02-1tensorflow.nn主要功能模块

Activation Functions

• relu
• relu6
• elu
• softplus
• softsign
• dropout
• bias_add
• sigmoid
• tanh

Convolution

• conv2d
• depthwise_conv2d
• separable_conv2d
• atrous_conv2d
• conv2d_transpose
• conv3d

Pooling

• avg_pool
• max_pool
• max_pool_with_argmax
• avg_pool3d
• max_pool3d

Morphological filtering

Morphological operators are non-linear filters used in image processing.

• dilation2d
• erosion2d

Normalization

• l2_normalize
• local_response_normalization
• sufficient_statistics
• normalize_moments
• moments

Losses

• l2_loss
• log_poisson_loss

Classification

TensorFlow provides several operations that help you perform classification.

• sigmoid_cross_entropy_with_logits
• softmax
• log_softmax
• softmax_cross_entropy_with_logits
• sparse_softmax_cross_entropy_with_logits
• weighted_cross_entropy_with_logits

Embeddings

TensorFlow provides library support for looking up values in embedding tensors.

• embedding_lookup
• embedding_lookup_sparse

Recurrent Neural Networks

TensorFlow provides a number of methods for constructing Recurrent Neural Networks. Most accept an RNNCell-subclassed object (see the documentation for tf.nn.rnn_cell).

• dynamic_rnn
• rnn
• state_saving_rnn
• bidirectional_rnn

Conectionist Temporal Classification (CTC)

• ctc_loss
• ctc_greedy_decoder
• ctc_beam_search_decoder

Evaluation

The evaluation ops are useful for measuring the performance of a network. Since they are nondifferentiable, they are typically used at evaluation time.

• top_k
• in_top_k

Candidate Sampling

Do you want to train a multiclass or multilabel model with thousands or millions of output classes (for example, a language model with a large vocabulary)? Training with a full Softmax is slow in this case, since all of the classes are evaluated for every training example. Candidate Sampling training algorithms can speed up your step times by only considering a small randomly-chosen subset of contrastive classes (called candidates) for each batch of training examples.

Sampled Loss Functions

TensorFlow provides the following sampled loss functions for faster training.

• nce_loss
• sampled_softmax_loss

Candidate Samplers

TensorFlow provides the following samplers for randomly sampling candidate classes when using one of the sampled loss functions above.

• uniform_candidate_sampler
• log_uniform_candidate_sampler
• learned_unigram_candidate_sampler
• fixed_unigram_candidate_sampler

Miscellaneous candidate sampling utilities

• Miscellaneous candidate sampling utilities

Other Functions and Classes

• batch_normalization
• depthwise_conv2d_native