在Pythorch上建立库以提高生产率
torchfuel的Python项目详细描述
torchfuel
建立在Pythorch之上以提高生产率。
功能
- 通用培训师
- 分类训练器(具有交叉熵损失)
- MSE培训师
- 附加实用程序层
- 更好的数据加载程序(目前仅适用于图像数据集)
分类示例
importosimporttimefromcollectionsimportnamedtupleimporttorchimporttorch.nnasnnimporttorch.optimasoptimfromtorch.optimimportlr_schedulerfromtorchvisionimportdatasets,models,transformsfromtorchfuel.data_loaders.imageimportImageDataLoaderfromtorchfuel.trainers.classificationimportClassificationTrainerfromtorchfuel.transforms.noiseimportDropPixelNoiserdl=ImageDataLoader(train_data_folder='imgs/train',eval_data_folder='imgs/eval',pil_transformations=[transforms.RandomHorizontalFlip()]tensor_transformations=[DropPixelNoiser()],batch_size=64,imagenet_format=True,)train_dataloader,eval_dataloader,n_classes=dl.prepare()device=torch.device('cuda:0'iftorch.cuda.is_available()else'cpu')model=Model(...).to(device)optimiser=optim.SGD(model.parameters(),lr=0.01,momentum=0.9)scheduler=optim.lr_scheduler.ReduceLROnPlateau(optimiser,'min',patience=20)trainer=ClassificationTrainer(device,model,optimiser,scheduler)fitted_model=trainer.fit(epochs,train_dataloader,eval_dataloader)
如何安装
克隆存储库并运行:
pip install .
可选(不是最新的):
pip install torchfuel