.0 visual studio 2015 I run cpp/mnist and got the right answer, but when I run cpp/dcgan, I got the error in file : D:\BUILD\libtorch\include\torch/csrc/utils/variadic.h(195):...
When I use Distribution in imagenet with one Node, there is three print at the same time. Just like this.  Is it right?
hi, should we save all the model in different rank when we use the distributeddataparallel? different rank seems do not share the same bn parameters. do we need to save...
