Skip to content

P
Paddle

BaiXuePrincess / Paddle
与 Fork 源项目一致

Fork自 PaddlePaddle / Paddle

通知 1
Star 1
Fork 0
P
Paddle
“8750b689438d6d2ba4d0d4f635f7b655d78a9b3e”上不存在“deploy/git@gitcode.net:paddlepaddle/PaddleSeg.git”
未验证 提交 dfde0eaa 编写于 作者: K Kaipeng Deng 提交者： GitHub
浏览文件
操作

[cherry-pick] refine en doc (#20360) 

* refine en doc. test=develop. test=document_fix
上级 ddb4b337
隐藏空白更改
内联 并排
Showing with 288 addition and 134 deletion
paddle/fluid/API.spec
浏览文件 @ dfde0eaa
...@@ -145,10 +145,10 @@ paddle.fluid.layers.conv3d (ArgSpec(args=['input', 'num_filters', 'filter_size', ...@@ -145,10 +145,10 @@ paddle.fluid.layers.conv3d (ArgSpec(args=['input', 'num_filters', 'filter_size',
paddle.fluid.layers.sequence_pool (ArgSpec(args=['input', 'pool_type', 'is_test', 'pad_value'], varargs=None, keywords=None, defaults=(False, 0.0)), ('document', '5a709f7ef3fdb8fc819d09dc4fbada9a')) paddle.fluid.layers.sequence_pool (ArgSpec(args=['input', 'pool_type', 'is_test', 'pad_value'], varargs=None, keywords=None, defaults=(False, 0.0)), ('document', '5a709f7ef3fdb8fc819d09dc4fbada9a'))
paddle.fluid.layers.sequence_softmax (ArgSpec(args=['input', 'use_cudnn', 'name'], varargs=None, keywords=None, defaults=(False, None)), ('document', 'eaa9d0bbd3d4e017c8bc4ecdac483711')) paddle.fluid.layers.sequence_softmax (ArgSpec(args=['input', 'use_cudnn', 'name'], varargs=None, keywords=None, defaults=(False, None)), ('document', 'eaa9d0bbd3d4e017c8bc4ecdac483711'))
paddle.fluid.layers.softmax (ArgSpec(args=['input', 'use_cudnn', 'name', 'axis'], varargs=None, keywords=None, defaults=(False, None, -1)), ('document', '7ccaea1b93fe4f7387a6036692986c6b')) paddle.fluid.layers.softmax (ArgSpec(args=['input', 'use_cudnn', 'name', 'axis'], varargs=None, keywords=None, defaults=(False, None, -1)), ('document', '7ccaea1b93fe4f7387a6036692986c6b'))
paddle.fluid.layers.pool2d (ArgSpec(args=['input', 'pool_size', 'pool_type', 'pool_stride', 'pool_padding', 'global_pooling', 'use_cudnn', 'ceil_mode', 'name', 'exclusive', 'data_format'], varargs=None, keywords=None, defaults=(-1, 'max', 1, 0, False, True, False, None, True, 'NCHW')), ('document', '630cae697d46b4b575b15d56cf8be25a')) paddle.fluid.layers.pool2d (ArgSpec(args=['input', 'pool_size', 'pool_type', 'pool_stride', 'pool_padding', 'global_pooling', 'use_cudnn', 'ceil_mode', 'name', 'exclusive', 'data_format'], varargs=None, keywords=None, defaults=(-1, 'max', 1, 0, False, True, False, None, True, 'NCHW')), ('document', 'daf9ae55b2d54bd5f35acb397fd1e1b5'))
paddle.fluid.layers.pool3d (ArgSpec(args=['input', 'pool_size', 'pool_type', 'pool_stride', 'pool_padding', 'global_pooling', 'use_cudnn', 'ceil_mode', 'name', 'exclusive', 'data_format'], varargs=None, keywords=None, defaults=(-1, 'max', 1, 0, False, True, False, None, True, 'NCDHW')), ('document', 'db0035a3132b1dfb12e53c57591fb9f6')) paddle.fluid.layers.pool3d (ArgSpec(args=['input', 'pool_size', 'pool_type', 'pool_stride', 'pool_padding', 'global_pooling', 'use_cudnn', 'ceil_mode', 'name', 'exclusive', 'data_format'], varargs=None, keywords=None, defaults=(-1, 'max', 1, 0, False, True, False, None, True, 'NCDHW')), ('document', 'df8edcb8dd020fdddf778c9f613dc650'))
paddle.fluid.layers.adaptive_pool2d (ArgSpec(args=['input', 'pool_size', 'pool_type', 'require_index', 'name'], varargs=None, keywords=None, defaults=('max', False, None)), ('document', '52343203de40afe29607397e13aaf0d2')) paddle.fluid.layers.adaptive_pool2d (ArgSpec(args=['input', 'pool_size', 'pool_type', 'require_index', 'name'], varargs=None, keywords=None, defaults=('max', False, None)), ('document', 'd873fdd73bcd74f9203d347cfb90de75'))
paddle.fluid.layers.adaptive_pool3d (ArgSpec(args=['input', 'pool_size', 'pool_type', 'require_index', 'name'], varargs=None, keywords=None, defaults=('max', False, None)), ('document', '55db6ae7275fb9678a6814aebab81a9c')) paddle.fluid.layers.adaptive_pool3d (ArgSpec(args=['input', 'pool_size', 'pool_type', 'require_index', 'name'], varargs=None, keywords=None, defaults=('max', False, None)), ('document', 'a94ed07bf4828e318aaaedb8b037579a'))
paddle.fluid.layers.batch_norm (ArgSpec(args=['input', 'act', 'is_test', 'momentum', 'epsilon', 'param_attr', 'bias_attr', 'data_layout', 'in_place', 'name', 'moving_mean_name', 'moving_variance_name', 'do_model_average_for_mean_and_var', 'fuse_with_relu', 'use_global_stats'], varargs=None, keywords=None, defaults=(None, False, 0.9, 1e-05, None, None, 'NCHW', False, None, None, None, False, False, False)), ('document', '1400433bae7876d0407ae205be39b7a1')) paddle.fluid.layers.batch_norm (ArgSpec(args=['input', 'act', 'is_test', 'momentum', 'epsilon', 'param_attr', 'bias_attr', 'data_layout', 'in_place', 'name', 'moving_mean_name', 'moving_variance_name', 'do_model_average_for_mean_and_var', 'fuse_with_relu', 'use_global_stats'], varargs=None, keywords=None, defaults=(None, False, 0.9, 1e-05, None, None, 'NCHW', False, None, None, None, False, False, False)), ('document', '1400433bae7876d0407ae205be39b7a1'))
paddle.fluid.layers.instance_norm (ArgSpec(args=['input', 'epsilon', 'param_attr', 'bias_attr', 'name'], varargs=None, keywords=None, defaults=(1e-05, None, None, None)), ('document', '23d6fba8ad8495f67a66d8878be5b0be')) paddle.fluid.layers.instance_norm (ArgSpec(args=['input', 'epsilon', 'param_attr', 'bias_attr', 'name'], varargs=None, keywords=None, defaults=(1e-05, None, None, None)), ('document', '23d6fba8ad8495f67a66d8878be5b0be'))
paddle.fluid.layers.data_norm (ArgSpec(args=['input', 'act', 'epsilon', 'param_attr', 'data_layout', 'in_place', 'name', 'moving_mean_name', 'moving_variance_name', 'do_model_average_for_mean_and_var'], varargs=None, keywords=None, defaults=(None, 1e-05, None, 'NCHW', False, None, None, None, False)), ('document', '5ba4cdb4ea5c03382da545335ffc05b7')) paddle.fluid.layers.data_norm (ArgSpec(args=['input', 'act', 'epsilon', 'param_attr', 'data_layout', 'in_place', 'name', 'moving_mean_name', 'moving_variance_name', 'do_model_average_for_mean_and_var'], varargs=None, keywords=None, defaults=(None, 1e-05, None, 'NCHW', False, None, None, None, False)), ('document', '5ba4cdb4ea5c03382da545335ffc05b7'))
...@@ -189,7 +189,7 @@ paddle.fluid.layers.row_conv (ArgSpec(args=['input', 'future_context_size', 'par ...@@ -189,7 +189,7 @@ paddle.fluid.layers.row_conv (ArgSpec(args=['input', 'future_context_size', 'par
paddle.fluid.layers.multiplex (ArgSpec(args=['inputs', 'index'], varargs=None, keywords=None, defaults=None), ('document', '2c4d1ae83da6ed35e3b36ba1b3b51d23')) paddle.fluid.layers.multiplex (ArgSpec(args=['inputs', 'index'], varargs=None, keywords=None, defaults=None), ('document', '2c4d1ae83da6ed35e3b36ba1b3b51d23'))
paddle.fluid.layers.layer_norm (ArgSpec(args=['input', 'scale', 'shift', 'begin_norm_axis', 'epsilon', 'param_attr', 'bias_attr', 'act', 'name'], varargs=None, keywords=None, defaults=(True, True, 1, 1e-05, None, None, None, None)), ('document', '79797f827d89ae72c77960e9696883a9')) paddle.fluid.layers.layer_norm (ArgSpec(args=['input', 'scale', 'shift', 'begin_norm_axis', 'epsilon', 'param_attr', 'bias_attr', 'act', 'name'], varargs=None, keywords=None, defaults=(True, True, 1, 1e-05, None, None, None, None)), ('document', '79797f827d89ae72c77960e9696883a9'))
paddle.fluid.layers.group_norm (ArgSpec(args=['input', 'groups', 'epsilon', 'param_attr', 'bias_attr', 'act', 'data_layout', 'name'], varargs=None, keywords=None, defaults=(1e-05, None, None, None, 'NCHW', None)), ('document', '87dd4b818f102bc1a780e1804c28bd38')) paddle.fluid.layers.group_norm (ArgSpec(args=['input', 'groups', 'epsilon', 'param_attr', 'bias_attr', 'act', 'data_layout', 'name'], varargs=None, keywords=None, defaults=(1e-05, None, None, None, 'NCHW', None)), ('document', '87dd4b818f102bc1a780e1804c28bd38'))
paddle.fluid.layers.spectral_norm (ArgSpec(args=['weight', 'dim', 'power_iters', 'eps', 'name'], varargs=None, keywords=None, defaults=(0, 1, 1e-12, None)), ('document', '9461e67095a6fc5d568fb2ce8fef66ff')) paddle.fluid.layers.spectral_norm (ArgSpec(args=['weight', 'dim', 'power_iters', 'eps', 'name'], varargs=None, keywords=None, defaults=(0, 1, 1e-12, None)), ('document', '7b3d14d6707d878923847ec617d7d521'))
paddle.fluid.layers.softmax_with_cross_entropy (ArgSpec(args=['logits', 'label', 'soft_label', 'ignore_index', 'numeric_stable_mode', 'return_softmax', 'axis'], varargs=None, keywords=None, defaults=(False, -100, True, False, -1)), ('document', '54e1675aa0364f4a78fa72804ec0f413')) paddle.fluid.layers.softmax_with_cross_entropy (ArgSpec(args=['logits', 'label', 'soft_label', 'ignore_index', 'numeric_stable_mode', 'return_softmax', 'axis'], varargs=None, keywords=None, defaults=(False, -100, True, False, -1)), ('document', '54e1675aa0364f4a78fa72804ec0f413'))
paddle.fluid.layers.smooth_l1 (ArgSpec(args=['x', 'y', 'inside_weight', 'outside_weight', 'sigma'], varargs=None, keywords=None, defaults=(None, None, None)), ('document', 'ecb75c1b00c4c76c98b482f633b7a10c')) paddle.fluid.layers.smooth_l1 (ArgSpec(args=['x', 'y', 'inside_weight', 'outside_weight', 'sigma'], varargs=None, keywords=None, defaults=(None, None, None)), ('document', 'ecb75c1b00c4c76c98b482f633b7a10c'))
paddle.fluid.layers.one_hot (ArgSpec(args=['input', 'depth', 'allow_out_of_range'], varargs=None, keywords=None, defaults=(False,)), ('document', 'cdf5dc2078f1e20dc61dd0bec7e28a29')) paddle.fluid.layers.one_hot (ArgSpec(args=['input', 'depth', 'allow_out_of_range'], varargs=None, keywords=None, defaults=(False,)), ('document', 'cdf5dc2078f1e20dc61dd0bec7e28a29'))
...@@ -282,7 +282,7 @@ paddle.fluid.layers.sequence_reverse (ArgSpec(args=['x', 'name'], varargs=None, ...@@ -282,7 +282,7 @@ paddle.fluid.layers.sequence_reverse (ArgSpec(args=['x', 'name'], varargs=None,
paddle.fluid.layers.affine_channel (ArgSpec(args=['x', 'scale', 'bias', 'data_layout', 'name', 'act'], varargs=None, keywords=None, defaults=(None, None, 'NCHW', None, None)), ('document', 'ecc4b1323028bde0518d666882d03515')) paddle.fluid.layers.affine_channel (ArgSpec(args=['x', 'scale', 'bias', 'data_layout', 'name', 'act'], varargs=None, keywords=None, defaults=(None, None, 'NCHW', None, None)), ('document', 'ecc4b1323028bde0518d666882d03515'))
paddle.fluid.layers.similarity_focus (ArgSpec(args=['input', 'axis', 'indexes', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '18ec2e3afeb90e70c8b73d2b71c40fdb')) paddle.fluid.layers.similarity_focus (ArgSpec(args=['input', 'axis', 'indexes', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '18ec2e3afeb90e70c8b73d2b71c40fdb'))
paddle.fluid.layers.hash (ArgSpec(args=['input', 'hash_size', 'num_hash', 'name'], varargs=None, keywords=None, defaults=(1, None)), ('document', 'a0b73c21be618cec0281e7903039e5e3')) paddle.fluid.layers.hash (ArgSpec(args=['input', 'hash_size', 'num_hash', 'name'], varargs=None, keywords=None, defaults=(1, None)), ('document', 'a0b73c21be618cec0281e7903039e5e3'))
paddle.fluid.layers.grid_sampler (ArgSpec(args=['x', 'grid', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '5d16663e096d7f04954c70ce1cc5e195')) paddle.fluid.layers.grid_sampler (ArgSpec(args=['x', 'grid', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '90c74742f48c70b103f1fbb9eb129066'))
paddle.fluid.layers.log_loss (ArgSpec(args=['input', 'label', 'epsilon', 'name'], varargs=None, keywords=None, defaults=(0.0001, None)), ('document', 'e3993a477c94729526040ff65d95728e')) paddle.fluid.layers.log_loss (ArgSpec(args=['input', 'label', 'epsilon', 'name'], varargs=None, keywords=None, defaults=(0.0001, None)), ('document', 'e3993a477c94729526040ff65d95728e'))
paddle.fluid.layers.add_position_encoding (ArgSpec(args=['input', 'alpha', 'beta', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', 'e399f9436fed5f7ff480d8532e42c937')) paddle.fluid.layers.add_position_encoding (ArgSpec(args=['input', 'alpha', 'beta', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', 'e399f9436fed5f7ff480d8532e42c937'))
paddle.fluid.layers.bilinear_tensor_product (ArgSpec(args=['x', 'y', 'size', 'act', 'name', 'param_attr', 'bias_attr'], varargs=None, keywords=None, defaults=(None, None, None, None)), ('document', '45fc3652a8e1aeffbe4eba371c54f756')) paddle.fluid.layers.bilinear_tensor_product (ArgSpec(args=['x', 'y', 'size', 'act', 'name', 'param_attr', 'bias_attr'], varargs=None, keywords=None, defaults=(None, None, None, None)), ('document', '45fc3652a8e1aeffbe4eba371c54f756'))
...@@ -290,13 +290,13 @@ paddle.fluid.layers.merge_selected_rows (ArgSpec(args=['x', 'name'], varargs=Non ...@@ -290,13 +290,13 @@ paddle.fluid.layers.merge_selected_rows (ArgSpec(args=['x', 'name'], varargs=Non
paddle.fluid.layers.get_tensor_from_selected_rows (ArgSpec(args=['x', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '2c568321feb4d16c41a83df43f95089d')) paddle.fluid.layers.get_tensor_from_selected_rows (ArgSpec(args=['x', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '2c568321feb4d16c41a83df43f95089d'))
paddle.fluid.layers.lstm (ArgSpec(args=['input', 'init_h', 'init_c', 'max_len', 'hidden_size', 'num_layers', 'dropout_prob', 'is_bidirec', 'is_test', 'name', 'default_initializer', 'seed'], varargs=None, keywords=None, defaults=(0.0, False, False, None, None, -1)), ('document', 'baa7327ed89df6b7bdd32f9ffdb62f63')) paddle.fluid.layers.lstm (ArgSpec(args=['input', 'init_h', 'init_c', 'max_len', 'hidden_size', 'num_layers', 'dropout_prob', 'is_bidirec', 'is_test', 'name', 'default_initializer', 'seed'], varargs=None, keywords=None, defaults=(0.0, False, False, None, None, -1)), ('document', 'baa7327ed89df6b7bdd32f9ffdb62f63'))
paddle.fluid.layers.shuffle_channel (ArgSpec(args=['x', 'group', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '276a1213dd431228cefa33c3146df34a')) paddle.fluid.layers.shuffle_channel (ArgSpec(args=['x', 'group', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '276a1213dd431228cefa33c3146df34a'))
paddle.fluid.layers.temporal_shift (ArgSpec(args=['x', 'seg_num', 'shift_ratio', 'name'], varargs=None, keywords=None, defaults=(0.25, None)), ('document', '13b1cdcb01f5ffdc26591ff9a2ec4669')) paddle.fluid.layers.temporal_shift (ArgSpec(args=['x', 'seg_num', 'shift_ratio', 'name'], varargs=None, keywords=None, defaults=(0.25, None)), ('document', 'd5945431cdcae3cda21914db5bbf383e'))
paddle.fluid.layers.py_func (ArgSpec(args=['func', 'x', 'out', 'backward_func', 'skip_vars_in_backward_input'], varargs=None, keywords=None, defaults=(None, None)), ('document', '8404e472ac12b4a30a505d3d3a3e5fdb')) paddle.fluid.layers.py_func (ArgSpec(args=['func', 'x', 'out', 'backward_func', 'skip_vars_in_backward_input'], varargs=None, keywords=None, defaults=(None, None)), ('document', '8404e472ac12b4a30a505d3d3a3e5fdb'))
paddle.fluid.layers.psroi_pool (ArgSpec(args=['input', 'rois', 'output_channels', 'spatial_scale', 'pooled_height', 'pooled_width', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '42d5155374f69786300d90d751956998')) paddle.fluid.layers.psroi_pool (ArgSpec(args=['input', 'rois', 'output_channels', 'spatial_scale', 'pooled_height', 'pooled_width', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '42d5155374f69786300d90d751956998'))
paddle.fluid.layers.prroi_pool (ArgSpec(args=['input', 'rois', 'output_channels', 'spatial_scale', 'pooled_height', 'pooled_width', 'name'], varargs=None, keywords=None, defaults=(1.0, 1, 1, None)), ('document', '454c7ea8c73313dd41513929d7526303')) paddle.fluid.layers.prroi_pool (ArgSpec(args=['input', 'rois', 'output_channels', 'spatial_scale', 'pooled_height', 'pooled_width', 'name'], varargs=None, keywords=None, defaults=(1.0, 1, 1, None)), ('document', '454c7ea8c73313dd41513929d7526303'))
paddle.fluid.layers.teacher_student_sigmoid_loss (ArgSpec(args=['input', 'label', 'soft_max_up_bound', 'soft_max_lower_bound'], varargs=None, keywords=None, defaults=(15.0, -15.0)), ('document', 'b0e07aa41caae04b07a8e8217cc96020')) paddle.fluid.layers.teacher_student_sigmoid_loss (ArgSpec(args=['input', 'label', 'soft_max_up_bound', 'soft_max_lower_bound'], varargs=None, keywords=None, defaults=(15.0, -15.0)), ('document', 'b0e07aa41caae04b07a8e8217cc96020'))
paddle.fluid.layers.huber_loss (ArgSpec(args=['input', 'label', 'delta'], varargs=None, keywords=None, defaults=None), ('document', '9d93ee81f7a3e526d68bb280bc695d6c')) paddle.fluid.layers.huber_loss (ArgSpec(args=['input', 'label', 'delta'], varargs=None, keywords=None, defaults=None), ('document', '9d93ee81f7a3e526d68bb280bc695d6c'))
paddle.fluid.layers.kldiv_loss (ArgSpec(args=['x', 'target', 'reduction', 'name'], varargs=None, keywords=None, defaults=('mean', None)), ('document', '18bc95c62d3300456c3c7da5278b47bb')) paddle.fluid.layers.kldiv_loss (ArgSpec(args=['x', 'target', 'reduction', 'name'], varargs=None, keywords=None, defaults=('mean', None)), ('document', '45f3ebbcb766fca84cb2fe6307086573'))
paddle.fluid.layers.npair_loss (ArgSpec(args=['anchor', 'positive', 'labels', 'l2_reg'], varargs=None, keywords=None, defaults=(0.002,)), ('document', '3828c4bd81c25af0ab955f52d453c587')) paddle.fluid.layers.npair_loss (ArgSpec(args=['anchor', 'positive', 'labels', 'l2_reg'], varargs=None, keywords=None, defaults=(0.002,)), ('document', '3828c4bd81c25af0ab955f52d453c587'))
paddle.fluid.layers.pixel_shuffle (ArgSpec(args=['x', 'upscale_factor'], varargs=None, keywords=None, defaults=None), ('document', '7e5cac851fd9bad344230e1044b6a565')) paddle.fluid.layers.pixel_shuffle (ArgSpec(args=['x', 'upscale_factor'], varargs=None, keywords=None, defaults=None), ('document', '7e5cac851fd9bad344230e1044b6a565'))
paddle.fluid.layers.fsp_matrix (ArgSpec(args=['x', 'y'], varargs=None, keywords=None, defaults=None), ('document', '3a4eb7cce366f5fd8bc38b42b6af5ba1')) paddle.fluid.layers.fsp_matrix (ArgSpec(args=['x', 'y'], varargs=None, keywords=None, defaults=None), ('document', '3a4eb7cce366f5fd8bc38b42b6af5ba1'))
...@@ -438,9 +438,9 @@ paddle.fluid.layers.box_decoder_and_assign (ArgSpec(args=['prior_box', 'prior_bo ...@@ -438,9 +438,9 @@ paddle.fluid.layers.box_decoder_and_assign (ArgSpec(args=['prior_box', 'prior_bo
paddle.fluid.layers.collect_fpn_proposals (ArgSpec(args=['multi_rois', 'multi_scores', 'min_level', 'max_level', 'post_nms_top_n', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', 'ff4a651d65a9a9f9da71349ba6a2dc1f')) paddle.fluid.layers.collect_fpn_proposals (ArgSpec(args=['multi_rois', 'multi_scores', 'min_level', 'max_level', 'post_nms_top_n', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', 'ff4a651d65a9a9f9da71349ba6a2dc1f'))
paddle.fluid.layers.accuracy (ArgSpec(args=['input', 'label', 'k', 'correct', 'total'], varargs=None, keywords=None, defaults=(1, None, None)), ('document', 'b691b7be425e281bd36897b514b2b064')) paddle.fluid.layers.accuracy (ArgSpec(args=['input', 'label', 'k', 'correct', 'total'], varargs=None, keywords=None, defaults=(1, None, None)), ('document', 'b691b7be425e281bd36897b514b2b064'))
paddle.fluid.layers.auc (ArgSpec(args=['input', 'label', 'curve', 'num_thresholds', 'topk', 'slide_steps'], varargs=None, keywords=None, defaults=('ROC', 4095, 1, 1)), ('document', 'c36ac7125da977c2bd1b192bee301f75')) paddle.fluid.layers.auc (ArgSpec(args=['input', 'label', 'curve', 'num_thresholds', 'topk', 'slide_steps'], varargs=None, keywords=None, defaults=('ROC', 4095, 1, 1)), ('document', 'c36ac7125da977c2bd1b192bee301f75'))
paddle.fluid.layers.exponential_decay (ArgSpec(args=['learning_rate', 'decay_steps', 'decay_rate', 'staircase'], varargs=None, keywords=None, defaults=(False,)), ('document', 'eaf430c5a0380fb11bfe9a8922cd6295')) paddle.fluid.layers.exponential_decay (ArgSpec(args=['learning_rate', 'decay_steps', 'decay_rate', 'staircase'], varargs=None, keywords=None, defaults=(False,)), ('document', '48c7b2563a6fc11f23030cde8d7a5c80'))
paddle.fluid.layers.natural_exp_decay (ArgSpec(args=['learning_rate', 'decay_steps', 'decay_rate', 'staircase'], varargs=None, keywords=None, defaults=(False,)), ('document', 'aa3146f64d5d508e4e50687603aa7b15')) paddle.fluid.layers.natural_exp_decay (ArgSpec(args=['learning_rate', 'decay_steps', 'decay_rate', 'staircase'], varargs=None, keywords=None, defaults=(False,)), ('document', '63edb712ab4ca837049f24a9421dfe30'))
paddle.fluid.layers.inverse_time_decay (ArgSpec(args=['learning_rate', 'decay_steps', 'decay_rate', 'staircase'], varargs=None, keywords=None, defaults=(False,)), ('document', 'ea37a3a8a0b3ce2254e7bc49a0951dbe')) paddle.fluid.layers.inverse_time_decay (ArgSpec(args=['learning_rate', 'decay_steps', 'decay_rate', 'staircase'], varargs=None, keywords=None, defaults=(False,)), ('document', 'ff553aa6546eeb1bc692fadb3df78370'))
paddle.fluid.layers.polynomial_decay (ArgSpec(args=['learning_rate', 'decay_steps', 'end_learning_rate', 'power', 'cycle'], varargs=None, keywords=None, defaults=(0.0001, 1.0, False)), ('document', 'a343254c36c2e89512cd8cd8a1960ead')) paddle.fluid.layers.polynomial_decay (ArgSpec(args=['learning_rate', 'decay_steps', 'end_learning_rate', 'power', 'cycle'], varargs=None, keywords=None, defaults=(0.0001, 1.0, False)), ('document', 'a343254c36c2e89512cd8cd8a1960ead'))
paddle.fluid.layers.piecewise_decay (ArgSpec(args=['boundaries', 'values'], varargs=None, keywords=None, defaults=None), ('document', 'd9f654117542c6b702963dda107a247f')) paddle.fluid.layers.piecewise_decay (ArgSpec(args=['boundaries', 'values'], varargs=None, keywords=None, defaults=None), ('document', 'd9f654117542c6b702963dda107a247f'))
paddle.fluid.layers.noam_decay (ArgSpec(args=['d_model', 'warmup_steps'], varargs=None, keywords=None, defaults=None), ('document', 'fd57228fb76195e66bbcc8d8e42c494d')) paddle.fluid.layers.noam_decay (ArgSpec(args=['d_model', 'warmup_steps'], varargs=None, keywords=None, defaults=None), ('document', 'fd57228fb76195e66bbcc8d8e42c494d'))
......
paddle/fluid/operators/kldiv_loss_op.cc
浏览文件 @ dfde0eaa
...@@ -69,10 +69,12 @@ class KLDivLossOpMaker : public framework::OpProtoAndCheckerMaker { ...@@ -69,10 +69,12 @@ class KLDivLossOpMaker : public framework::OpProtoAndCheckerMaker {
AddInput("X", AddInput("X",
"The input tensor of KL divergence loss operator. " "The input tensor of KL divergence loss operator. "
"This is a tensor with shape of [N, *], where N is the " "This is a tensor with shape of [N, *], where N is the "
"batch size, * means any number of additional dimensions."); "batch size, * means any number of additional dimensions. "
"The data type is float32 or flaot64");
AddInput("Target", AddInput("Target",
"The tensor of KL divergence loss operator. " "The tensor of KL divergence loss operator. "
"This is a tensor with shape of Input(X)."); "This is a tensor with shape of Input(X). "
"The data type is same as Input(X)");
AddOutput( AddOutput(
"Loss", "Loss",
"The output KL divergence loss tensor. if Attr(reduction) is " "The output KL divergence loss tensor. if Attr(reduction) is "
...@@ -90,7 +92,8 @@ class KLDivLossOpMaker : public framework::OpProtoAndCheckerMaker { ...@@ -90,7 +92,8 @@ class KLDivLossOpMaker : public framework::OpProtoAndCheckerMaker {
AddComment(R"DOC( AddComment(R"DOC(
This operator calculates the Kullback-Leibler divergence loss This operator calculates the Kullback-Leibler divergence loss
between Input(X) and Input(Target). between Input(X) and Input(Target). Notes that Input(X) is the
log-probability and Input(Target) is the probability.
KL divergence loss is calculated as follows: KL divergence loss is calculated as follows:
......
paddle/fluid/operators/pool_op.cc
浏览文件 @ dfde0eaa
...@@ -200,8 +200,9 @@ void Pool2dOpMaker::Make() { ...@@ -200,8 +200,9 @@ void Pool2dOpMaker::Make() {
// TypedAttrChecker don't support vector type.) // TypedAttrChecker don't support vector type.)
AddAttr<bool>( AddAttr<bool>(
"global_pooling", "global_pooling",
"(bool, default false) Whether to use the global pooling. " "(bool) Whether to use the global pooling. "
"If global_pooling = true, kernel size and paddings will be ignored.") "If global_pooling = true, kernel size and paddings will be ignored. "
"Default False.")
.SetDefault(false); .SetDefault(false);
AddAttr<std::vector<int>>("strides", AddAttr<std::vector<int>>("strides",
"(vector<int>, default {1, 1}), strides(height, " "(vector<int>, default {1, 1}), strides(height, "
...@@ -217,36 +218,38 @@ void Pool2dOpMaker::Make() { ...@@ -217,36 +218,38 @@ void Pool2dOpMaker::Make() {
.SetDefault({0, 0}); .SetDefault({0, 0});
AddAttr<bool>( AddAttr<bool>(
"exclusive", "exclusive",
"(bool, default True) When true, will exclude the zero-padding in the " "(bool) When true, will exclude the zero-padding in the "
"averaging calculating, otherwise, include the zero-padding. Note, it " "averaging calculating, otherwise, include the zero-padding. Note, it "
"is only used when pooling_type is avg. The default is True.") "is only used when pooling_type is avg. The default is True. "
"Default True.")
.SetDefault(true); .SetDefault(true);
AddAttr<bool>( AddAttr<bool>(
"adaptive", "adaptive",
"(bool, default False) When true, will perform adaptive pooling instead, " "(bool) When true, will perform adaptive pooling instead, "
"output shape in H and W dimensions will be same as ksize, input data " "output shape in H and W dimensions will be same as ksize, input data "
"will be divided into grids specify by ksize averagely and perform " "will be divided into grids specify by ksize averagely and perform "
"pooling in each grid area to get output pooling value.") "pooling in each grid area to get output pooling value. "
"Default False.")
.SetDefault(false); .SetDefault(false);
AddAttr<bool>( AddAttr<bool>(
"use_cudnn", "use_cudnn",
"(bool, default false) Only used in cudnn kernel, need install cudnn.") "(bool) Only used in cudnn kernel, need install cudnn. Default False")
.SetDefault(false); .SetDefault(false);
AddAttr<bool>( AddAttr<bool>(
"ceil_mode", "ceil_mode",
"(bool, default false) Whether to use the ceil function to calculate " "(bool) Whether to use the ceil function to calculate "
"output height and width. False is the default. If it is set to False, " "output height and width. False is the default. If it is set to False, "
"the floor function will be used.") "the floor function will be used. Default False")
.SetDefault(false); .SetDefault(false);
AddAttr<bool>("use_mkldnn", AddAttr<bool>("use_mkldnn",
"(bool, default false) Only used in mkldnn kernel.") "(bool) Only used in mkldnn kernel. Default False")
.SetDefault(false); .SetDefault(false);
AddAttr<bool>("use_quantizer", AddAttr<bool>("use_quantizer",
"(bool, default false) " "(bool) "
"Set to true for operators that should be quantized and use " "Set to true for operators that should be quantized and use "
"int8 kernel. " "int8 kernel. "
"Only used on CPU.") "Only used on CPU. Default False")
.SetDefault(false); .SetDefault(false);
AddAttr<std::string>( AddAttr<std::string>(
"data_format", "data_format",
...@@ -269,11 +272,11 @@ void Pool2dOpMaker::Make() { ...@@ -269,11 +272,11 @@ void Pool2dOpMaker::Make() {
// TODO(dzhwinter): need to registered layout transform function // TODO(dzhwinter): need to registered layout transform function
AddComment(R"DOC( AddComment(R"DOC(
The pooling2d operation calculates the output based on This operation calculates the pooling output based on
the input, pooling_type and ksize, strides, paddings parameters. the input, pooling_type and pool_size, pool_stride, pool_padding parameters.
Input(X) and output(Out) are in NCHW or NHWC format, where N is batch size, C is the Input(X) and Output(Out) are in NCHW or NHWC format, where N is batch size, C is the
number of channels, H is the height of the feature, and W is the width of the feature. number of channels, H is the height of the feature, and W is the width of the feature.
Parameters(ksize, strides, paddings) are two elements. Parameters(pool_size, pool_stride, pool_padding) hold two integer elements.
These two elements represent height and width, respectively. These two elements represent height and width, respectively.
The input(X) size and output(Out) size may be different. The input(X) size and output(Out) size may be different.
...@@ -393,8 +396,9 @@ void Pool3dOpMaker::Make() { ...@@ -393,8 +396,9 @@ void Pool3dOpMaker::Make() {
// TypedAttrChecker don't support vector type.) // TypedAttrChecker don't support vector type.)
AddAttr<bool>( AddAttr<bool>(
"global_pooling", "global_pooling",
"(bool, default false) Whether to use the global pooling. " "(bool) Whether to use the global pooling. "
"If global_pooling = true, kernel size and paddings will be ignored.") "If global_pooling = true, kernel size and paddings will be ignored. "
"Default False")
.SetDefault(false); .SetDefault(false);
AddAttr<std::vector<int>>( AddAttr<std::vector<int>>(
"strides", "strides",
...@@ -413,30 +417,32 @@ void Pool3dOpMaker::Make() { ...@@ -413,30 +417,32 @@ void Pool3dOpMaker::Make() {
// TypedAttrChecker don't support vector type.) // TypedAttrChecker don't support vector type.)
AddAttr<bool>( AddAttr<bool>(
"exclusive", "exclusive",
"(bool, default True) When true, will exclude the zero-padding in the " "(bool) When true, will exclude the zero-padding in the "
"averaging calculating, otherwise, include the zero-padding. Note, it " "averaging calculating, otherwise, include the zero-padding. Note, it "
"is only used when pooling_type is avg. The default is True.") "is only used when pooling_type is avg. The default is True. "
"Default True")
.SetDefault(true); .SetDefault(true);
AddAttr<bool>( AddAttr<bool>(
"adaptive", "adaptive",
"(bool, default False) When true, will perform adaptive pooling instead, " "(bool) When true, will perform adaptive pooling instead, "
"output shape in H and W dimensions will be same as ksize, input data " "output shape in H and W dimensions will be same as ksize, input data "
"will be divided into grids specify by ksize averagely and perform " "will be divided into grids specify by ksize averagely and perform "
"pooling in each grid area to get output pooling value.") "pooling in each grid area to get output pooling value. "
"Default False")
.SetDefault(false); .SetDefault(false);
AddAttr<bool>( AddAttr<bool>(
"use_cudnn", "use_cudnn",
"(bool, default false) Only used in cudnn kernel, need install cudnn.") "(bool) Only used in cudnn kernel, need install cudnn. Default False")
.SetDefault(false); .SetDefault(false);
AddAttr<bool>( AddAttr<bool>(
"ceil_mode", "ceil_mode",
"(bool, default false) Whether to use the ceil function to calculate " "(bool) Whether to use the ceil function to calculate "
"output height and width. False is the default. If it is set to False, " "output height and width. False is the default. If it is set to False, "
"the floor function will be used.") "the floor function will be used. Default False")
.SetDefault(false); .SetDefault(false);
AddAttr<bool>("use_mkldnn", AddAttr<bool>("use_mkldnn",
"(bool, default false) Only used in mkldnn kernel") "(bool) Only used in mkldnn kernel. Default False")
.SetDefault(false); .SetDefault(false);
AddAttr<std::string>( AddAttr<std::string>(
"data_format", "data_format",
...@@ -454,14 +460,12 @@ void Pool3dOpMaker::Make() { ...@@ -454,14 +460,12 @@ void Pool3dOpMaker::Make() {
// TODO(dzhwinter): need to registered layout transform function // TODO(dzhwinter): need to registered layout transform function
AddComment(R"DOC( AddComment(R"DOC(
Pool3d Operator. This operation calculates the output based on
the input, pooling_type, pool_size, pool_stride, and pool_padding parameters.
The pooling3d operation calculates the output based on
the input, pooling_type, ksize, strides, and paddings parameters.
Input(X) and output(Out) are in NCDHW or NDHWC format, where N is batch Input(X) and output(Out) are in NCDHW or NDHWC format, where N is batch
size, C is the number of channels, and D, H and W are the depth, height and size, C is the number of channels, and D, H and W are the depth, height and
width of the feature, respectively. Parameters(ksize, strides, paddings) width of the feature, respectively. Parameters(pool_size, pool_stride, pool_padding)
are three elements. These three elements represent depth, height and hold three integer elements. These three elements represent depth, height and
width, respectively. The input(X) size and output(Out) size may be different. width, respectively. The input(X) size and output(Out) size may be different.
Example: Example:
......
paddle/fluid/operators/spectral_norm_op.cc
浏览文件 @ dfde0eaa
...@@ -88,7 +88,8 @@ class SpectralNormOpMaker : public framework::OpProtoAndCheckerMaker { ...@@ -88,7 +88,8 @@ class SpectralNormOpMaker : public framework::OpProtoAndCheckerMaker {
AddInput("Weight", AddInput("Weight",
"The input weight tensor of spectral_norm operator, " "The input weight tensor of spectral_norm operator, "
"This can be a 2-D, 3-D, 4-D, 5-D tensor which is the " "This can be a 2-D, 3-D, 4-D, 5-D tensor which is the "
"weights of fc, conv1d, conv2d, conv3d layer."); "weights of fc, conv1d, conv2d, conv3d layer. "
"The data type is float32 or float64.");
AddInput("U", AddInput("U",
"The weight_u tensor of spectral_norm operator, " "The weight_u tensor of spectral_norm operator, "
"This can be a 1-D tensor in shape [H, 1]," "This can be a 1-D tensor in shape [H, 1],"
...@@ -123,7 +124,9 @@ class SpectralNormOpMaker : public framework::OpProtoAndCheckerMaker { ...@@ -123,7 +124,9 @@ class SpectralNormOpMaker : public framework::OpProtoAndCheckerMaker {
.SetDefault(1); .SetDefault(1);
AddAttr<float>("eps", AddAttr<float>("eps",
"epsilon for numerical stability in " "epsilon for numerical stability in "
"calculating norms") "calculating norms, it will be added to "
"the denominator to aviod divide zero. "
"Default 1e-12.")
.SetDefault(1e-12); .SetDefault(1e-12);
AddComment(R"DOC( AddComment(R"DOC(
......
paddle/fluid/operators/temporal_shift_op.cc
浏览文件 @ dfde0eaa
...@@ -69,7 +69,8 @@ class TemporalShiftOpMaker : public framework::OpProtoAndCheckerMaker { ...@@ -69,7 +69,8 @@ class TemporalShiftOpMaker : public framework::OpProtoAndCheckerMaker {
"This is a 4-D tensor with shape of [N*T, C, H, W]. " "This is a 4-D tensor with shape of [N*T, C, H, W]. "
"While N is the batch size, T is the temporal segment " "While N is the batch size, T is the temporal segment "
"number, C is the channel number, H is the height of " "number, C is the channel number, H is the height of "
"features and W is the width of features."); "features and W is the width of features. "
"The data type is float32 and float64");
AddOutput("Out", AddOutput("Out",
"The output tensor of temporal shift operator. " "The output tensor of temporal shift operator. "
"This is a 4-D tensor in the same shape with Input(X)."); "This is a 4-D tensor in the same shape with Input(X).");
...@@ -82,7 +83,8 @@ class TemporalShiftOpMaker : public framework::OpProtoAndCheckerMaker { ...@@ -82,7 +83,8 @@ class TemporalShiftOpMaker : public framework::OpProtoAndCheckerMaker {
"The shift ratio of the channels, the first :attr:`shift_ratio` part " "The shift ratio of the channels, the first :attr:`shift_ratio` part "
"of channels will be shifted by -1 along the temporal dimension, " "of channels will be shifted by -1 along the temporal dimension, "
"and the second :attr:`shift_ratio` part of channels will be shifted " "and the second :attr:`shift_ratio` part of channels will be shifted "
"by 1 along the temporal dimension. Default 0.25.") "by 1 along the temporal dimension. :attr:`shift_ratio` should be in "
"range [0, 0.5]. Default 0.25.")
.SetDefault(0.25); .SetDefault(0.25);
AddComment(R"DOC( AddComment(R"DOC(
......
python/paddle/fluid/layers/learning_rate_scheduler.py
浏览文件 @ dfde0eaa
...@@ -109,20 +109,25 @@ def exponential_decay(learning_rate, decay_steps, decay_rate, staircase=False): ...@@ -109,20 +109,25 @@ def exponential_decay(learning_rate, decay_steps, decay_rate, staircase=False):
training progresses. By using this function, the learning rate will be decayed by training progresses. By using this function, the learning rate will be decayed by
'decay_rate' every 'decay_steps' steps. 'decay_rate' every 'decay_steps' steps.
Decayed learning rate calcualtes as follows:
>>> if staircase == True: >>> if staircase == True:
>>> decayed_learning_rate = learning_rate * decay_rate ^ floor(global_step / decay_steps) >>> decayed_learning_rate = learning_rate * decay_rate ^ floor(global_step / decay_steps)
>>> else: >>> else:
>>> decayed_learning_rate = learning_rate * decay_rate ^ (global_step / decay_steps) >>> decayed_learning_rate = learning_rate * decay_rate ^ (global_step / decay_steps)
Args: Args:
learning_rate(Variable|float): The initial learning rate. learning_rate(Variable|float): The initial learning rate. It should be a Variable
decay_steps(int): See the decay computation above. or a float
decay_rate(float): The decay rate. See the decay computation above. decay_steps(int): The learning rate decay steps. See the decay computation above.
staircase(Boolean): If True, decay the learning rate at discrete intervals. decay_rate(float): The learning rate decay rate. See the decay computation above.
Default: False staircase(bool): If True, decay the learning rate at discrete intervals, which
means the learning rate will be decayed by `decay_rate` every
`decay_steps`. If False, learning rate will be decayed continuously
and following the formula above. Default: False
Returns: Returns:
Variable: The decayed learning rate Variable: The decayed learning rate. The data type is float32.
Examples: Examples:
.. code-block:: python .. code-block:: python
...@@ -156,20 +161,29 @@ def exponential_decay(learning_rate, decay_steps, decay_rate, staircase=False): ...@@ -156,20 +161,29 @@ def exponential_decay(learning_rate, decay_steps, decay_rate, staircase=False):
def natural_exp_decay(learning_rate, decay_steps, decay_rate, staircase=False): def natural_exp_decay(learning_rate, decay_steps, decay_rate, staircase=False):
"""Applies natural exponential decay to the initial learning rate. """Applies natural exponential decay to the initial learning rate.
When training a model, it is often recommended to lower the learning rate as the
training progresses. By using this function, the learning rate will be decayed by
natural exponential power 'decay_rate' every 'decay_steps' steps.
Decayed learning rate calcualtes as follows:
>>> if not staircase: >>> if not staircase:
>>> decayed_learning_rate = learning_rate * exp(- decay_rate * (global_step / decay_steps)) >>> decayed_learning_rate = learning_rate * exp(- decay_rate * (global_step / decay_steps))
>>> else: >>> else:
>>> decayed_learning_rate = learning_rate * exp(- decay_rate * floor(global_step / decay_steps)) >>> decayed_learning_rate = learning_rate * exp(- decay_rate * floor(global_step / decay_steps))
Args: Args:
learning_rate: A scalar float32 value or a Variable. This learning_rate(Variable|float): The initial learning rate. It should be a Variable
will be the initial learning rate during training or a float
decay_steps: A Python `int32` number. decay_steps(int): The learning rate decay steps. See the decay computation above.
decay_rate: A Python `float` number. decay_rate(float): The learning rate decay rate. See the decay computation above.
staircase: Boolean. If set true, decay the learning rate every decay_steps. staircase(bool): If True, decay the learning rate at discrete intervals, which
means the learning rate will be decayed by natual exponential power
`decay_rate` every `decay_steps`. If False, learning rate will be
decayed continuously and following the formula above. Default: False
Returns: Returns:
The decayed learning rate The decayed learning rate. The data type is float32.
Examples: Examples:
.. code-block:: python .. code-block:: python
...@@ -208,20 +222,25 @@ def inverse_time_decay(learning_rate, decay_steps, decay_rate, staircase=False): ...@@ -208,20 +222,25 @@ def inverse_time_decay(learning_rate, decay_steps, decay_rate, staircase=False):
training progresses. By using this function, an inverse decay function will be training progresses. By using this function, an inverse decay function will be
applied to the initial learning rate. applied to the initial learning rate.
Decayed learning rate calcualtes as follows:
>>> if staircase == True: >>> if staircase == True:
>>> decayed_learning_rate = learning_rate / (1 + decay_rate * floor(global_step / decay_step)) >>> decayed_learning_rate = learning_rate / (1 + decay_rate * floor(global_step / decay_step))
>>> else: >>> else:
>>> decayed_learning_rate = learning_rate / (1 + decay_rate * global_step / decay_step) >>> decayed_learning_rate = learning_rate / (1 + decay_rate * global_step / decay_step)
Args: Args:
learning_rate(Variable|float): The initial learning rate. learning_rate(Variable|float): The initial learning rate. It should be a Variable
decay_steps(int): See the decay computation above. or a float
decay_rate(float): The decay rate. See the decay computation above. decay_steps(int): The learning rate decay steps. See the decay computation above.
staircase(Boolean): If True, decay the learning rate at discrete intervals. decay_rate(float): The learning rate decay rate. See the decay computation above.
Default: False staircase(bool): If True, decay the learning rate at discrete intervals, which
means the learning rate will be decayed by `decay_rate` times
every `decay_steps`. If False, learning rate will be decayed
continuously and following the formula above. Default: False
Returns: Returns:
Variable: The decayed learning rate Variable: The decayed learning rate. The data type is float32.
Examples: Examples:
.. code-block:: python .. code-block:: python
...@@ -229,7 +248,7 @@ def inverse_time_decay(learning_rate, decay_steps, decay_rate, staircase=False): ...@@ -229,7 +248,7 @@ def inverse_time_decay(learning_rate, decay_steps, decay_rate, staircase=False):
import paddle.fluid as fluid import paddle.fluid as fluid
base_lr = 0.1 base_lr = 0.1
sgd_optimizer = fluid.optimizer.SGD( sgd_optimizer = fluid.optimizer.SGD(
learning_rate=fluid.layers.natural_exp_decay( learning_rate=fluid.layers.inverse_time_decay(
learning_rate=base_lr, learning_rate=base_lr,
decay_steps=10000, decay_steps=10000,
decay_rate=0.5, decay_rate=0.5,
......
python/paddle/fluid/layers/nn.py
浏览文件 @ dfde0eaa
...@@ -3272,10 +3272,11 @@ def pool2d(input, ...@@ -3272,10 +3272,11 @@ def pool2d(input,
${comment} ${comment}
Args: Args:
input (Variable): The input tensor of pooling operator. The format of input (Variable): The input tensor of pooling operator which is a 4-D tensor with
input tensor is `"NCHW"` or `"NHWC"`, where `N` is batch size, `C` is shape [N, C, H, W]. The format of input tensor is `"NCHW"` or
the number of channels, `H` is the height of the `"NHWC"`, where `N` is batch size, `C` is the number of channels,
feature, and `W` is the width of the feature. `H` is the height of the feature, and `W` is the width of the
feature. The data type if float32 or float64.
pool_size (int|list|tuple): The pool kernel size. If pool kernel size is a tuple or list, pool_size (int|list|tuple): The pool kernel size. If pool kernel size is a tuple or list,
it must contain two integers, (pool_size_Height, pool_size_Width). it must contain two integers, (pool_size_Height, pool_size_Width).
Otherwise, the pool kernel size will be a square of an int. Otherwise, the pool kernel size will be a square of an int.
...@@ -3294,8 +3295,9 @@ def pool2d(input, ...@@ -3294,8 +3295,9 @@ def pool2d(input,
global_pooling (bool): ${global_pooling_comment} global_pooling (bool): ${global_pooling_comment}
use_cudnn (bool): ${use_cudnn_comment} use_cudnn (bool): ${use_cudnn_comment}
ceil_mode (bool): ${ceil_mode_comment} ceil_mode (bool): ${ceil_mode_comment}
name (str|None): A name for this layer(optional). If set None, the name(str, optional): For detailed information, please refer
layer will be named automatically. to :ref:`api_guide_Name`. Usually name is no need to set and
None by default.
exclusive (bool): Whether to exclude padding points in average pooling exclusive (bool): Whether to exclude padding points in average pooling
mode, default is `true`. mode, default is `true`.
data_format (string): The data format of the input and output data. An optional string from: `"NCHW"`, `"NDHW"`. data_format (string): The data format of the input and output data. An optional string from: `"NCHW"`, `"NDHW"`.
...@@ -3303,7 +3305,7 @@ def pool2d(input, ...@@ -3303,7 +3305,7 @@ def pool2d(input,
`[batch_size, input_channels, input_height, input_width]`. `[batch_size, input_channels, input_height, input_width]`.
Returns: Returns:
Variable: The pooling result. Variable: The output tensor of pooling result. The data type is same as input tensor.
Raises: Raises:
ValueError: If `pool_type` is not "max" nor "avg" ValueError: If `pool_type` is not "max" nor "avg"
...@@ -3316,10 +3318,32 @@ def pool2d(input, ...@@ -3316,10 +3318,32 @@ def pool2d(input,
import paddle.fluid as fluid import paddle.fluid as fluid
data = fluid.layers.data( data = fluid.data(name='data', shape=[None, 3, 32, 32], dtype='float32')
name='data', shape=[10, 3, 32, 32], append_batch_size=False, dtype='float32')
# max pool2d
pool2d = fluid.layers.pool2d(
input = data,
pool_size = 2,
pool_type = "max",
pool_stride = 1,
global_pooling=False)
# average pool2d
pool2d = fluid.layers.pool2d(
input = data,
pool_size = 2,
pool_type = "avg",
pool_stride = 1,
global_pooling=False)
# global average pool2d
pool2d = fluid.layers.pool2d(
input = data,
pool_size = 2,
pool_type = "avg",
pool_stride = 1,
global_pooling=True)
# example 1:
# Attr(pool_padding) is a list with 4 elements, Attr(data_format) is "NCHW". # Attr(pool_padding) is a list with 4 elements, Attr(data_format) is "NCHW".
out_1 = fluid.layers.pool2d( out_1 = fluid.layers.pool2d(
input = data, input = data,
...@@ -3329,7 +3353,6 @@ def pool2d(input, ...@@ -3329,7 +3353,6 @@ def pool2d(input,
pool_padding = [1, 2, 1, 0], pool_padding = [1, 2, 1, 0],
data_format = "NCHW") data_format = "NCHW")
# example 2:
# Attr(pool_padding) is a string, Attr(data_format) is "NCHW". # Attr(pool_padding) is a string, Attr(data_format) is "NCHW".
out_2 = fluid.layers.pool2d( out_2 = fluid.layers.pool2d(
input = data, input = data,
...@@ -3451,7 +3474,8 @@ def pool3d(input, ...@@ -3451,7 +3474,8 @@ def pool3d(input,
${comment} ${comment}
Args: Args:
input (Variable): The input tensor of pooling operator. The format of input (Variable): The input tensor of pooling operator, which is a 5-D tensor with
shape [N, C, D, H, W]. The format of
input tensor is `"NCDHW"` or `"NDHWC"`, where `N` is batch size, `C` is input tensor is `"NCDHW"` or `"NDHWC"`, where `N` is batch size, `C` is
the number of channels, `D` is the depth of the feature, the number of channels, `D` is the depth of the feature,
`H` is the height of the feature, and `W` is the width `H` is the height of the feature, and `W` is the width
...@@ -3475,8 +3499,9 @@ def pool3d(input, ...@@ -3475,8 +3499,9 @@ def pool3d(input,
global_pooling (bool): ${global_pooling_comment} global_pooling (bool): ${global_pooling_comment}
use_cudnn (bool): ${use_cudnn_comment} use_cudnn (bool): ${use_cudnn_comment}
ceil_mode (bool): ${ceil_mode_comment} ceil_mode (bool): ${ceil_mode_comment}
name (str): A name for this layer(optional). If set None, the layer name(str, optional): For detailed information, please refer
will be named automatically. to :ref:`api_guide_Name`. Usually name is no need to set and
None by default.
exclusive (bool): Whether to exclude padding points in average pooling exclusive (bool): Whether to exclude padding points in average pooling
mode, default is true. mode, default is true.
data_format (string): The data format of the input and output data. An optional string from: `"NCDHW"`, `"NDHWC"`. data_format (string): The data format of the input and output data. An optional string from: `"NCDHW"`, `"NDHWC"`.
...@@ -3484,7 +3509,7 @@ def pool3d(input, ...@@ -3484,7 +3509,7 @@ def pool3d(input,
`[batch_size, input_channels, input_depth, input_height, input_width]`. `[batch_size, input_channels, input_depth, input_height, input_width]`.
Returns: Returns:
Variable: output of pool3d layer. Variable: The output tensor of pooling result. The data type is same as input tensor.
Examples: Examples:
...@@ -3492,8 +3517,31 @@ def pool3d(input, ...@@ -3492,8 +3517,31 @@ def pool3d(input,
import paddle.fluid as fluid import paddle.fluid as fluid
data = fluid.layers.data( data = fluid.data(name='data', shape=[None, 3, 32, 32, 32], dtype='float32')
name='data', shape=[10, 3, 32, 32, 32], append_batch_size=False, dtype='float32')
# max pool3d
pool3d = fluid.layers.pool3d(
input = data,
pool_size = 2,
pool_type = "max",
pool_stride = 1,
global_pooling=False)
# average pool3d
pool3d = fluid.layers.pool3d(
input = data,
pool_size = 2,
pool_type = "avg",
pool_stride = 1,
global_pooling=False)
# global average pool3d
pool3d = fluid.layers.pool3d(
input = data,
pool_size = 2,
pool_type = "avg",
pool_stride = 1,
global_pooling=True)
# example 1: # example 1:
# Attr(pool_padding) is a list with 6 elements, Attr(data_format) is "NCDHW". # Attr(pool_padding) is a list with 6 elements, Attr(data_format) is "NCDHW".
...@@ -3625,13 +3673,12 @@ def adaptive_pool2d(input, ...@@ -3625,13 +3673,12 @@ def adaptive_pool2d(input,
require_index=False, require_index=False,
name=None): name=None):
""" """
**Adaptive Pool2d Operator** This operation calculates the output based on the input, pool_size,
The adaptive_pool2d operation calculates the output based on the input, pool_size,
pool_type parameters. Input(X) and output(Out) are in NCHW format, where N is batch pool_type parameters. Input(X) and output(Out) are in NCHW format, where N is batch
size, C is the number of channels, H is the height of the feature, and W is size, C is the number of channels, H is the height of the feature, and W is
the width of the feature. Parameters(pool_size) should contain two elements which the width of the feature. Parameters(pool_size) should contain two elements which
represent height and width, respectively. Also the H and W dimensions of output(Out) represent height and width, respectively. Also the H and W dimensions of output(Out)
is same as Parameter(pool_size). is same as Parameter(pool_size). The output tensor shape will be [N, C, pool_size[0], pool_size[1]]
For average adaptive pool2d: For average adaptive pool2d:
...@@ -3648,20 +3695,23 @@ def adaptive_pool2d(input, ...@@ -3648,20 +3695,23 @@ def adaptive_pool2d(input,
Output(i ,j) &= \\frac{sum(Input[hstart:hend, wstart:wend])}{(hend - hstart) * (wend - wstart)} Output(i ,j) &= \\frac{sum(Input[hstart:hend, wstart:wend])}{(hend - hstart) * (wend - wstart)}
Args: Args:
input (Variable): The input tensor of pooling operator. The format of input (Variable): The input tensor of pooling operator, which is a 4-D tensor
input tensor is NCHW, where N is batch size, C is with shape [N, C, H, W]. The format of input tensor is NCHW,
the number of channels, H is the height of the where N is batch size, C is the number of channels, H is the
feature, and W is the width of the feature. height of the feature, and W is the width of the feature.
The data type is float32 or float64.
pool_size (int|list|tuple): The pool kernel size. If pool kernel size is a tuple or list, pool_size (int|list|tuple): The pool kernel size. If pool kernel size is a tuple or list,
it must contain two integers, (pool_size_Height, pool_size_Width). it must contain two integers, (pool_size_Height, pool_size_Width).
pool_type: ${pooling_type_comment} pool_type: ${pooling_type_comment}
require_index (bool): If true, the index of max pooling point will be returned along require_index (bool): If true, the index of max pooling point will be returned along
with outputs. It cannot be set in average pooling type. with outputs. It cannot be set in average pooling type. Default False.
name (str|None): A name for this layer(optional). If set None, the name(str, optional): For detailed information, please refer
layer will be named automatically. to :ref:`api_guide_Name`. Usually name is no need to set and
None by default.
Returns: Returns:
Variable: The pooling result. Variable: The output tensor of adaptive pooling result. The data type is same
as input tensor.
Raises: Raises:
ValueError: 'pool_type' is not 'max' nor 'avg'. ValueError: 'pool_type' is not 'max' nor 'avg'.
...@@ -3671,6 +3721,7 @@ def adaptive_pool2d(input, ...@@ -3671,6 +3721,7 @@ def adaptive_pool2d(input,
Examples: Examples:
.. code-block:: python .. code-block:: python
# average adaptive pool2d
# suppose input data in shape of [N, C, H, W], `pool_size` is [m, n], # suppose input data in shape of [N, C, H, W], `pool_size` is [m, n],
# output shape is [N, C, m, n], adaptive pool divide H and W dimentions # output shape is [N, C, m, n], adaptive pool divide H and W dimentions
# of input data into m * n grids averagely and performs poolings in each # of input data into m * n grids averagely and performs poolings in each
...@@ -3686,12 +3737,33 @@ def adaptive_pool2d(input, ...@@ -3686,12 +3737,33 @@ def adaptive_pool2d(input,
# output[:, :, i, j] = avg(input[:, :, hstart: hend, wstart: wend]) # output[:, :, i, j] = avg(input[:, :, hstart: hend, wstart: wend])
# #
import paddle.fluid as fluid import paddle.fluid as fluid
data = fluid.layers.data( data = fluid.data(name='data', shape=[None, 3, 32, 32], dtype='float32')
name='data', shape=[3, 32, 32], dtype='float32')
pool_out = fluid.layers.adaptive_pool2d( pool_out = fluid.layers.adaptive_pool2d(
input=data, input=data,
pool_size=[3, 3], pool_size=[3, 3],
pool_type='avg') pool_type='avg')
# max adaptive pool2d
# suppose input data in shape of [N, C, H, W], `pool_size` is [m, n],
# output shape is [N, C, m, n], adaptive pool divide H and W dimentions
# of input data into m * n grids averagely and performs poolings in each
# grid to get output.
# adaptive average pool performs calculations as follow:
#
# for i in range(m):
# for j in range(n):
# hstart = floor(i * H / m)
# hend = ceil((i + 1) * H / m)
# wstart = floor(i * W / n)
# wend = ceil((i + 1) * W / n)
# output[:, :, i, j] = max(input[:, :, hstart: hend, wstart: wend])
#
import paddle.fluid as fluid
data = fluid.data(name='data', shape=[None, 3, 32, 32], dtype='float32')
pool_out = fluid.layers.adaptive_pool2d(
input=data,
pool_size=[3, 3],
pool_type='max')
""" """
if pool_type not in ["max", "avg"]: if pool_type not in ["max", "avg"]:
raise ValueError( raise ValueError(
...@@ -3738,13 +3810,13 @@ def adaptive_pool3d(input, ...@@ -3738,13 +3810,13 @@ def adaptive_pool3d(input,
require_index=False, require_index=False,
name=None): name=None):
""" """
**Adaptive Pool3d Operator** This operation calculates the output based on the input, pool_size,
The adaptive_pool3d operation calculates the output based on the input, pool_size,
pool_type parameters. Input(X) and output(Out) are in NCDHW format, where N is batch pool_type parameters. Input(X) and output(Out) are in NCDHW format, where N is batch
size, C is the number of channels, D is the depth of the feature, H is the height of size, C is the number of channels, D is the depth of the feature, H is the height of
the feature, and W is the width of the feature. Parameters(pool_size) should contain the feature, and W is the width of the feature. Parameters(pool_size) should contain
three elements which represent height and width, respectively. Also the D, H and W three elements which represent height and width, respectively. Also the D, H and W
dimensions of output(Out) is same as Parameter(pool_size). dimensions of output(Out) is same as Parameter(pool_size). The output tensor shape
will be [N, C, pool_size[0], pool_size[1], pool_size[2]]
For average adaptive pool3d: For average adaptive pool3d:
...@@ -3765,20 +3837,22 @@ def adaptive_pool3d(input, ...@@ -3765,20 +3837,22 @@ def adaptive_pool3d(input,
Output(i ,j, k) &= \\frac{sum(Input[dstart:dend, hstart:hend, wstart:wend])}{(dend - dstart) * (hend - hstart) * (wend - wstart)} Output(i ,j, k) &= \\frac{sum(Input[dstart:dend, hstart:hend, wstart:wend])}{(dend - dstart) * (hend - hstart) * (wend - wstart)}
Args: Args:
input (Variable): The input tensor of pooling operator. The format of input (Variable): The input tensor of pooling operator, which is a 5-D tensor with
input tensor is NCDHW, where N is batch size, C is shape [N, C, D, H, W]. The format of input tensor is NCDHW, where
the number of channels, D is the depth of the feature, N is batch size, C is the number of channels, D is the depth of the feature,
H is the height of the feature, and W is the width of the feature. H is the height of the feature, and W is the width of the feature.
The data type is float32 or float64.
pool_size (int|list|tuple): The pool kernel size. If pool kernel size is a tuple or list, pool_size (int|list|tuple): The pool kernel size. If pool kernel size is a tuple or list,
it must contain three integers, (Depth, Height, Width). it must contain three integers, (Depth, Height, Width).
pool_type: ${pooling_type_comment} pool_type: ${pooling_type_comment}
require_index (bool): If true, the index of max pooling point will be returned along require_index (bool): If true, the index of max pooling point will be returned along
with outputs. It cannot be set in average pooling type. with outputs. It cannot be set in average pooling type. Default False.
name (str|None): A name for this layer(optional). If set None, the name(str, optional): For detailed information, please refer
layer will be named automatically. to :ref:`api_guide_Name`. Usually name is no need to set and
None by default.
Returns: Returns:
Variable: The pooling result. Variable: The output tensor of adaptive pooling result. The data type is same as input tensor.
Raises: Raises:
ValueError: 'pool_type' is not 'max' nor 'avg'. ValueError: 'pool_type' is not 'max' nor 'avg'.
...@@ -3788,6 +3862,7 @@ def adaptive_pool3d(input, ...@@ -3788,6 +3862,7 @@ def adaptive_pool3d(input,
Examples: Examples:
.. code-block:: python .. code-block:: python
# average adaptive pool3d
# suppose input data in shape of [N, C, D, H, W], `pool_size` is [l, m, n], # suppose input data in shape of [N, C, D, H, W], `pool_size` is [l, m, n],
# output shape is [N, C, l, m, n], adaptive pool divide D, H and W dimentions # output shape is [N, C, l, m, n], adaptive pool divide D, H and W dimentions
# of input data into l * m * n grids averagely and performs poolings in each # of input data into l * m * n grids averagely and performs poolings in each
...@@ -3809,12 +3884,41 @@ def adaptive_pool3d(input, ...@@ -3809,12 +3884,41 @@ def adaptive_pool3d(input,
import paddle.fluid as fluid import paddle.fluid as fluid
data = fluid.layers.data( data = fluid.data(
name='data', shape=[3, 32, 32, 32], dtype='float32') name='data', shape=[None, 3, 32, 32, 32], dtype='float32')
pool_out = fluid.layers.adaptive_pool3d( pool_out = fluid.layers.adaptive_pool3d(
input=data, input=data,
pool_size=[3, 3, 3], pool_size=[3, 3, 3],
pool_type='avg') pool_type='avg')
# max adaptive pool3d
# suppose input data in shape of [N, C, D, H, W], `pool_size` is [l, m, n],
# output shape is [N, C, l, m, n], adaptive pool divide D, H and W dimentions
# of input data into l * m * n grids averagely and performs poolings in each
# grid to get output.
# adaptive average pool performs calculations as follow:
#
# for i in range(l):
# for j in range(m):
# for k in range(n):
# dstart = floor(i * D / l)
# dend = ceil((i + 1) * D / l)
# hstart = floor(j * H / m)
# hend = ceil((j + 1) * H / m)
# wstart = floor(k * W / n)
# wend = ceil((k + 1) * W / n)
# output[:, :, i, j, k] =
# avg(input[:, :, dstart:dend, hstart: hend, wstart: wend])
#
import paddle.fluid as fluid
data = fluid.data(
name='data', shape=[None, 3, 32, 32, 32], dtype='float32')
pool_out = fluid.layers.adaptive_pool3d(
input=data,
pool_size=[3, 3, 3],
pool_type='max')
""" """
if pool_type not in ["max", "avg"]: if pool_type not in ["max", "avg"]:
raise ValueError( raise ValueError(
...@@ -4524,9 +4628,10 @@ def spectral_norm(weight, dim=0, power_iters=1, eps=1e-12, name=None): ...@@ -4524,9 +4628,10 @@ def spectral_norm(weight, dim=0, power_iters=1, eps=1e-12, name=None):
""" """
**Spectral Normalization Layer** **Spectral Normalization Layer**
This layer calculates the spectral normalization value of weight parameters of This operation calculates the spectral normalization value of weight parameters of
fc, conv1d, conv2d, conv3d layers which should be 2-D, 3-D, 4-D, 5-D fc, conv1d, conv2d, conv3d layers which should be 2-D, 3-D, 4-D, 5-D
Parameters. Calculations are showed as follows. Parameters. Output tensor will be in same shape with input tensor.
Calculations are showed as follows.
Step 1: Step 1:
Generate vector U in shape of [H], and V in shape of [W]. Generate vector U in shape of [H], and V in shape of [W].
...@@ -4535,7 +4640,8 @@ def spectral_norm(weight, dim=0, power_iters=1, eps=1e-12, name=None): ...@@ -4535,7 +4640,8 @@ def spectral_norm(weight, dim=0, power_iters=1, eps=1e-12, name=None):
Step 2: Step 2:
:attr:`power_iters` shoule be a positive interger, do following :attr:`power_iters` shoule be a positive interger, do following
calculations with U and V for :attr:`power_iters` rounds. calculations with U and V for :attr:`power_iters` rounds. Calculations
as follows:
.. math:: .. math::
...@@ -4560,18 +4666,20 @@ def spectral_norm(weight, dim=0, power_iters=1, eps=1e-12, name=None): ...@@ -4560,18 +4666,20 @@ def spectral_norm(weight, dim=0, power_iters=1, eps=1e-12, name=None):
dim(int): ${dim_comment} dim(int): ${dim_comment}
power_iters(int): ${power_iters_comment} power_iters(int): ${power_iters_comment}
eps(float): ${eps_comment} eps(float): ${eps_comment}
name (str): The name of this layer. It is optional. name(str, optional): For detailed information, please refer
to :ref:`api_guide_Name`. Usually name is no need to set and
None by default.
Returns: Returns:
Variable: A tensor variable of weight parameters after spectral normalization. Variable: A tensor variable of weight parameters after spectral normalization.
The data type and shape is same as input tensor.
Examples: Examples:
.. code-block:: python .. code-block:: python
import paddle.fluid as fluid import paddle.fluid as fluid
weight = fluid.layers.data(name='weight', shape=[2, 8, 32, 32], weight = fluid.data(name='weight', shape=[2, 8, 32, 32], dtype='float32')
append_batch_size=False, dtype='float32')
x = fluid.layers.spectral_norm(weight=weight, dim=1, power_iters=2) x = fluid.layers.spectral_norm(weight=weight, dim=1, power_iters=2)
""" """
helper = LayerHelper('spectral_norm', **locals()) helper = LayerHelper('spectral_norm', **locals())
...@@ -13986,19 +14094,22 @@ def grid_sampler(x, grid, name=None): ...@@ -13986,19 +14094,22 @@ def grid_sampler(x, grid, name=None):
""" """
This operation samples input X by using bilinear interpolation based on This operation samples input X by using bilinear interpolation based on
flow field grid, which is usually gennerated by :code:`affine_grid` . The grid of flow field grid, which is usually gennerated by :code:`affine_grid` . The grid of
shape [N, H, W, 2] is the concatenation of (grid_x, grid_y) coordinates shape [N, H, W, 2] is the concatenation of (x, y) coordinates
with shape [N, H, W] each, where grid_x is indexing the 4th dimension with shape [N, H, W] each, where x is indexing the 4th dimension
(in width dimension) of input data x and grid_y is indexng the 3rd (in width dimension) of input data x and y is indexng the 3rd
dimention (in height dimension), finally results is the bilinear dimention (in height dimension), finally results is the bilinear
interpolation value of 4 nearest corner points. interpolation value of 4 nearest corner points. The output tensor
shape will be [N, C, H, W].
.. code-block:: text .. code-block:: text
Step 1: Step 1:
Get (x, y) grid coordinates and scale to [0, H-1/W-1]. Get (x, y) grid coordinates and scale to [0, H-1/W-1].
grid_x = 0.5 * (grid[:, :, :, 0] + 1) * (W - 1) .. code-block:: text
grid_y = 0.5 * (grid[:, :, :, 1] + 1) * (H - 1)
grid_x = 0.5 * (grid[:, :, :, 0] + 1) * (W - 1)
grid_y = 0.5 * (grid[:, :, :, 1] + 1) * (H - 1)
Step 2: Step 2:
Indices input data X with grid (x, y) in each [H, W] area, and bilinear Indices input data X with grid (x, y) in each [H, W] area, and bilinear
...@@ -14033,13 +14144,20 @@ def grid_sampler(x, grid, name=None): ...@@ -14033,13 +14144,20 @@ def grid_sampler(x, grid, name=None):
+ ws * d_e * d_n + es * d_w * d_n + ws * d_e * d_n + es * d_w * d_n
Args: Args:
x(Variable): Input data of shape [N, C, H, W]. x(Variable): The input tensor, which is a 4-D tensor with shape
grid(Variable): Input grid tensor of shape [N, H, W, 2]. [N, C, H, W], N is the batch size, C is the channel
name (str, default None): The name of this layer. number, H and W is the feature height and width.
The data type is float32 or float64.
grid(Variable): Input grid tensor of shape [N, H, W, 2]. The
data type is float32 or float64.
name(str, optional): For detailed information, please refer
to :ref:`api_guide_Name`. Usually name is no need to set and
None by default.
Returns: Returns:
Variable: Output of shape [N, C, H, W] data samples input X Variable: Output of shape [N, C, H, W] data samples input X
using bilnear interpolation based on input grid. using bilnear interpolation based on input grid.
The data type is same as input tensor.
Examples: Examples:
...@@ -14047,7 +14165,8 @@ def grid_sampler(x, grid, name=None): ...@@ -14047,7 +14165,8 @@ def grid_sampler(x, grid, name=None):
import paddle.fluid as fluid import paddle.fluid as fluid
x = fluid.layers.data(name='x', shape=[10, 32, 32], dtype='float32') # use with affine_grid
x = fluid.data(name='x', shape=[None, 10, 32, 32], dtype='float32')
theta = fluid.layers.data(name='theta', shape=[2, 3], dtype='float32') theta = fluid.layers.data(name='theta', shape=[2, 3], dtype='float32')
grid = fluid.layers.affine_grid(theta=theta, out_shape=[3, 10, 32, 32]) grid = fluid.layers.affine_grid(theta=theta, out_shape=[3, 10, 32, 32])
out = fluid.layers.grid_sampler(x=x, grid=grid) out = fluid.layers.grid_sampler(x=x, grid=grid)
...@@ -14431,11 +14550,13 @@ def temporal_shift(x, seg_num, shift_ratio=0.25, name=None): ...@@ -14431,11 +14550,13 @@ def temporal_shift(x, seg_num, shift_ratio=0.25, name=None):
x(Variable): ${x_comment} x(Variable): ${x_comment}
seg_num(int): ${seg_num_comment} seg_num(int): ${seg_num_comment}
shift_ratio(float): ${shift_ratio_comment} shift_ratio(float): ${shift_ratio_comment}
name (str, default None): The name of this layer. name(str, optional): For detailed information, please refer
to :ref:`api_guide_Name`. Usually name is no need to set and
None by default.
Returns: Returns:
out(Variable): The temporal shifting result is a tensor variable with the out(Variable): The temporal shifting result is a tensor variable with the
same shape and same type as the input. same shape and same data type as the input.
Raises: Raises:
TypeError: seg_num must be int type. TypeError: seg_num must be int type.
...@@ -14444,7 +14565,7 @@ def temporal_shift(x, seg_num, shift_ratio=0.25, name=None): ...@@ -14444,7 +14565,7 @@ def temporal_shift(x, seg_num, shift_ratio=0.25, name=None):
.. code-block:: python .. code-block:: python
import paddle.fluid as fluid import paddle.fluid as fluid
input = fluid.layers.data(name='input', shape=[4,2,2], dtype='float32') input = fluid.data(name='input', shape=[None,4,2,2], dtype='float32')
out = fluid.layers.temporal_shift(x=input, seg_num=2, shift_ratio=0.2) out = fluid.layers.temporal_shift(x=input, seg_num=2, shift_ratio=0.2)
""" """
helper = LayerHelper("temporal_shift", **locals()) helper = LayerHelper("temporal_shift", **locals())
...@@ -14875,16 +14996,18 @@ def kldiv_loss(x, target, reduction='mean', name=None): ...@@ -14875,16 +14996,18 @@ def kldiv_loss(x, target, reduction='mean', name=None):
x (Variable): ${x_comment} x (Variable): ${x_comment}
target (Variable): ${target_comment} target (Variable): ${target_comment}
reduction (Variable): ${reduction_comment} reduction (Variable): ${reduction_comment}
name (str, default None): The name of this layer. name(str, optional): For detailed information, please refer
to :ref:`api_guide_Name`. Usually name is no need to set and
None by default.
Returns: Returns:
kldiv\_loss (Variable): The KL divergence loss. Variable(Tensor): The KL divergence loss. The data type is same as input tensor
Examples: Examples:
.. code-block:: python .. code-block:: python
import paddle.fluid as fluid import paddle.fluid as fluid
x = fluid.layers.data(name='x', shape=[4,2,2], dtype='float32') x = fluid.data(name='x', shape=[None,4,2,2], dtype='float32')
target = fluid.layers.data(name='target', shape=[4,2,2], dtype='float32') target = fluid.layers.data(name='target', shape=[4,2,2], dtype='float32')
loss = fluid.layers.kldiv_loss(x=x, target=target, reduction='batchmean') loss = fluid.layers.kldiv_loss(x=x, target=target, reduction='batchmean')
""" """
......
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或