EfficientNet-PyTorch
EfficientNet-PyTorch copied to clipboard
lukemelas
A PyTorch implementation of EfficientNet
Hi @lukemelas, Did you finish the upgrade of the code to version 2 of EfficientNet? Thank you!
Code: `net = EfficientNet.from_name(model_name='efficientnet-b5',in_channels=1)` Error: `TypeError: from_name() got an unexpected keyword argument 'in_channels'` By reading the source code, I found that from_name() contains the in_channels argument, as follows: ~~~ @classmethod...
in fastai, if we convert loaded model to sequential: mode = EfficientNet.from_pretrained('efficientnet-b0') model1 = nn.Sequential(*list(chiuldren(model))) not able to train using learn.fit_one_cycle. reported error is NotImplementedError
I train efficientnet-b3 with ImageNet dataset by the script in ./examples/imagenet/main.py with the following command `python main.py /path/to/imagenet -b 128 --image_size 300 -a 'efficient-b3' `. The GPU of my machine...
Hi, where could I find training details for pre-trained models?
Thank you very much for your contributions. The original version of efficientnet implements b0-b7. Where is the source of the paper of b8 in the current code, and what is...
Hello there, so I've been working with this repo for quite a time now, can say since it was released. Trying to extract GradCam images as explained here https://arxiv.org/abs/1610.02391 I...
Efficient-b0  flops:0.014819392 params:1.323016 I used pytorch's code to test, but found that params and FLOPs are much smaller than the paper's numerical values. I wonder why this is? It's...
Hi, I would like to extract features and the endpoints in one pass like in the original implementation. ``` import efficientnet_builder features, endpoints = efficientnet_builder.build_model_base(images, 'efficientnet-b0') ``` Can I call...
