pytorch_misc
pytorch_misc copied to clipboard
ptrblck
Code snippets created for the PyTorch discussion board
Hi, ptrblck. Thanks for providing the example of sharing an array among different workers in `shared_array.py'. However, there's only one `Dataset` instance in the job. I'm wondering whether it still...
I am trying to add Unet as a preprocessing layer before the YOLOv6 architecture and when I am trying to do this, I am facing the following error. And how...
Hi Ptrblk, I am playing with PyTorch batchnorm2d and your implementation. I tried to use your implementation in mobilenetv3 and the performance seems similar. However, I found the gradient values...
The `padding` and `stride` arguments are swapped in `BaseConv`. Note that this does not fix that the architecture does not work with `stride != 1`.
Hi, ptrblck, I don't know why your target tensor the final dimension is a tuple. could you explain y = torch.randint(0, nb_classes, (1, 96, 96))
``` --------------------------------------------------------------------------- RuntimeError Traceback (most recent call last) in 1 inputs = torch.randn(1, 3, 222, 222).to(device) 2 print(inputs.dtype) ----> 3 outputs = unet(inputs) 4 print(outputs.shape) 5 print(outputs.dtype) ~/miniconda3/envs/deep_mol/lib/python3.6/site-packages/torch/nn/modules/module.py in __call__(self,...
Hi, It is about the piece of code [shared_dict](https://github.com/ptrblck/pytorch_misc/tree/master/shared_dict.py). Reproduced here with minor changes to track the memory consumption: ``` import resource from multiprocessing import Manager import torch from torch.utils.data...
