You need to enable JavaScript to run this app.
\u200E
develop
2.0-rc
2.0-beta
2.0-alpha
1.8
1.7
1.6
1.5
1.4
1.3
1.2
1.1
1.0
0.15.0
0.14.0
0.13.0
0.12.0
0.11.0
0.10.0
中文(简)
English(En)
安装说明
Ubuntu下安装
CentOS下安装
MacOS下安装
Windows下安装
使用Conda安装
使用Docker安装
从源码编译
Ubuntu下从源码编译
CentOS下从源码编译
MacOS下从源码编译
Windows下从源码编译
附录
快速上手
基本概念
编程指南
Variable
Tensor
LoDTensor
Operator
Program
Executor
命令式编程使用教程
编程实践
Reader
配置简单的网络
单机训练
训练过程中评测模型
模型/变量的保存、载入与增量训练
典型案例
简单案例
线性回归
数字识别
词向量
计算机视觉
图像分类
生成对抗网络
自然语言处理
情感分析
语义角色标注
机器翻译
推荐
个性化推荐
工具组件
ELASTIC CTR
飞桨大规模分类库简介
进阶指南
准备数据
声明式编程模式（静态图）
准备步骤
数据预处理工具
异步数据读取
同步数据读取
命令式编程模式（动态图）
数据准备、载入及加速
分布式训练
分布式训练快速开始
使用FleetAPI进行分布式训练
预测部署
服务器端部署
安装与编译 Linux 预测库
安装与编译 Windows 预测库
C++ 预测 API介绍
C 预测 API介绍
Python 预测 API介绍
移动端部署
Paddle-Lite
模型压缩
性能调优
单机训练优秀实践
存储分配与优化
运行时设备切换
混合精度训练最佳实践
分布式CPU训练优秀实践
分布式GPU训练优秀实践
重计算：大Batch训练特性
使用Paddle-TensorRT库预测
性能优化分析及工具
CPU性能调优
timeline工具简介
模型评估/调试
模型评估
VisualDL 工具
VisualDL 工具简介
VisualDL 使用指南
二次开发
设计思想
新增OP
如何写新的C++ OP
C++ OP相关注意事项
如何写新的Python OP
如何在框架外部自定义C++ OP
如何贡献代码
本地开发指南
提交PR注意事项
FAQ
环境变量FLAGS
cudnn
数值计算
调试
check nan inf工具
设备管理
分布式
执行器
存储管理
其他
API Reference
API功能分类
基础概念
神经网络层
卷积
池化
图像检测
序列
数学操作
激活函数
损失函数
数据输入输出
控制流
稀疏更新
使用DataFeeder传入训练/预测数据
学习率调度器
张量
复杂网络
优化器
反向传播
评价指标
模型保存与加载
预测引擎
执行引擎
数据并行执行引擎
CompiledProgram
模型参数
分布式训练
分布式同步训练
分布式异步训练
大规模稀疏特征模型训练
分布式训练reader准备
TensorFlow-Fluid常用接口对应表
Caffe-Fluid常用层对应表
fluid
BuildStrategy
CompiledProgram
ComplexVariable
cpu_places
CPUPlace
create_lod_tensor
create_random_int_lodtensor
cuda_pinned_places
cuda_places
CUDAPinnedPlace
CUDAPlace
data
DataFeedDesc
DataFeeder
default_main_program
default_startup_program
disable_dygraph
disable_imperative
device_guard
DistributeTranspiler
DistributeTranspilerConfig
embedding
enable_dygraph
enable_imperative
ExecutionStrategy
Executor
get_flags
global_scope
gradients
in_dygraph_mode
is_compiled_with_cuda
load
load_op_library
LoDTensor
LoDTensorArray
memory_optimize
name_scope
one_hot
ParallelExecutor
ParamAttr
Program
program_guard
release_memory
require_version
save
scope_guard
set_flags
Tensor
Variable
WeightNormParamAttr
fluid.backward
append_backward
gradients
fluid.clip
ErrorClipByValue
GradientClipByGlobalNorm
GradientClipByNorm
GradientClipByValue
set_gradient_clip
dataset
cifar
Conll05
imdb
imikolov
mnist
movielens
sentiment
uci_housing
wmt14
wmt16
fluid.dataset
DatasetFactory
InMemoryDataset
QueueDataset
fluid.dygraph
BackwardStrategy
BatchNorm
BCELoss
BilinearTensorProduct
Conv2D
Conv2DTranspose
Conv3D
Conv3DTranspose
CosineDecay
DataParallel
disable_dygraph
disable_imperative
Dropout
declarative
Embedding
enable_dygraph
enable_imperative
enabled
ExponentialDecay
grad
GroupNorm
GRUUnit
guard
InstanceNorm
InverseTimeDecay
L1Loss
Layer
LayerList
LayerNorm
Linear
load_dygraph
MSELoss
NaturalExpDecay
NCE
NLLLoss
NoamDecay
ParallelEnv
ParameterList
no_grad
PiecewiseDecay
PolynomialDecay
Pool2D
PRelu
prepare_context
ProgramTranslator
save_dygraph
Sequential
SpectralNorm
to_variable
TracedLayer
TreeConv
fluid.executor
Executor
global_scope
scope_guard
fluid.initializer
Bilinear
BilinearInitializer
Constant
ConstantInitializer
MSRA
MSRAInitializer
Normal
NormalInitializer
NumpyArrayInitializer
TruncatedNormal
TruncatedNormalInitializer
Uniform
UniformInitializer
Xavier
XavierInitializer
fluid.io
batch
buffered
cache
chain
compose
ComposeNotAligned
DataLoader
firstn
get_program_parameter
get_program_persistable_vars
load
load_inference_model
load_params
load_persistables
load_program_state
load_vars
map_readers
multiprocess_reader
PyReader
save
save_inference_model
save_params
save_persistables
save_vars
set_program_state
shuffle
xmap_readers
fluid.layers
abs
accuracy
acos
adaptive_pool2d
adaptive_pool3d
add_position_encoding
addcmul
addmm
affine_channel
affine_grid
allclose
anchor_generator
arange
argmax
argmin
argsort
array_length
array_read
array_write
asin
assign
atan
auc
autoincreased_step_counter
batch_norm
BasicDecoder
beam_search
beam_search_decode
bilinear_tensor_product
bipartite_match
bmm
box_clip
box_coder
box_decoder_and_assign
bpr_loss
brelu
BeamSearchDecoder
case
cast
Categorical
ceil
center_loss
chunk_eval
clamp
clip_by_norm
clip
collect_fpn_proposals
concat
cond
continuous_value_model
conv2d
conv2d_transpose
conv3d
conv3d_transpose
cos
cos_sim
cosine_decay
create_array
create_global_var
create_parameter
create_py_reader_by_data
create_tensor
crf_decoding
crop
crop_tensor
cross
cross_entropy
ctc_greedy_decoder
cumsum
data
data_norm
deformable_conv
deformable_roi_pooling
density_prior_box
detection_output
diag
diag_embed
dice_loss
dist
distribute_fpn_proposals
dot
double_buffer
dropout
dynamic_gru
dynamic_lstm
dynamic_lstmp
dynamic_decode
Decoder
DecodeHelper
DynamicRNN
edit_distance
elementwise_add
elementwise_div
elementwise_equal
elementwise_floordiv
elementwise_max
elementwise_min
elementwise_mod
elementwise_mul
elementwise_pow
elementwise_sub
elu
embedding
equal
erf
exp
expand
expand_as
exponential_decay
eye
fc
fill_constant
filter_by_instag
flatten
flip
floor
fsp_matrix
full
full_like
gather
gather_nd
gather_tree
gaussian_random
gelu
generate_mask_labels
generate_proposal_labels
generate_proposals
get_tensor_from_selected_rows
greater_equal
greater_than
GreedyEmbeddingHelper
grid_sampler
group_norm
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
inverse_time_decay
index_select
inplace_abn
instance_norm
interpolate
iou_similarity
is_empty
isfinite
kldiv_loss
kron
l2_normalize
label_smooth
layer_norm
leaky_relu
less_equal
less_than
linear_chain_crf
linear_lr_warmup
linspace
load
locality_aware_nms
lod_append
lod_reset
log
log1p
log_loss
log_softmax
logical_and
logical_not
logical_or
logical_xor
logsigmoid
logsumexp
lrn
lstm
lstm_unit
LSTMCell
margin_rank_loss
matmul
maxout
mean
mean_iou
merge_selected_rows
meshgrid
mse_loss
mul
multi_box_head
multiclass_nms
multiplex
MultivariateNormalDiag
natural_exp_decay
nce
noam_decay
nonzero
Normal
not_equal
npair_loss
one_hot
ones
ones_like
pad
pad_constant_like
pad2d
piecewise_decay
pixel_shuffle
polygon_box_transform
polynomial_decay
pool2d
pool3d
pow
prelu
Print
prior_box
prroi_pool
psroi_pool
py_func
py_reader
randint
randn
random_crop
range
randperm
rank
rank_loss
read_file
reciprocal
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
roi_align
roi_perspective_transform
roi_pool
roll
round
row_conv
rpn_target_assign
rsqrt
RNNCell
sampled_softmax_with_cross_entropy
SampleEmbeddingHelper
sampling_id
scale
scatter
scatter_nd_add
scatter_nd
selu
sequence_concat
sequence_conv
sequence_enumerate
sequence_expand_as
sequence_expand
sequence_first_step
sequence_last_step
sequence_mask
sequence_pad
sequence_pool
sequence_reshape
sequence_reverse
sequence_scatter
sequence_slice
sequence_softmax
sequence_unpad
shape
shard_index
shuffle_channel
sigmoid
sigmoid_cross_entropy_with_logits
sigmoid_focal_loss
sign
similarity_focus
sin
size
slice
smooth_l1
soft_relu
softmax
softmax_with_cross_entropy
softplus
softshrink
softsign
space_to_depth
spectral_norm
split
sqrt
square
square_error_cost
squeeze
ssd_loss
stack
stanh
StaticRNN
strided_slice
sum
sums
swish
Switch
switch_case
t
tanh
tanh_shrink
target_assign
teacher_student_sigmoid_loss
temporal_shift
tensor_array_to_tensor
thresholded_relu
topk
trace
transpose
TrainingHelper
tril
triu
unfold
Uniform
uniform_random
unique
unique_with_counts
unsqueeze
unstack
warpctc
where
While
while_loop
yolo_box
yolov3_loss
zeros
zeros_like
fluid.metrics
Accuracy
Auc
ChunkEvaluator
CompositeMetric
DetectionMAP
EditDistance
MetricBase
Precision
Recall
fluid.nets
glu
img_conv_group
scaled_dot_product_attention
sequence_conv_pool
simple_img_conv_pool
fluid.optimizer
Adadelta
AdadeltaOptimizer
Adagrad
AdagradOptimizer
Adam
Adamax
AdamaxOptimizer
AdamOptimizer
DecayedAdagrad
DecayedAdagradOptimizer
DGCMomentumOptimizer
Dpsgd
DpsgdOptimizer
ExponentialMovingAverage
Ftrl
FtrlOptimizer
LambOptimizer
LarsMomentum
LarsMomentumOptimizer
LookaheadOptimizer
ModelAverage
Momentum
MomentumOptimizer
RecomputeOptimizer
RMSPropOptimizer
SGD
SGDOptimizer
fluid.profiler
cuda_profiler
profiler
reset_profiler
start_profiler
stop_profiler
fluid.regularizer
L1Decay
L1DecayRegularizer
L2Decay
L2DecayRegularizer
fluid.transpiler
DistributeTranspiler
DistributeTranspilerConfig
HashName
memory_optimize
release_memory
fluid.unique_name
generate
guard
switch
常见问题
安装类FAQ
框架类FAQ
其他常见问题
Release Note
fluid.backward
»
API Reference
»
fluid.backward
View page source
fluid.backward
¶
append_backward
gradients
