EfficientNet-PyTorch
EfficientNet-PyTorch copied to clipboard
lukemelas
A PyTorch implementation of EfficientNet
Is it possible to use EfficientNet-PyTorch with half / mixed precision somehow? I know the mixed precision is supported by PyTorch for about a year, but what about pretrained weights?
Is it possible to add an input in one intermediate layer? For example: ```python y = self.conv_block1(image) y = self.conv_block2(y) y = self.conv_block3(y) y = self.conv_block4(y) # fusion y =...
I use this model(efficient b4) as backbone.However , it occupies a large memory when going on training.Anyone else meets this problem? But ,in fact,it's size
hello, Thanks for your great work! I try to convert keras model to pytorch pth file, however I can not get output because tf_to_pytorch do not support op set? how...
warnings.warn('You have chosen a specific GPU. This will completely ' Use GPU: 0 for training Loaded pretrained weights for efficientnet-b3 => using pre-trained model 'efficientnet-b3' Using image size 300 Traceback...
I implement EfficientNet-PyTorch with TensorRT C++ api(https://github.com/upczww/TensorRT-EfficientNet)
`python 3.8.0` `efficientnet-pytorch==0.7.0` I'm attempting to use EfficientNet for a transfer learning task. I am loading the model like: ```python model = EfficientNet.from_pretrained("efficientnet-b0", num_classes=2) ``` I'm training on multiple GPUs...
I was comparing this implementation with the original paper and it seems to me that either I am missing something (apologies in advance) or the parameters he is using are...
hello, I am little confused with using num_classes, according to documentaton "num_classes" is optional argument for both `from_pretrained` and `from_name` but in the code it is like that: ``` def...
Hello How are you? Thanks for contributing to this project. I have a question in your Conv2dDynamicSamePadding class. ``` class Conv2dDynamicSamePadding(nn.Conv2d): """2D Convolutions like TensorFlow, for a dynamic image size....
