EfficientNet-PyTorch
EfficientNet-PyTorch copied to clipboard
lukemelas
A PyTorch implementation of EfficientNet
I tried converting the EfficientNet-b4 model to TensorRT for optimized inference. It looks like there are some layers that don't have converters implemented and throws - AttributeError: 'Tensor' object has...
Hi, I am running a EfficientNet model built in tensorflow to classify some categories. The version of my TF is 2.7.0. I have already tried to save the checkpoints like...
@lukemelas Hi Luke, I am a student working on a project on disparity estimation. For that I have trained AnyNet model, however, while converting it to torchscript, I come across...
How can i extract layers till Conv2dStaticSamePadding: 3-245 and further add dense layer. i want to extract till [-1,2112,1,1]? any suggestion guys?? @lukemelas 
I don't see the initialization weights in similar tf code, is it not needed?
The default model input size is 224~600. What adjustments should I make to fit CIFAR-10's 32x32? ```py def efficientnet_params(model_name): """ Map EfficientNet model name to parameter coefficients. """ params_dict =...
Maybe it is a stupid question.I wonder how to train the model from scratch on a different dataset with a different classes,say,10 classes?
Hi, Thank you for sharing your code! I'm wondering how you might apply the efficientNet-pytorch code to the state farm distracted driver dataset? Thanks in advance.
I'm trying to use pretrained model b-1 to train the model on Places365 but the training is blocking at ~25% (accuracy). I used Imagenet auto-augment policy founded [here](https://github.com/DeepVoltaire/AutoAugment/blob/master/autoaugment.py) using this...
**The problem** There was a scenario on the code where a Python built-in name was being shadowed. It's a good practice to never replace built-in methods with variables, since it...
