PaddlePaddle
- abs
- acos
- add
- add_n
- addmm
- all
- allclose
- any
- arange
- argmax
- argmin
- argsort
- asin
- assign
- atan
- bernoulli
- bmm
- broadcast_to
- cast
- ceil
- cholesky
- chunk
- clip
- concat
- conj
- cos
- cosh
- CPUPlace
- cross
- CUDAPinnedPlace
- CUDAPlace
- cumsum
- DataParallel
- diag
- disable_static
- dist
- divide
- dot
- empty
- empty_like
- enable_static
- equal
- equal_all
- erf
- exp
- expand
- expand_as
- eye
- flatten
- flip
- floor
- floor_divide
- flops
- full
- full_like
- gather
- gather_nd
- get_cuda_rng_state
- get_cudnn_version
- get_default_dtype
- get_device
- grad
- greater_equal
- greater_than
- histogram
- imag
- in_dynamic_mode
- increment
- index_sample
- index_select
- inverse
- is_compiled_with_cuda
- is_compiled_with_xpu
- is_empty
- is_tensor
- isfinite
- isinf
- isnan
- kron
- less_equal
- less_than
- linspace
- load
- log
- log10
- log1p
- log2
- logical_and
- logical_not
- logical_or
- logical_xor
- logsumexp
- masked_select
- matmul
- max
- maximum
- mean
- median
- meshgrid
- min
- minimum
- mm
- mod
- Model
- multinomial
- multiplex
- multiply
- mv
- no_grad
- nonzero
- norm
- normal
- not_equal
- numel
- ones
- ones_like
- ParamAttr
- pow
- prod
- rand
- randint
- randn
- randperm
- rank
- real
- reciprocal
- reshape
- reshape_
- roll
- round
- rsqrt
- save
- scale
- scatter
- scatter_
- scatter_nd
- scatter_nd_add
- seed
- set_cuda_rng_state
- set_default_dtype
- set_device
- shape
- shard_index
- sign
- sin
- sinh
- slice
- sort
- split
- sqrt
- square
- squeeze
- squeeze_
- stack
- stanh
- std
- strided_slice
- subtract
- sum
- summary
- t
- tan
- tanh
- tanh_
- Tensor
- tile
- to_tensor
- topk
- trace
- transpose
- tril
- triu
- unbind
- uniform
- unique
- unsqueeze
- unsqueeze_
- unstack
- var
- where
- XPUPlace
- zeros
- zeros_like
- create_lod_tensor
- create_random_int_lodtensor
- cuda_pinned_places
- data
- DataFeedDesc
- DataFeeder
- device_guard
- DistributeTranspiler
- DistributeTranspilerConfig
- get_flags
-
- adaptive_pool2d
- adaptive_pool3d
- add_position_encoding
- affine_channel
- affine_grid
- anchor_generator
- argmax
- argmin
- argsort
- array_length
- array_read
- array_write
- assign
- autoincreased_step_counter
- BasicDecoder
- beam_search
- beam_search_decode
- bipartite_match
- box_clip
- box_coder
- box_decoder_and_assign
- bpr_loss
- brelu
- Categorical
- center_loss
- clip
- clip_by_norm
- collect_fpn_proposals
- concat
- cond
- continuous_value_model
- cosine_decay
- create_array
- create_py_reader_by_data
- create_tensor
- crop
- crop_tensor
- cross_entropy
- ctc_greedy_decoder
- cumsum
- data
- DecodeHelper
- Decoder
- deformable_conv
- deformable_roi_pooling
- density_prior_box
- detection_output
- diag
- distribute_fpn_proposals
- double_buffer
- dropout
- dynamic_gru
- dynamic_lstm
- dynamic_lstmp
- DynamicRNN
- edit_distance
- elementwise_add
- elementwise_div
- elementwise_floordiv
- elementwise_max
- elementwise_min
- elementwise_mod
- elementwise_pow
- elementwise_sub
- elu
- embedding
- equal
- expand
- expand_as
- exponential_decay
- eye
- fc
- fill_constant
- filter_by_instag
- flatten
- fsp_matrix
- gather
- gather_nd
- gaussian_random
- gelu
- generate_mask_labels
- generate_proposal_labels
- generate_proposals
- get_tensor_from_selected_rows
- greater_equal
- greater_than
- GreedyEmbeddingHelper
- grid_sampler
- gru_unit
- GRUCell
- hard_shrink
- hard_sigmoid
- hard_swish
- has_inf
- has_nan
- hash
- hsigmoid
- huber_loss
- IfElse
- im2sequence
- image_resize
- image_resize_short
- increment
- inplace_abn
- inverse_time_decay
- iou_similarity
- isfinite
- kldiv_loss
- l2_normalize
- label_smooth
- leaky_relu
- less_equal
- less_than
- linear_chain_crf
- linear_lr_warmup
- locality_aware_nms
- lod_append
- lod_reset
- logsigmoid
- lrn
- lstm
- lstm_unit
- LSTMCell
- margin_rank_loss
- matmul
- matrix_nms
- maxout
- mean
- merge_selected_rows
- mse_loss
- mul
- multiclass_nms
- MultivariateNormalDiag
- natural_exp_decay
- noam_decay
- Normal
- not_equal
- one_hot
- ones
- ones_like
- pad
- pad2d
- pad_constant_like
- piecewise_decay
- pixel_shuffle
- polygon_box_transform
- polynomial_decay
- pool2d
- pool3d
- pow
- prior_box
- prroi_pool
- psroi_pool
- py_reader
- random_crop
- range
- rank_loss
- read_file
- reduce_all
- reduce_any
- reduce_max
- reduce_mean
- reduce_min
- reduce_prod
- reduce_sum
- relu
- relu6
- reorder_lod_tensor_by_rank
- reshape
- resize_bilinear
- resize_nearest
- resize_trilinear
- retinanet_detection_output
- retinanet_target_assign
- reverse
- rnn
- RNNCell
- roi_align
- roi_perspective_transform
- roi_pool
- rpn_target_assign
- sampled_softmax_with_cross_entropy
- SampleEmbeddingHelper
- sampling_id
- scatter
- selu
- sequence_concat
- sequence_conv
- sequence_enumerate
- sequence_expand
- sequence_expand_as
- sequence_first_step
- sequence_last_step
- sequence_mask
- sequence_pad
- sequence_pool
- sequence_reshape
- sequence_reverse
- sequence_scatter
- sequence_slice
- sequence_softmax
- sequence_unpad
- shuffle_channel
- sigmoid_cross_entropy_with_logits
- sigmoid_focal_loss
- sign
- similarity_focus
- size
- smooth_l1
- soft_relu
- softmax
- softplus
- softshrink
- softsign
- space_to_depth
- split
- squeeze
- ssd_loss
- stack
- StaticRNN
- strided_slice
- sum
- sums
- swish
- Switch
- tanh
- tanh_shrink
- target_assign
- teacher_student_sigmoid_loss
- tensor_array_to_tensor
- thresholded_relu
- topk
- TrainingHelper
- unbind
- Uniform
- uniform_random
- unique
- unique_with_counts
- unsqueeze
- warpctc
- where
- While
- while_loop
- yolo_box
- yolov3_loss
- zeros
- zeros_like
- load_op_library
- LoDTensor
- LoDTensorArray
- memory_optimize
- one_hot
- release_memory
- require_version
- set_flags
- Tensor
- Overview
- AdaptiveAvgPool1D
- AdaptiveAvgPool2D
- AdaptiveAvgPool3D
- AdaptiveMaxPool1D
- AdaptiveMaxPool2D
- AdaptiveMaxPool3D
- AlphaDropout
- AvgPool1D
- AvgPool2D
- AvgPool3D
- BatchNorm
- BatchNorm1D
- BatchNorm2D
- BatchNorm3D
- BCELoss
- BCEWithLogitsLoss
- BeamSearchDecoder
- Bilinear
- BiRNN
- ClipGradByGlobalNorm
- ClipGradByNorm
- ClipGradByValue
- Conv1D
- Conv1DTranspose
- Conv2D
- Conv2DTranspose
- Conv3D
- Conv3DTranspose
- CosineSimilarity
- CrossEntropyLoss
- CTCLoss
- Dropout
- Dropout2D
- Dropout3D
- dynamic_decode
- ELU
- Embedding
- Flatten
-
- adaptive_avg_pool1d
- adaptive_avg_pool2d
- adaptive_avg_pool3d
- adaptive_max_pool1d
- adaptive_max_pool2d
- adaptive_max_pool3d
- affine_grid
- alpha_dropout
- avg_pool1d
- avg_pool2d
- avg_pool3d
- batch_norm
- bilinear
- binary_cross_entropy
- binary_cross_entropy_with_logits
- conv1d
- conv1d_transpose
- conv2d
- conv2d_transpose
- conv3d
- conv3d_transpose
- cosine_similarity
- cross_entropy
- ctc_loss
- diag_embed
- dice_loss
- dropout
- dropout2d
- dropout3d
- elu
- elu_
- embedding
- gather_tree
- gelu
- grid_sample
- hardshrink
- hardsigmoid
- hardswish
- hardtanh
- hsigmoid_loss
- instance_norm
- interpolate
- kl_div
- l1_loss
- label_smooth
- layer_norm
- leaky_relu
- linear
- local_response_norm
- log_loss
- log_sigmoid
- log_softmax
- margin_ranking_loss
- max_pool1d
- max_pool2d
- max_pool3d
- maxout
- mse_loss
- nll_loss
- normalize
- npair_loss
- one_hot
- pad
- pixel_shuffle
- prelu
- relu
- relu6
- relu_
- selu
- sigmoid
- sigmoid_focal_loss
- smooth_l1_loss
- softmax
- softmax_
- softmax_with_cross_entropy
- softplus
- softshrink
- softsign
- square_error_cost
- swish
- tanhshrink
- temporal_shift
- thresholded_relu
- unfold
- upsample
- GELU
- GroupNorm
- GRU
- GRUCell
- Hardshrink
- Hardsigmoid
- Hardswish
- Hardtanh
- HSigmoidLoss
- InstanceNorm1D
- InstanceNorm2D
- InstanceNorm3D
- KLDivLoss
- L1Loss
- Layer
- LayerList
- LayerNorm
- LeakyReLU
- Linear
- LocalResponseNorm
- LogSigmoid
- LogSoftmax
- LSTM
- LSTMCell
- MarginRankingLoss
- Maxout
- MaxPool1D
- MaxPool2D
- MaxPool3D
- MSELoss
- MultiHeadAttention
- NLLLoss
- Pad1D
- Pad2D
- Pad3D
- PairwiseDistance
- ParameterList
- PixelShuffle
- PReLU
- ReLU
- ReLU6
- RNN
- RNNCellBase
- SELU
- Sequential
- Sigmoid
- SimpleRNN
- SimpleRNNCell
- SmoothL1Loss
- Softmax
- Softplus
- Softshrink
- Softsign
- SpectralNorm
- Swish
- SyncBatchNorm
- Tanh
- Tanhshrink
- ThresholdedReLU
- Transformer
- TransformerDecoder
- TransformerDecoderLayer
- TransformerEncoder
- TransformerEncoderLayer
- Upsample
- UpsamplingBilinear2D
- UpsamplingNearest2D
- append_backward
- BuildStrategy
- CompiledProgram
- cpu_places
- create_global_var
- create_parameter
- cuda_places
- data
- default_main_program
- default_startup_program
- deserialize_persistables
- deserialize_program
- device_guard
- ExecutionStrategy
- Executor
- global_scope
- gradients
- InputSpec
- load
- load_from_file
- load_inference_model
- load_program_state
- name_scope
- ParallelExecutor
- Program
- program_guard
- py_func
- save
- save_inference_model
- save_to_file
- scope_guard
- serialize_persistables
- serialize_program
- set_program_state
- Variable
- WeightNormParamAttr
-
- adjust_brightness
- adjust_contrast
- adjust_hue
- adjust_saturation
- BaseTransform
- BrightnessTransform
- center_crop
- CenterCrop
- ColorJitter
- Compose
- ContrastTransform
- crop
- Grayscale
- hflip
- HueTransform
- Normalize
- normalize
- Pad
- pad
- RandomCrop
- RandomHorizontalFli
- RandomResizedCrop
- RandomRotation
- RandomVerticalFlip
- Resize
- resize
- rotate
- SaturationTransform
- to_grayscale
- to_tensor
- ToTensor
- Transpose
- vflip
paddle.optimizer / Adadelta
Adadelta¶
-
class
paddle.optimizer.
Adadelta
( learning_rate=0.001, epsilon=1.0e-6, rho=0.95, parameters=None, weight_decay=0.01, grad_clip=None, name=None ) [源代码] ¶
注意:此接口不支持稀疏参数更新。
Adadelta优化器,具体细节可参考论文 ADADELTA: AN ADAPTIVE LEARNING RATE METHOD 。
更新公式如下:
- 参数:
-
learning_rate (float|_LRScheduleri, 可选) - 学习率,用于参数更新的计算。可以是一个浮点型值或者一个_LRScheduler类,默认值为0.001
epsilon (float, 可选) - 保持数值稳定性的短浮点类型值,默认值为1e-06
rho (float, 可选) - 算法中的衰减率,默认值为0.95。
parameters (list, 可选) - 指定优化器需要优化的参数。在动态图模式下必须提供该参数;在静态图模式下默认值为None,这时所有的参数都将被优化。
weight_decay (float|Tensor, 可选) - 权重衰减系数,是一个float类型或者shape为[1] ,数据类型为float32的Tensor类型。默认值为0.01
grad_clip (GradientClipBase, 可选) – 梯度裁剪的策略,支持三种裁剪策略: cn_api_fluid_clip_GradientClipByGlobalNorm 、 cn_api_fluid_clip_GradientClipByNorm 、 cn_api_fluid_clip_GradientClipByValue 。 默认值为None,此时将不进行梯度裁剪。
name (str, 可选)- 该参数供开发人员打印调试信息时使用,具体用法请参见 Name ,默认值为None
Adadelta优化器出自 DECOUPLED WEIGHT DECAY REGULARIZATION 论文 <https://arxiv.org/pdf/1711.05101.pdf>,用来解决Adam优化器中L2正则化失效的问题。
代码示例
import paddle
inp = paddle.uniform(min=-0.1, max=0.1, shape=[10, 10], dtype='float32')
linear = paddle.nn.Linear(10, 10)
out = linear(inp)
loss = paddle.mean(out)
adadelta = paddle.optimizer.Adadelta(learning_rate=0.0003, epsilon=1.0e-6, rho=0.95,
parameters=linear.parameters())
out.backward()
adadelta.step()
adadelta.clear_grad()
-
step
( ) ¶
注意:
1. 该API只在 Dygraph 模式下生效
执行一次优化器并进行参数更新。
返回:None。
代码示例
import paddle
value = paddle.arange(26, dtype='float32')
a = paddle.reshape(value, [2, 13])
linear = paddle.nn.Linear(13, 5)
adadelta = paddle.optimizer.Adadelta(learning_rate=0.0003, epsilon=1.0e-6, rho=0.95,
parameters = linear.parameters())
out = linear(a)
out.backward()
adadelta.step()
adadelta.clear_grad()
-
minimize
( loss, startup_program=None, parameters=None, no_grad_set=None ) ¶
为网络添加反向计算过程,并根据反向计算所得的梯度,更新parameters中的Parameters,最小化网络损失值loss。
- 参数:
-
loss (Tensor) – 需要最小化的损失值变量
startup_program (Program, 可选) – 用于初始化parameters中参数的 Program , 默认值为None,此时将使用 default_startup_program
parameters (list, 可选) – 待更新的Parameter或者Parameter.name组成的列表, 默认值为None,此时将更新所有的Parameter
no_grad_set (set, 可选) – 不需要更新的Parameter或者Parameter.name组成的集合,默认值为None
返回: tuple(optimize_ops, params_grads),其中optimize_ops为参数优化OP列表;param_grads为由(param, param_grad)组成的列表,其中param和param_grad分别为参数和参数的梯度。在静态图模式下,该返回值可以加入到 Executor.run()
接口的 fetch_list
参数中,若加入,则会重写 use_prune
参数为True,并根据 feed
和 fetch_list
进行剪枝,详见 Executor
的文档。
代码示例
import paddle
inp = paddle.uniform(min=-0.1, max=0.1, shape=[10, 10], dtype='float32')
linear = paddle.nn.Linear(10, 10)
out = linear(inp)
loss = paddle.mean(out)
beta1 = paddle.to_tensor([0.9], dtype="float32")
beta2 = paddle.to_tensor([0.99], dtype="float32")
adadelta = paddle.optimizer.Adadelta(learning_rate=0.0003, epsilon=1.0e-6, rho=0.95,
parameters=linear.parameters())
out.backward()
adadelta.minimize(loss)
adadelta.clear_grad()
-
clear_grad
( ) ¶
注意:
1. 该API只在 Dygraph 模式下生效
清除需要优化的参数的梯度。
代码示例
import paddle
value = paddle.arange(26, dtype='float32')
a = paddle.reshape(value, [2, 13])
linear = paddle.nn.Linear(13, 5)
optimizer = paddle.optimizer.Adadelta(learning_rate=0.0003, epsilon=1.0e-6, rho=0.95,
parameters=linear.parameters())
out = linear(a)
out.backward()
optimizer.step()
optimizer.clear_grad()
-
set_lr
( value ) ¶
注意:
1. 该API只在 Dygraph 模式下生效
手动设置当前 optimizer
的学习率。当使用_LRScheduler时,无法使用该API手动设置学习率,因为这将导致冲突。
- 参数:
-
value (float) - 需要设置的学习率的值。
返回:None
代码示例
import paddle
linear = paddle.nn.Linear(10, 10)
adadelta = paddle.optimizer.Adadelta(weight_decay=0.01,
learning_rate=0.1, parameters=linear.parameters())
# set learning rate manually by python float value
lr_list = [0.2, 0.3, 0.4, 0.5, 0.6]
for i in range(5):
adadelta.set_lr(lr_list[i])
lr = adadelta.get_lr()
print("current lr is {}".format(lr))
# Print:
# current lr is 0.2
# current lr is 0.3
# current lr is 0.4
# current lr is 0.5
# current lr is 0.6
-
get_lr
( ) ¶
注意:
1. 该API只在 Dygraph 模式下生效
获取当前步骤的学习率。当不使用_LRScheduler时,每次调用的返回值都相同,否则返回当前步骤的学习率。
返回:float,当前步骤的学习率。
代码示例
import numpy as np
import paddle
# example1: _LRScheduler is not used, return value is all the same
emb = paddle.nn.Embedding(10, 10, sparse=False)
adadelta = paddle.optimizer.Adadelta(learning_rate=0.001, parameters = emb.parameters(),weight_decay=0.01)
lr = adadelta.get_lr()
print(lr) # 0.001
# example2: PiecewiseDecay is used, return the step learning rate
inp = np.random.uniform(-0.1, 0.1, [10, 10]).astype("float32")
linear = paddle.nn.Linear(10, 10)
inp = paddle.to_tensor(inp)
out = linear(inp)
loss = paddle.mean(out)
bd = [2, 4, 6, 8]
value = [0.2, 0.4, 0.6, 0.8, 1.0]
scheduler = paddle.optimizer.lr.PiecewiseDecay(bd, value, 0)
adadelta = paddle.optimizer.Adadelta(scheduler,
parameters=linear.parameters(),
weight_decay=0.01)
# first step: learning rate is 0.2
np.allclose(adadelta.get_lr(), 0.2, rtol=1e-06, atol=0.0) # True
# learning rate for different steps
ret = [0.2, 0.2, 0.4, 0.4, 0.6, 0.6, 0.8, 0.8, 1.0, 1.0, 1.0, 1.0]
for i in range(12):
adadelta.step()
lr = adadelta.get_lr()
scheduler.step()
np.allclose(lr, ret[i], rtol=1e-06, atol=0.0) # True
此页内容是否对您有帮助
感谢反馈!