imgclsmob
imgclsmob copied to clipboard
osmr
Sandbox for training deep learning networks
Hi, thank you for your good code, recently I've tried to reproduce RevNet with PyTorch 1.11.0, and I use your code. However, I got a RunError as follows: ```console File...
Not sure if you would like me to do the same for all the other TF models, but I can. Also did not add unit tests, but this is also...
pytorch now supports the XDG Base Directory specification https://github.com/pytorch/pytorch/issues/14693. The `pytorchcv` module, provided by this repo is still [using the hardcoded `~/.torch/models` path](https://github.com/osmr/imgclsmob/blob/f2993d3ce73a2f7ddba05da3891defb08547d504/pytorch/pytorchcv/models/model_store.py#L617). You can see the "correct" logic for...
 PyramidNet's residual block(d) is not the same as pre-resnet's(a). It deletes the first ReLU and adds a new BN at the end. I noticed that in the pytorch version...
Hi thank you for wonderful DL networks repo. I have one question to ask about pytorchcv in `pytorch/pytorchcv/models/squeezenext.py` I found that SqueezeNext class has `in_size` argument but never being used....
Is that possible to provide pretrained vgg model checkpoints (for example, bn-vgg11/13/16/19) for CIFAR10/100? Thanks!
Are there any plans to add some ViT models with their pretrained weights (ImageNet)? https://github.com/lucidrains/vit-pytorch
Hello! I've found a performance issue in your project: - `tf.Session` being defined repeatedly leads to incremental overhead. You can make your program more efficient by fixing this bug. Here...
pytorch=>'seresnext50_32x4d'=>model=>Different input and output
It is always desirable to try the latest neural network model, but unfortunately there is no researched by deepmind in this code base, and I look forward to adding it...