\u200E
  • 开始使用
  • 特性
  • 文档
    • API
    • 使用指南
  • 工具平台
    • 工具
      • AutoDL
      • PaddleHub
      • PARL
      • ERNIE
      • 全部
    • 平台
      • AI Studio
      • EasyDL
      • EasyEdge
  • 资源
    • 模型和数据集
    • 学习资料
    • 应用案例
  • 3.0
  • develop
  • 3.0-beta
  • 2.6
  • 2.5
  • 2.4
  • 2.3
  • 2.2
  • 2.1
  • 2.0
  • 1.8
  • 中文(简)
  • English(En)
  • Installation Guide
    • Install via pip
      • Install on Linux via PIP
      • Install on macOS via PIP
      • Install on Windows via PIP
    • Install via conda
      • Installation on Linux via Conda
      • Installation on macOS via Conda
      • Installation on Windows via Conda
    • Install via docker
      • Install on Linux via Docker
      • Install on macOS via Docker
      • Docker List
    • Compile From Source Code
      • Compile on Linux from Source Code
      • Compile on macOS from Source Code
      • Compile on Windows from Source Code
    • NVIDIA PaddlePaddle Container Installation Guide
    • Appendix
  • Guides
    • Model Development
      • Introduction to Tensor
    • More Uses for Model Development
      • Model Visualization
      • Introduction to models and layers
      • Gradient clip methods in Paddle
      • Introduction to Data Type Promotion
    • Dynamic to Static Graph
      • Supported Grammars
      • Error Debugging Experience
    • Deploy Inference Model
      • Model Compression
    • Distributed Training
      • Quick start for distributed training
    • Performance Improving
      • Automatic Mixed Precision Training (AMP)
      • Auto-tuning in Full-process Training (Beta)
    • Model Convert
      • Upgrade guide
    • FLAGS
      • cudnn
      • data processing
      • debug
        • check nan inf tool
      • device management
      • distributed
      • executor
      • memory management
      • ascend npu
      • others
  • API Reference
    • paddle
      • abs
      • abs_
      • acos
      • acos_
      • acosh
      • add
      • add_n
      • addmm
      • addmm_
      • all
      • allclose
      • amax
      • amin
      • angle
      • any
      • arange
      • argmax
      • argmin
      • argsort
      • as_complex
      • as_real
      • as_strided
      • asin
      • asinh
      • assign
      • atan
      • atan2
      • atan_
      • atanh
      • atleast_1d
      • atleast_2d
      • atleast_3d
      • baddbmm
      • baddbmm_
      • batch
      • bernoulli
      • bernoulli_
      • bincount
      • binomial
      • bitwise_and
      • bitwise_and_
      • bitwise_invert
      • bitwise_invert_
      • bitwise_left_shift
      • bitwise_left_shift_
      • bitwise_not
      • bitwise_not_
      • bitwise_or
      • bitwise_or_
      • bitwise_right_shift
      • bitwise_right_shift_
      • bitwise_xor
      • bitwise_xor_
      • block_diag
      • bmm
      • broadcast_shape
      • broadcast_tensors
      • broadcast_to
      • bucketize
      • cartesian_prod
      • cast
      • cast_
      • cauchy_
      • cdist
      • ceil
      • check_shape
      • chunk
      • clip
      • clone
      • column_stack
      • combinations
      • complex
      • concat
      • conj
      • copysign
      • copysign_
      • cos
      • cos_
      • cosh
      • count_nonzero
      • CPUPlace
      • create_parameter
      • crop
      • cross
      • CUDAPinnedPlace
      • CUDAPlace
      • cummax
      • cummin
      • cumprod
      • cumprod_
      • cumsum
      • cumsum_
      • cumulative_trapezoid
      • DataParallel
      • deg2rad
      • diag
      • diag_embed
      • diagflat
      • diagonal
      • diagonal_scatter
      • diff
      • digamma
      • digamma_
      • disable_signal_handler
      • disable_static
      • dist
      • divide
      • divide_
      • dot
      • dsplit
      • dstack
      • dtype
      • einsum
      • empty
      • empty_like
      • enable_grad
      • enable_static
      • equal
      • equal_
      • equal_all
      • erf
      • erf_
      • erfinv
      • exp
      • expand
      • expand_as
      • expm1
      • expm1_
      • eye
      • finfo
      • flatten
      • flatten_
      • flip
      • floor
      • floor_divide
      • floor_divide_
      • floor_mod
      • floor_mod_
      • flops
      • fmax
      • fmin
      • frac
      • frac_
      • frexp
      • from_dlpack
      • full
      • full_like
      • gammainc
      • gammainc_
      • gammaincc
      • gammaincc_
      • gammaln
      • gammaln_
      • gather
      • gather_nd
      • gcd
      • gcd_
      • geometric_
      • get_cuda_rng_state
      • get_default_dtype
      • get_flags
      • get_rng_state
      • grad
      • greater_equal
      • greater_equal_
      • greater_than
      • greater_than_
      • heaviside
      • histogram
      • histogram_bin_edges
      • histogramdd
      • hsplit
      • hstack
      • hypot
      • hypot_
      • i0
      • i0_
      • i0e
      • i1
      • i1e
      • iinfo
      • imag
      • in_dynamic_mode
      • increment
      • index_add
      • index_add_
      • index_fill
      • index_fill_
      • index_put
      • index_put_
      • index_sample
      • index_select
      • inner
      • is_complex
      • is_empty
      • is_floating_point
      • is_grad_enabled
      • is_integer
      • is_tensor
      • isclose
      • isfinite
      • isin
      • isinf
      • isnan
      • isneginf
      • isposinf
      • isreal
      • kron
      • kthvalue
      • LazyGuard
      • lcm
      • lcm_
      • ldexp
      • ldexp_
      • lerp
      • less
      • less_
      • less_equal
      • less_equal_
      • less_than
      • less_than_
      • lgamma
      • lgamma_
      • linspace
      • load
      • log
      • log10
      • log10_
      • log1p
      • log2
      • log2_
      • log_
      • log_normal
      • log_normal_
      • logaddexp
      • logcumsumexp
      • logical_and
      • logical_and_
      • logical_not
      • logical_not_
      • logical_or
      • logical_or_
      • logical_xor
      • logit
      • logit_
      • logspace
      • logsumexp
      • masked_fill
      • masked_fill_
      • masked_scatter
      • masked_scatter_
      • masked_select
      • matmul
      • matrix_transpose
      • max
      • maximum
      • mean
      • median
      • meshgrid
      • min
      • minimum
      • mm
      • mode
      • Model
      • moveaxis
      • multigammaln
      • multigammaln_
      • multinomial
      • multiplex
      • multiply
      • multiply_
      • mv
      • nan_to_num
      • nan_to_num_
      • nanmean
      • nanmedian
      • nanquantile
      • nansum
      • neg
      • neg_
      • negative
      • nextafter
      • no_grad
      • nonzero
      • normal
      • normal_
      • not_equal
      • numel
      • ones
      • ones_like
      • outer
      • ParamAttr
      • pdist
      • poisson
      • polar
      • polygamma
      • polygamma_
      • positive
      • pow
      • pow_
      • prod
      • put_along_axis
      • quantile
      • rad2deg
      • rand
      • randint
      • randint_like
      • randn
      • randperm
      • rank
      • real
      • reciprocal
      • reduce_as
      • renorm
      • renorm_
      • repeat_interleave
      • reshape
      • reshape_
      • roll
      • rot90
      • round
      • row_stack
      • rsqrt
      • save
      • scale
      • scatter
      • scatter_
      • scatter_nd
      • scatter_nd_add
      • searchsorted
      • seed
      • select_scatter
      • set_cuda_rng_state
      • set_default_dtype
      • set_flags
      • set_grad_enabled
      • set_printoptions
      • set_rng_state
      • sgn
      • shape
      • shard_index
      • sign
      • signbit
      • sin
      • sin_
      • sinc
      • sinc_
      • sinh
      • sinh_
      • slice
      • slice_scatter
      • sort
      • split
      • sqrt
      • square
      • square_
      • squeeze
      • squeeze_
      • stack
      • standard_gamma
      • standard_normal
      • stanh
      • std
      • strided_slice
      • subtract
      • sum
      • summary
      • t
      • t_
      • take
      • take_along_axis
      • tan
      • tan_
      • tanh
      • tanh_
      • Tensor
      • tensor_split
      • tensordot
      • tile
      • to_dlpack
      • to_tensor
      • tolist
      • topk
      • trace
      • transpose
      • transpose_
      • trapezoid
      • tril
      • tril_
      • tril_indices
      • triu
      • triu_
      • triu_indices
      • trunc
      • trunc_
      • unbind
      • unflatten
      • unfold
      • uniform
      • unique
      • unique_consecutive
      • unsqueeze
      • unsqueeze_
      • unstack
      • vander
      • var
      • vecdot
      • view
      • view_as
      • vsplit
      • vstack
      • where
      • where_
      • zeros
      • zeros_like
    • paddle.amp
      • auto_cast
      • debugging
        • check_layer_numerics
        • check_numerics
        • collect_operator_stats
        • compare_accuracy
        • DebugMode
        • disable_operator_stats_collection
        • disable_tensor_checker
        • enable_operator_stats_collection
        • enable_tensor_checker
        • TensorCheckerConfig
      • decorate
      • GradScaler
      • is_bfloat16_supported
      • is_float16_supported
    • paddle.audio
      • backends
        • get_current_backend
        • list_available_backends
        • set_backend
      • datasets
        • ESC50
        • TESS
      • features
        • LogMelSpectrogram
        • MelSpectrogram
        • MFCC
        • Spectrogram
      • functional
        • compute_fbank_matrix
        • create_dct
        • fft_frequencies
        • get_window
        • hz_to_mel
        • mel_frequencies
        • mel_to_hz
        • power_to_db
      • info
      • load
      • save
    • paddle.autograd
      • backward
      • hessian
      • ir_backward
        • calc_gradient
        • calc_gradient_helper
        • grad
      • jacobian
      • PyLayer
      • PyLayerContext
      • saved_tensors_hooks
    • paddle.callbacks
      • Callback
      • EarlyStopping
      • LRScheduler
      • ModelCheckpoint
      • ProgBarLogger
      • ReduceLROnPlateau
      • VisualDL
      • WandbCallback
    • paddle.device
      • cuda
        • current_stream
        • device_count
        • empty_cache
        • Event
        • get_device_capability
        • get_device_name
        • get_device_properties
        • max_memory_allocated
        • max_memory_reserved
        • memory_allocated
        • memory_reserved
        • reset_max_memory_allocated
        • reset_max_memory_reserved
        • Stream
        • stream_guard
        • synchronize
      • current_stream
      • Event
      • get_all_custom_device_type
      • get_all_device_type
      • get_available_custom_device
      • get_available_device
      • get_cudnn_version
      • get_device
      • IPUPlace
      • is_compiled_with_cinn
      • is_compiled_with_cuda
      • is_compiled_with_custom_device
      • is_compiled_with_distribute
      • is_compiled_with_ipu
      • is_compiled_with_rocm
      • is_compiled_with_xpu
      • set_device
      • set_stream
      • Stream
      • stream_guard
      • synchronize
      • xpu
        • empty_cache
        • synchronize
      • XPUPlace
    • paddle.distributed
      • all_gather
      • all_gather_object
      • all_reduce
      • alltoall
      • alltoall_single
      • barrier
      • broadcast
      • broadcast_object_list
      • ColWiseParallel
      • communication
        • stream
          • all_gather
          • all_reduce
          • alltoall
          • alltoall_single
          • broadcast
          • gather
          • recv
          • reduce
          • reduce_scatter
          • scatter
          • send
      • CountFilterEntry
      • destroy_process_group
      • DistAttr
      • DistModel
      • dtensor_from_fn
      • fleet
        • CommunicateTopology
        • DistributedStrategy
        • Fleet
        • HybridCommunicateGroup
        • MultiSlotDataGenerator
        • MultiSlotStringDataGenerator
        • PaddleCloudRoleMaker
        • Role
        • UserDefinedRoleMaker
        • UtilBase
        • utils
          • DistributedInfer
          • HDFSClient
          • LocalFS
          • recompute
      • gather
      • get_backend
      • get_group
      • get_mesh
      • get_rank
      • get_world_size
      • gloo_barrier
      • gloo_init_parallel_env
      • gloo_release
      • init_parallel_env
      • InMemoryDataset
      • irecv
      • is_available
      • is_initialized
      • isend
      • launch
      • load_state_dict
      • LocalLayer
      • new_group
      • ParallelEnv
      • parallelize
      • ParallelMode
      • Partial
      • passes
        • new_pass
        • PassContext
        • PassManager
      • Placement
      • PrepareLayerInput
      • PrepareLayerOutput
      • ProbabilityEntry
      • ProcessMesh
      • ps
        • the_one_ps
          • BarrierTable
          • DenseTable
          • GeoSparseTable
          • SparseTable
          • Table
          • TensorTable
        • utils
          • ps_factory
            • CpuAsyncPsProgramBuilder
            • CpuSyncPsProgramBuilder
            • FlPsProgramBuilder
            • GeoPsProgramBuilder
            • GpuPsProgramBuilder
            • HeterAsyncPsProgramBuilder
            • NuPsProgramBuilder
            • PsProgramBuilder
      • QueueDataset
      • recv
      • reduce
      • reduce_scatter
      • ReduceOp
      • ReduceType
      • Replicate
      • reshard
      • RowWiseParallel
      • rpc
        • get_all_worker_infos
        • get_current_worker_info
        • get_worker_info
        • init_rpc
        • rpc_async
        • rpc_sync
        • shutdown
      • save_state_dict
      • scatter
      • scatter_object_list
      • send
      • SequenceParallelBegin
      • SequenceParallelDisable
      • SequenceParallelEnable
      • SequenceParallelEnd
      • set_mesh
      • Shard
      • shard_dataloader
      • shard_layer
      • shard_optimizer
      • shard_scaler
      • shard_tensor
      • sharding
        • group_sharded_parallel
        • save_group_sharded_model
      • ShardingStage1
      • ShardingStage2
      • ShardingStage3
      • ShowClickEntry
      • spawn
      • split
      • SplitPoint
      • Strategy
      • to_distributed
      • to_static
      • unshard_dtensor
      • wait
    • paddle.distribution
      • AbsTransform
      • AffineTransform
      • Bernoulli
      • Beta
      • Binomial
      • Categorical
      • Cauchy
      • ChainTransform
      • Chi2
      • ContinuousBernoulli
      • Dirichlet
      • Distribution
      • Exponential
      • ExponentialFamily
      • ExpTransform
      • Gamma
      • Geometric
      • Gumbel
      • Independent
      • IndependentTransform
      • kl_divergence
      • Laplace
      • LKJCholesky
      • LogNormal
      • Multinomial
      • MultivariateNormal
      • Normal
      • Poisson
      • PowerTransform
      • register_kl
      • ReshapeTransform
      • SigmoidTransform
      • SoftmaxTransform
      • StackTransform
      • StickBreakingTransform
      • StudentT
      • TanhTransform
      • Transform
      • TransformedDistribution
      • Uniform
    • paddle.fft
      • fft
      • fft2
      • fftfreq
      • fftn
      • fftshift
      • hfft
      • hfft2
      • hfftn
      • ifft
      • ifft2
      • ifftn
      • ifftshift
      • ihfft
      • ihfft2
      • ihfftn
      • irfft
      • irfft2
      • irfftn
      • rfft
      • rfft2
      • rfftfreq
      • rfftn
    • paddle.geometric
      • reindex_graph
      • reindex_heter_graph
      • sample_neighbors
      • segment_max
      • segment_mean
      • segment_min
      • segment_sum
      • send_u_recv
      • send_ue_recv
      • send_uv
      • weighted_sample_neighbors
    • paddle.hub
      • help
      • list
      • load
      • load_state_dict_from_url
    • paddle.incubate
      • asp
        • add_supported_layer
        • calculate_density
        • decorate
        • prune_model
        • reset_excluded_layers
        • set_excluded_layers
      • autograd
        • disable_prim
        • enable_prim
        • forward_grad
        • grad
        • Hessian
        • Jacobian
        • jvp
        • vjp
      • autotune
        • set_config
      • distributed
        • fleet
          • recompute_hybrid
          • recompute_sequential
        • utils
          • io
            • dist_save
              • save
              • save_for_auto_inference
      • graph_khop_sampler
      • graph_reindex
      • graph_sample_neighbors
      • graph_send_recv
      • identity_loss
      • inference
      • LookAhead
      • ModelAverage
      • nn
        • functional
          • blha_get_max_len
          • block_multihead_attention
          • fused_bias_act
          • fused_bias_dropout_residual_layer_norm
          • fused_dropout_add
          • fused_feedforward
          • fused_layer_norm
          • fused_linear
          • fused_linear_activation
          • fused_matmul_bias
          • fused_moe
          • fused_multi_head_attention
          • fused_multi_transformer
          • fused_rms_norm
          • fused_rotary_position_embedding
          • masked_multihead_attention
          • moe_dispatch
          • moe_ffn
          • moe_reduce
          • swiglu
          • variable_length_memory_efficient_attention
        • FusedBiasDropoutResidualLayerNorm
        • FusedDropoutAdd
        • FusedFeedForward
        • FusedLinear
        • FusedMultiHeadAttention
        • FusedMultiTransformer
        • FusedTransformerEncoderLayer
      • optimizer
        • functional
          • minimize_bfgs
          • minimize_lbfgs
        • LBFGS
      • segment_max
      • segment_mean
      • segment_min
      • segment_sum
      • softmax_mask_fuse
      • softmax_mask_fuse_upper_triangle
      • xpu
        • resnet_block
          • resnet_basic_block
          • ResNetBasicBlock
    • paddle.inference
      • Config
      • convert_to_mixed_precision
      • DataType
      • PlaceType
      • PrecisionType
      • Predictor
      • PredictorPool
      • Tensor
      • XpuConfig
    • paddle.io
      • BatchSampler
      • ChainDataset
      • ComposeDataset
      • ConcatDataset
      • DataLoader
      • Dataset
      • DistributedBatchSampler
      • get_worker_info
      • IterableDataset
      • random_split
      • RandomSampler
      • Sampler
      • SequenceSampler
      • Subset
      • SubsetRandomSampler
      • TensorDataset
      • WeightedRandomSampler
    • paddle.jit
      • enable_to_static
      • ignore_module
      • load
      • not_to_static
      • save
      • set_code_level
      • set_verbosity
      • to_static
      • TranslatedLayer
    • paddle.linalg
      • cholesky
      • cholesky_inverse
      • cholesky_solve
      • cond
      • corrcoef
      • cov
      • det
      • eig
      • eigh
      • eigvals
      • eigvalsh
      • fp8_fp8_half_gemm_fused
      • householder_product
      • inv
      • lstsq
      • lu
      • lu_solve
      • lu_unpack
      • matrix_exp
      • matrix_norm
      • matrix_power
      • matrix_rank
      • multi_dot
      • norm
      • ormqr
      • pca_lowrank
      • pinv
      • qr
      • slogdet
      • solve
      • svd
      • svd_lowrank
      • svdvals
      • triangular_solve
      • vector_norm
    • paddle.metric
      • accuracy
      • Accuracy
      • Auc
      • Metric
      • Precision
      • Recall
    • paddle.nn
      • AdaptiveAvgPool1D
      • AdaptiveAvgPool2D
      • AdaptiveAvgPool3D
      • AdaptiveLogSoftmaxWithLoss
      • AdaptiveMaxPool1D
      • AdaptiveMaxPool2D
      • AdaptiveMaxPool3D
      • AlphaDropout
      • AvgPool1D
      • AvgPool2D
      • AvgPool3D
      • BatchNorm
      • BatchNorm1D
      • BatchNorm2D
      • BatchNorm3D
      • BCELoss
      • BCEWithLogitsLoss
      • BeamSearchDecoder
      • Bilinear
      • BiRNN
      • CELU
      • ChannelShuffle
      • ClipGradByGlobalNorm
      • ClipGradByNorm
      • ClipGradByValue
      • Conv1D
      • Conv1DTranspose
      • Conv2D
      • Conv2DTranspose
      • Conv3D
      • Conv3DTranspose
      • CosineEmbeddingLoss
      • CosineSimilarity
      • CrossEntropyLoss
      • CTCLoss
      • Dropout
      • Dropout2D
      • Dropout3D
      • dynamic_decode
      • ELU
      • Embedding
      • FeatureAlphaDropout
      • Flatten
      • Fold
      • FractionalMaxPool2D
      • FractionalMaxPool3D
      • functional
        • adaptive_avg_pool1d
        • adaptive_avg_pool2d
        • adaptive_avg_pool3d
        • adaptive_log_softmax_with_loss
        • 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
        • celu
        • channel_shuffle
        • class_center_sample
        • conv1d
        • conv1d_transpose
        • conv2d
        • conv2d_transpose
        • conv3d
        • conv3d_transpose
        • cosine_embedding_loss
        • cosine_similarity
        • cross_entropy
        • ctc_loss
        • dice_loss
        • dropout
        • dropout2d
        • dropout3d
        • elu
        • elu_
        • embedding
        • feature_alpha_dropout
        • flash_attn_qkvpacked
        • flash_attn_varlen_qkvpacked
        • flashmask_attention
        • fold
        • fractional_max_pool2d
        • fractional_max_pool3d
        • gather_tree
        • gaussian_nll_loss
        • gelu
        • glu
        • grid_sample
        • group_norm
        • gumbel_softmax
        • hardshrink
        • hardsigmoid
        • hardswish
        • hardtanh
        • hardtanh_
        • hinge_embedding_loss
        • hsigmoid_loss
        • instance_norm
        • interpolate
        • kl_div
        • l1_loss
        • label_smooth
        • layer_norm
        • leaky_relu
        • leaky_relu_
        • linear
        • local_response_norm
        • log_loss
        • log_sigmoid
        • log_softmax
        • lp_pool1d
        • lp_pool2d
        • margin_cross_entropy
        • margin_ranking_loss
        • max_pool1d
        • max_pool2d
        • max_pool3d
        • max_unpool1d
        • max_unpool2d
        • max_unpool3d
        • maxout
        • mish
        • mse_loss
        • multi_label_soft_margin_loss
        • multi_margin_loss
        • nll_loss
        • normalize
        • npair_loss
        • one_hot
        • pad
        • pairwise_distance
        • pixel_shuffle
        • pixel_unshuffle
        • poisson_nll_loss
        • prelu
        • relu
        • relu6
        • relu_
        • rnnt_loss
        • rrelu
        • scaled_dot_product_attention
        • selu
        • sequence_mask
        • sigmoid_focal_loss
        • silu
        • smooth_l1_loss
        • soft_margin_loss
        • softmax
        • softmax_
        • softmax_with_cross_entropy
        • softplus
        • softshrink
        • softsign
        • sparse_attention
        • square_error_cost
        • swish
        • tanhshrink
        • temporal_shift
        • thresholded_relu
        • thresholded_relu_
        • triplet_margin_loss
        • triplet_margin_with_distance_loss
        • unfold
        • upsample
        • zeropad2d
      • GaussianNLLLoss
      • GELU
      • GLU
      • GroupNorm
      • GRU
      • GRUCell
      • Hardshrink
      • Hardsigmoid
      • Hardswish
      • Hardtanh
      • HingeEmbeddingLoss
      • HSigmoidLoss
      • Identity
      • initializer
        • Assign
        • Bilinear
        • calculate_gain
        • Constant
        • Dirac
        • KaimingNormal
        • KaimingUniform
        • Normal
        • Orthogonal
        • set_global_initializer
        • TruncatedNormal
        • Uniform
        • XavierNormal
        • XavierUniform
      • InstanceNorm1D
      • InstanceNorm2D
      • InstanceNorm3D
      • KLDivLoss
      • L1Loss
      • Layer
      • LayerDict
      • LayerList
      • LayerNorm
      • LeakyReLU
      • Linear
      • LocalResponseNorm
      • LogSigmoid
      • LogSoftmax
      • LPPool1D
      • LPPool2D
      • LSTM
      • LSTMCell
      • MarginRankingLoss
      • Maxout
      • MaxPool1D
      • MaxPool2D
      • MaxPool3D
      • MaxUnPool1D
      • MaxUnPool2D
      • MaxUnPool3D
      • Mish
      • MSELoss
      • MultiHeadAttention
      • MultiLabelSoftMarginLoss
      • MultiMarginLoss
      • NLLLoss
      • Pad1D
      • Pad2D
      • Pad3D
      • PairwiseDistance
      • ParameterDict
      • ParameterList
      • PixelShuffle
      • PixelUnshuffle
      • PoissonNLLLoss
      • PReLU
      • quant
        • llm_int8_linear
        • quant_layers
          • FakeQuantAbsMax
          • FakeQuantChannelWiseAbsMax
          • FakeQuantMAOutputScaleLayer
          • FakeQuantMovingAverageAbsMax
          • MAOutputScaleLayer
          • MovingAverageAbsMaxScale
          • QuantizedColumnParallelLinear
          • QuantizedConv2D
          • QuantizedConv2DTranspose
          • QuantizedLinear
          • QuantizedMatmul
          • QuantizedRowParallelLinear
        • Stub
        • weight_dequantize
        • weight_only_linear
        • weight_quantize
      • ReLU
      • ReLU6
      • RNN
      • RNNCellBase
      • RNNTLoss
      • RReLU
      • SELU
      • Sequential
      • Sigmoid
      • Silu
      • SimpleRNN
      • SimpleRNNCell
      • SmoothL1Loss
      • SoftMarginLoss
      • Softmax
      • Softmax2D
      • Softplus
      • Softshrink
      • Softsign
      • SpectralNorm
      • Swish
      • SyncBatchNorm
      • Tanh
      • Tanhshrink
      • ThresholdedReLU
      • Transformer
      • TransformerDecoder
      • TransformerDecoderLayer
      • TransformerEncoder
      • TransformerEncoderLayer
      • TripletMarginLoss
      • TripletMarginWithDistanceLoss
      • Unflatten
      • Unfold
      • Upsample
      • UpsamplingBilinear2D
      • UpsamplingNearest2D
      • utils
        • clip_grad_norm_
        • clip_grad_value_
        • parameters_to_vector
        • remove_weight_norm
        • spectral_norm
        • vector_to_parameters
        • weight_norm
      • ZeroPad1D
      • ZeroPad2D
      • ZeroPad3D
    • paddle.onnx
      • export
    • paddle.optimizer
      • Adadelta
      • Adagrad
      • Adam
      • Adamax
      • AdamW
      • ASGD
      • Lamb
      • LBFGS
      • lr
        • CosineAnnealingDecay
        • CosineAnnealingWarmRestarts
        • CyclicLR
        • ExponentialDecay
        • InverseTimeDecay
        • LambdaDecay
        • LinearLR
        • LinearWarmup
        • LRScheduler
        • MultiplicativeDecay
        • MultiStepDecay
        • NaturalExpDecay
        • NoamDecay
        • OneCycleLR
        • PiecewiseDecay
        • PolynomialDecay
        • ReduceOnPlateau
        • StepDecay
      • Momentum
      • NAdam
      • Optimizer
      • RAdam
      • RMSProp
      • Rprop
      • SGD
    • paddle.profiler
      • export_chrome_tracing
      • export_protobuf
      • load_profiler_result
      • make_scheduler
      • Profiler
      • ProfilerState
      • ProfilerTarget
      • RecordEvent
      • SortedKeys
      • SummaryView
    • paddle.quantization
      • BaseObserver
      • BaseQuanter
      • PTQ
      • QAT
      • QuantConfig
      • quanter
    • paddle.regularizer
      • L1Decay
      • L2Decay
    • paddle.signal
      • istft
      • stft
    • paddle.sparse
      • abs
      • add
      • addmm
      • asin
      • asinh
      • atan
      • atanh
      • cast
      • coalesce
      • deg2rad
      • divide
      • expm1
      • is_same_shape
      • isnan
      • log1p
      • mask_as
      • masked_matmul
      • matmul
      • multiply
      • mv
      • neg
      • nn
        • BatchNorm
        • Conv2D
        • Conv3D
        • functional
          • attention
          • conv2d
          • conv3d
          • leaky_relu
          • max_pool3d
          • relu
          • relu6
          • softmax
          • subm_conv2d
          • subm_conv2d_igemm
          • subm_conv3d
          • subm_conv3d_igemm
        • LeakyReLU
        • MaxPool3D
        • ReLU
        • ReLU6
        • Softmax
        • SubmConv2D
        • SubmConv3D
        • SyncBatchNorm
      • pca_lowrank
      • pow
      • rad2deg
      • reshape
      • sin
      • sinh
      • slice
      • sparse_coo_tensor
      • sparse_csr_tensor
      • sqrt
      • square
      • subtract
      • sum
      • tan
      • tanh
      • transpose
    • paddle.static
      • accuracy
      • append_backward
      • auc
      • BuildStrategy
      • CompiledProgram
      • cpu_places
      • create_global_var
      • ctr_metric_bundle
      • cuda_places
      • data
      • default_main_program
      • default_startup_program
      • deserialize_persistables
      • deserialize_program
      • device_guard
      • Executor
      • ExponentialMovingAverage
      • global_scope
      • gradients
      • InputSpec
      • ipu_shard_guard
      • IpuCompiledProgram
      • IpuStrategy
      • load
      • load_from_file
      • load_inference_model
      • load_program_state
      • name_scope
      • nn
        • batch_norm
        • bilinear_tensor_product
        • case
        • cond
        • conv2d
        • conv2d_transpose
        • conv3d
        • conv3d_transpose
        • data_norm
        • deform_conv2d
        • embedding
        • fc
        • group_norm
        • instance_norm
        • layer_norm
        • nce
        • prelu
        • row_conv
        • sequence_conv
        • sequence_expand
        • sequence_first_step
        • sequence_last_step
        • sequence_pool
        • sequence_softmax
        • sparse_embedding
        • spectral_norm
        • static_pylayer
        • switch_case
        • while_loop
      • normalize_program
      • Print
      • Program
      • program_guard
      • py_func
      • save
      • save_inference_model
      • save_to_file
      • scope_guard
      • serialize_persistables
      • serialize_program
      • set_ipu_shard
      • set_program_state
      • Variable
      • WeightNormParamAttr
      • xpu_places
    • paddle.sysconfig
      • get_include
      • get_lib
    • paddle.Tensor
      • Overview
      • acosh_
      • add_
      • apply
      • apply_
      • asin_
      • asinh_
      • astype
      • atanh_
      • backward
      • ceil_
      • clear_grad
      • clip_
      • coalesce
      • cosh_
      • cpu
      • create_tensor
      • cuda
      • dim
      • erfinv_
      • exp_
      • exponential_
      • fill_
      • fill_diagonal_
      • fill_diagonal_tensor
      • fill_diagonal_tensor_
      • floor_
      • gradient
      • item
      • lerp_
      • log1p_
      • logical_xor_
      • ndimension
      • not_equal_
      • pin_memory
      • put_along_axis_
      • reciprocal_
      • register_hook
      • resize_
      • round_
      • rsqrt_
      • scale_
      • set_
      • set_value
      • sigmoid
      • sigmoid_
      • sqrt_
      • subtract_
      • to
      • to_dense
      • to_sparse_coo
      • top_p_sampling
      • uniform_
      • value
      • values
      • zero_
    • paddle.text
      • Conll05st
      • Imdb
      • Imikolov
      • Movielens
      • UCIHousing
      • viterbi_decode
      • ViterbiDecoder
      • WMT14
      • WMT16
    • paddle.utils
      • cpp_extension
        • CppExtension
        • CUDAExtension
        • get_build_directory
        • load
        • setup
      • deprecated
      • download
        • get_weights_path_from_url
      • require_version
      • run_check
      • try_import
      • unique_name
        • generate
        • guard
        • switch
    • paddle.version
      • cuda
      • cuda_archs
      • cudnn
      • nccl
      • show
      • tensorrt
      • xpu
      • xpu_xccl
      • xpu_xhpc
      • xpu_xre
    • paddle.vision
      • datasets
        • Cifar10
        • Cifar100
        • DatasetFolder
        • FashionMNIST
        • Flowers
        • ImageFolder
        • MNIST
        • VOC2012
      • get_image_backend
      • image_load
      • models
        • AlexNet
        • alexnet
        • DenseNet
        • densenet121
        • densenet161
        • densenet169
        • densenet201
        • densenet264
        • googlenet
        • GoogLeNet
        • inception_v3
        • InceptionV3
        • LeNet
        • mobilenet_v1
        • mobilenet_v2
        • mobilenet_v3_large
        • mobilenet_v3_small
        • MobileNetV1
        • MobileNetV2
        • MobileNetV3Large
        • MobileNetV3Small
        • ResNet
        • resnet101
        • resnet152
        • resnet18
        • resnet34
        • resnet50
        • resnext101_32x4d
        • resnext101_64x4d
        • resnext152_32x4d
        • resnext152_64x4d
        • resnext50_32x4d
        • resnext50_64x4d
        • shufflenet_v2_swish
        • shufflenet_v2_x0_25
        • shufflenet_v2_x0_33
        • shufflenet_v2_x0_5
        • shufflenet_v2_x1_0
        • shufflenet_v2_x1_5
        • shufflenet_v2_x2_0
        • ShuffleNetV2
        • SqueezeNet
        • squeezenet1_0
        • squeezenet1_1
        • VGG
        • vgg11
        • vgg13
        • vgg16
        • vgg19
        • wide_resnet101_2
        • wide_resnet50_2
      • ops
        • box_coder
        • decode_jpeg
        • deform_conv2d
        • DeformConv2D
        • distribute_fpn_proposals
        • generate_proposals
        • matrix_nms
        • nms
        • prior_box
        • psroi_pool
        • PSRoIPool
        • read_file
        • roi_align
        • roi_pool
        • RoIAlign
        • RoIPool
        • yolo_box
        • yolo_loss
      • set_image_backend
      • transforms
        • adjust_brightness
        • adjust_contrast
        • adjust_hue
        • affine
        • BaseTransform
        • BrightnessTransform
        • center_crop
        • CenterCrop
        • ColorJitter
        • Compose
        • ContrastTransform
        • crop
        • erase
        • Grayscale
        • hflip
        • HueTransform
        • Normalize
        • normalize
        • Pad
        • pad
        • perspective
        • RandomAffine
        • RandomCrop
        • RandomErasing
        • RandomHorizontalFlip
        • RandomPerspective
        • RandomResizedCrop
        • RandomRotation
        • RandomVerticalFlip
        • Resize
        • resize
        • rotate
        • SaturationTransform
        • to_grayscale
        • to_tensor
        • ToTensor
        • Transpose
        • vflip
  • Contribution Guidelines
    • Kernel Primitive API
      • API Description
        • API Description - IO
        • API Description - Compute
        • API Description - OpFunc
      • API Examples
        • ElementwiseAdd
        • Reduce
        • Model
    • Custom Device Support
      • Custom Runtime
        • Data Type
        • Device APIs
        • Memory APIs
        • Stream APIs
        • Event APIs
      • Custom Kernel
        • Kernel Function Declaration
        • Kernel Implementation APIs
          • Context APIs
          • Tensor APIs
          • Exception API
        • Kernel Registration API
      • CustomDevice Example
  • 3.0 Release Note
  • Neural Network Layer
  • »
  • Neural Network Layer
  • Edit on GitHub

Neural Network Layer¶

  • Activation Function
  • Control Flow
  • Convolution
  • Learning rate scheduler
  • Loss function
  • Pooling
  • Sparse update