Cheat sheet

PyTorch and TensorFlow

Tensors, models, losses, data pipelines, training loops, optimizers, mixed precision, checkpoints, and debugging.

Layer	PyTorch	Keras
Dense	nn.Linear	Dense
Convolution	nn.Conv2d	Conv2D
Normalization	nn.BatchNorm2d, nn.LayerNorm	BatchNormalization, LayerNormalization
Embedding	nn.Embedding	Embedding
Recurrent	nn.LSTM, nn.GRU	LSTM, GRU
Attention	nn.MultiheadAttention	MultiHeadAttention

Task	PyTorch	Keras
Multiclass	CrossEntropyLoss (logits)	SparseCategoricalCrossentropy(from_logits=True)
Binary / multilabel	BCEWithLogitsLoss	BinaryCrossentropy(from_logits=True)
Regression	MSELoss, HuberLoss	MeanSquaredError, Huber