EfficientNet-PyTorch
EfficientNet-PyTorch copied to clipboard
lukemelas
A PyTorch implementation of EfficientNet
when I want to save the trained Model as .pt. The error is (RuntimeError: Could not export Python function call 'SwishImplementation'. Remove calls to Python functions before export. Did you...
Using the pretrained model, encounter the error when i change the num of class to 3 from default 1000. Or is it not meant to change class if using the...
Hi, Thanks for the PyTorch implementation. It is really good. However, I've ran into some issues. While exporting using torch.onnx, I am getting an error. The code is as follows:...
I use [mypy](https://mypy-lang.org/) and want to have type hints for retrying to fix this error: ``` error: Skipping analyzing "efficientnet_pytorch": module is installed, but missing library stubs or py.typed marker...
Hi all, I pretrained myself using EfficientNet B0 with 5 classes, and.. Now I have been loaded using below code: model = EfficientNet.from_pretrained('efficientnet-b0', weight_path = './weights_path/model.pt', num_classess=5) and i'm using...
Just trying to understand what happens when in_channels=1. Every time I rerun the script the _conv_stem.weight is different each time. When in_channels=3 it is the same each time. It seems...
The AutoEncoder is implemented by reverse the forward EfficientNet as a decoder, current implementation only uses Dynamic Padding for TransposedConv2d which works fine for me now.
from_pretrained() got an unexpected keyword argument 'weights_path' EfficientNet.from_pretrained(model_name='efficientnet-b3', weights_path='efficientnet-b3-5fb5a3c3.pth')
