Skip to content

lyhue1991/torchkeras

Repository files navigation

Pytorch❤️Keras

The torchkeras library is a simple tool for training neural network in pytorch jusk in a keras style. 😋😋

torchkeras ❤️ wandb: https://wandb.ai/lyhue1991/mnist_torchkeras


Open In Kaggle

1, Introduction

With torchkeras, You need not to write your training loop with many lines of code, all you need to do is just

like these two steps as below:

(i) create your network and wrap it and the loss_fn together with torchkeras.KerasModel like this: model = torchkeras.KerasModel(net,loss_fn=nn.BCEWithLogitsLoss()) a metrics_dict parameter is optional.

(ii) fit your model with the training data and validate data.

The main code of use torchkeras is like below.

import torch 
import torchkeras

#use torchkeras.KerasModel 
model = torchkeras.KerasModel(net,
                              loss_fn = nn.BCEWithLogitsLoss(),
                              optimizer= torch.optim.Adam(net.parameters(),lr = 0.001),
                              metrics_dict = {"acc":torchmetrics.Accuracy(task='binary')}
                             )
dfhistory=model.fit(train_data=dl_train, 
                    val_data=dl_val, 
                    epochs=20, 
                    patience=3, 
                    ckpt_path='checkpoint.pt',
                    monitor="val_acc",
                    mode="max")

This project seems somehow powerful, but the source code is very simple.

Actually, only about 200 lines of Python code.

If you want to understand or modify some details of this project, feel free to read and change the source code!!!

2, Features

Besides the basic torchkeras.KerasModel, another powerful class torchkeras.LightModel is created to support pytorch_lightning training style.

The KerasModel is much simpler, and is recommended for beginner users.

The LightModel borrows many features from the library pytorch_lightning and shows a best practice.

Although different, the usage of torchkeras.KerasModel and torchkeras.LightModel is very similar.

features torchkeras.KerasModel 🔥🔥🔥 torchkeras.LightModel
progress bar
early stopping
metrics from torchmetrics
gpu training
multi-gpus training(ddp)
tensorboard callback
pretty wandb callback
other callbacks from pytorch_lightning
simple code

3, Basic Examples

You can follow these full examples to get started with torchkeras.

Have fun!😋😋

example read notebook code run example in kaggle
①kerasmodel basic 🔥🔥 torchkeras.KerasModel example
Open In Kaggle

②kerasmodel wandb 🔥🔥🔥 torchkeras.KerasModel with wandb demo
Open In Kaggle

③kerasmodel tunning 🔥🔥🔥 torchkeras.KerasModel with wandb sweep demo
Open In Kaggle

④kerasmodel tensorboard torchkeras.KerasModel with tensorboard example
⑤kerasmodel ddp/tpu torchkeras.KerasModel ddp tpu examples
Open In Kaggle

⑥lightmodel basic torchkeras.LightModel example
⑦lightmodel tensorboard torchkeras.LightModel with tensorboard example

If you want to understand or modify some details of this project, feel free to read and change the source code!!!

Any other questions, you can contact the author form the wechat official account below:

算法美食屋