在 pytorch 中使用 DataLoader 时对批量大小感到困惑

Question

I am new to pytorch. I am training an ANN for classification on the MNIST dataset.

train_loader = DataLoader(train_data,batch_size=200,shuffle=True)

I am confused. The dataset is of 60,000 images and I have set batch size of 6000 and my model has 30 epochs. Will every epoch see only 6000 images or will every epoch see 10 batches of 6000 images?

Answer 1

Every call to the dataset iterator will return batch of images of size batch_size . Hence you will have 10 batches until you exhaust all the 60000 images.