Guide
Quick search
code
Show Source
D2L Book GitHub
deepnumpy
Table Of Contents
  • Guide
    • Getting started with NP on MXNet
      • Step 1: Manipulate data with NP on MXNet
      • Step 2: Create a neural network
      • Step 3: Automatic differentiation with autograd
      • Step 4: Train the neural network
      • Step 5: Predict with a pretrained model
      • Step 6: Use GPUs to increase efficiency
    • What is NP on MXNet
  • API
    • NP on MXNet reference
      • Array objects
        • The N-dimensional array (ndarray)
          • ndarray
          • ndarray.shape
          • ndarray.ndim
          • ndarray.size
          • ndarray.dtype
          • ndarray.T
          • ndarray.item
          • ndarray.copy
          • ndarray.tolist
          • ndarray.astype
          • ndarray.reshape
          • ndarray.transpose
          • ndarray.swapaxes
          • ndarray.flatten
          • ndarray.squeeze
          • ndarray.nonzero
          • ndarray.take
          • ndarray.repeat
          • ndarray.max
          • ndarray.argmax
          • ndarray.min
          • ndarray.argmin
          • ndarray.clip
          • ndarray.sum
          • ndarray.mean
          • ndarray.prod
          • ndarray.cumsum
          • ndarray.var
          • ndarray.std
          • ndarray.__lt__
          • ndarray.__le__
          • ndarray.__gt__
          • ndarray.__ge__
          • ndarray.__eq__
          • ndarray.__ne__
          • ndarray.__bool__
          • ndarray.__neg__
          • ndarray.__add__
          • ndarray.__sub__
          • ndarray.__mul__
          • ndarray.__truediv__
          • ndarray.__mod__
          • ndarray.__pow__
          • ndarray.__iadd__
          • ndarray.__isub__
          • ndarray.__imul__
          • ndarray.__itruediv__
          • ndarray.__imod__
          • ndarray.__reduce__
          • ndarray.__setstate__
          • ndarray.__len__
          • ndarray.__getitem__
          • ndarray.__setitem__
          • ndarray.__int__
          • ndarray.__float__
          • ndarray.__str__
          • ndarray.__repr__
        • Indexing
      • Routines
        • Array creation routines
          • eye
          • empty
          • full
          • identity
          • ones
          • ones_like
          • zeros
          • zeros_like
          • array
          • copy
          • arange
          • linspace
          • logspace
          • meshgrid
          • tril
        • Array manipulation routines
          • reshape
          • ravel
          • ndarray.flatten
          • swapaxes
          • ndarray.T
          • transpose
          • moveaxis
          • expand_dims
          • squeeze
          • broadcast_to
          • broadcast_arrays
          • concatenate
          • stack
          • dstack
          • vstack
          • split
          • hsplit
          • vsplit
          • tile
          • repeat
          • unique
          • reshape
          • flip
          • roll
          • rot90
        • Input and output
          • genfromtxt
        • Linear algebra (numpy.linalg)
          • dot
          • vdot
          • inner
          • outer
          • tensordot
          • einsum
          • svd
          • norm
          • trace
        • Mathematical functions
          • sin
          • cos
          • tan
          • arcsin
          • arccos
          • arctan
          • degrees
          • radians
          • hypot
          • arctan2
          • deg2rad
          • rad2deg
          • sinh
          • cosh
          • tanh
          • arcsinh
          • arccosh
          • arctanh
          • rint
          • fix
          • floor
          • ceil
          • trunc
          • around
          • sum
          • prod
          • cumsum
          • exp
          • expm1
          • log
          • log10
          • log2
          • log1p
          • ldexp
          • lcm
          • add
          • reciprocal
          • negative
          • divide
          • power
          • subtract
          • mod
          • multiply
          • true_divide
          • remainder
          • clip
          • sqrt
          • cbrt
          • square
          • absolute
          • sign
          • maximum
          • minimum
        • np.random
          • choice
          • shuffle
          • normal
          • uniform
          • rand
          • randint
        • Sorting, searching, and counting
          • argmax
          • argmin
        • Statistics
          • min
          • max
          • mean
          • std
          • var
          • histogram
      • NP Extensions
        • set_np
        • reset_np
        • cpu
        • cpu_pinned
        • gpu
        • gpu_memory_info
        • current_context
        • num_gpus
        • activation
        • batch_norm
        • convolution
        • dropout
        • embedding
        • fully_connected
        • layer_norm
        • pooling
        • rnn
        • leaky_relu
        • multibox_detection
        • multibox_prior
        • multibox_target
        • roi_pooling
        • sigmoid
        • smooth_l1
        • softmax
        • mxnet.npx.threading
        • topk
        • waitall
        • load
        • save
        • one_hot
        • pick
        • reshape_like
        • batch_flatten
        • batch_dot
        • gamma
        • sequence_mask
    • Gluon reference
      • Creating Nerual Networks
        • Block objects
          • Block
          • Block.forward
          • Block.__call__
          • Block.initialize
          • Block.save_parameters
          • Block.load_parameters
          • Block.collect_params
          • Block.cast
          • Block.apply
          • Block.summary
          • Block.name_scope
          • Block.register_child
          • Block.register_forward_hook
          • Block.register_forward_pre_hook
          • Block.name
          • Block.params
          • Block.prefix
          • Block.save_params
          • Block.load_params
          • HybridBlock
          • HybridBlock.hybridize
          • HybridBlock.hybrid_forward
          • SymbolBlock
        • Container objects
          • Sequential
          • HybridSequential
          • Concurrent
          • HybridConcurrent
        • Feedforward Layers
          • Dense
          • Activation
          • Dropout
          • Flatten
          • Lambda
          • HybridLambda
          • Conv1D
          • Conv2D
          • Conv3D
          • Conv1DTranspose
          • Conv2DTranspose
          • Conv3DTranspose
          • MaxPool1D
          • MaxPool2D
          • MaxPool3D
          • AvgPool1D
          • AvgPool2D
          • AvgPool3D
          • GlobalMaxPool1D
          • GlobalMaxPool2D
          • GlobalMaxPool3D
          • GlobalAvgPool1D
          • GlobalAvgPool2D
          • GlobalAvgPool3D
          • ReflectionPad2D
          • BatchNorm
          • InstanceNorm
          • LayerNorm
          • SyncBatchNorm
          • Embedding
          • SparseEmbedding
          • LeakyReLU
          • PReLU
          • ELU
          • SELU
          • Swish
        • Recurrent Layers
          • LSTMCell
          • GRUCell
          • RecurrentCell
          • SequentialRNNCell
          • BidirectionalCell
          • DropoutCell
          • ZoneoutCell
          • ResidualCell
          • Conv1DRNNCell
          • Conv2DRNNCell
          • Conv3DRNNCell
          • Conv1DLSTMCell
          • Conv2DLSTMCell
          • Conv3DLSTMCell
          • Conv1DGRUCell
          • Conv2DGRUCell
          • Conv3DGRUCell
          • VariationalDropoutCell
          • LSTMPCell
          • RNN
          • LSTM
          • GRU
      • Parameters
        • Parameter
          • Parameter.initialize
          • Parameter.data
          • Parameter.list_data
          • Parameter.list_row_sparse_data
          • Parameter.row_sparse_data
          • Parameter.set_data
          • Parameter.shape
          • Parameter.grad
          • Parameter.list_grad
          • Parameter.zero_grad
          • Parameter.grad_req
          • Parameter.cast
          • Parameter.list_ctx
          • Parameter.reset_ctx
          • Parameter.var
        • ParameterDict
          • ParameterDict.load
          • ParameterDict.save
          • ParameterDict.get
          • ParameterDict.get_constant
          • ParameterDict.items
          • ParameterDict.keys
          • ParameterDict.values
          • ParameterDict.initialize
          • ParameterDict.setattr
          • ParameterDict.update
          • ParameterDict.reset_ctx
          • ParameterDict.zero_grad
          • ParameterDict.prefix
        • mxnet.initializer
          • Bilinear
          • Constant
          • FusedRNN
          • InitDesc
          • Initializer
          • LSTMBias
          • Load
          • MSRAPrelu
          • Mixed
          • Normal
          • One
          • Orthogonal
          • Uniform
          • Xavier
          • Zero
          • register
      • Loss functions
        • Loss
        • L2Loss
        • L1Loss
        • SigmoidBinaryCrossEntropyLoss
        • SoftmaxCrossEntropyLoss
        • KLDivLoss
        • HuberLoss
        • HingeLoss
        • SquaredHingeLoss
        • LogisticLoss
        • TripletLoss
        • CTCLoss
      • Training
        • Trainer
          • Trainer.step
          • Trainer.allreduce_grads
          • Trainer.update
          • Trainer.load_states
          • Trainer.save_states
          • Trainer.learning_rate
          • Trainer.set_learning_rate
        • mxnet.autograd
          • backward
          • get_symbol
          • grad
          • is_recording
          • is_training
          • mark_variables
          • pause
          • predict_mode
          • record
          • set_recording
          • set_training
          • train_mode
          • Function
        • mxnet.optimizer
          • AdaDelta
          • AdaGrad
          • Adam
          • Adamax
          • DCASGD
          • FTML
          • Ftrl
          • LBSGD
          • NAG
          • Nadam
          • Optimizer
          • RMSProp
          • SGD
          • SGLD
          • Signum
          • Updater
        • mxnet.lr_scheduler
          • LRScheduler
          • FactorScheduler
          • MultiFactorScheduler
          • PolyScheduler
          • CosineScheduler
      • Loading Data
        • Dataset
        • ArrayDataset
        • RecordFileDataset
        • Sampler
        • SequentialSampler
        • RandomSampler
        • BatchSampler
        • DataLoader
      • Model Zoo
        • get_model
        • resnet18_v1
        • resnet34_v1
        • resnet50_v1
        • resnet101_v1
        • resnet152_v1
        • resnet18_v2
        • resnet34_v2
        • resnet50_v2
        • resnet101_v2
        • resnet152_v2
        • ResNetV1
        • ResNetV2
        • BasicBlockV1
        • BasicBlockV2
        • BottleneckV1
        • BottleneckV2
        • get_resnet
        • vgg11
        • vgg13
        • vgg16
        • vgg19
        • vgg11_bn
        • vgg13_bn
        • vgg16_bn
        • vgg19_bn
        • VGG
        • get_vgg
        • AlexNet
        • densenet121
        • densenet161
        • densenet169
        • densenet201
        • DenseNet
        • squeezenet1_0
        • squeezenet1_1
        • SqueezeNet
        • inception_v3
        • Inception3
        • mobilenet1_0
        • mobilenet0_75
        • mobilenet0_5
        • mobilenet0_25
        • mobilenet_v2_1_0
        • mobilenet_v2_0_75
        • mobilenet_v2_0_5
        • mobilenet_v2_0_25
        • MobileNet
        • MobileNetV2
      • Utility functions
        • split_data
        • split_and_load
        • clip_global_norm
        • download
        • check_sha1
deepnumpy
Table Of Contents
  • Guide
    • Getting started with NP on MXNet
      • Step 1: Manipulate data with NP on MXNet
      • Step 2: Create a neural network
      • Step 3: Automatic differentiation with autograd
      • Step 4: Train the neural network
      • Step 5: Predict with a pretrained model
      • Step 6: Use GPUs to increase efficiency
    • What is NP on MXNet
  • API
    • NP on MXNet reference
      • Array objects
        • The N-dimensional array (ndarray)
          • ndarray
          • ndarray.shape
          • ndarray.ndim
          • ndarray.size
          • ndarray.dtype
          • ndarray.T
          • ndarray.item
          • ndarray.copy
          • ndarray.tolist
          • ndarray.astype
          • ndarray.reshape
          • ndarray.transpose
          • ndarray.swapaxes
          • ndarray.flatten
          • ndarray.squeeze
          • ndarray.nonzero
          • ndarray.take
          • ndarray.repeat
          • ndarray.max
          • ndarray.argmax
          • ndarray.min
          • ndarray.argmin
          • ndarray.clip
          • ndarray.sum
          • ndarray.mean
          • ndarray.prod
          • ndarray.cumsum
          • ndarray.var
          • ndarray.std
          • ndarray.__lt__
          • ndarray.__le__
          • ndarray.__gt__
          • ndarray.__ge__
          • ndarray.__eq__
          • ndarray.__ne__
          • ndarray.__bool__
          • ndarray.__neg__
          • ndarray.__add__
          • ndarray.__sub__
          • ndarray.__mul__
          • ndarray.__truediv__
          • ndarray.__mod__
          • ndarray.__pow__
          • ndarray.__iadd__
          • ndarray.__isub__
          • ndarray.__imul__
          • ndarray.__itruediv__
          • ndarray.__imod__
          • ndarray.__reduce__
          • ndarray.__setstate__
          • ndarray.__len__
          • ndarray.__getitem__
          • ndarray.__setitem__
          • ndarray.__int__
          • ndarray.__float__
          • ndarray.__str__
          • ndarray.__repr__
        • Indexing
      • Routines
        • Array creation routines
          • eye
          • empty
          • full
          • identity
          • ones
          • ones_like
          • zeros
          • zeros_like
          • array
          • copy
          • arange
          • linspace
          • logspace
          • meshgrid
          • tril
        • Array manipulation routines
          • reshape
          • ravel
          • ndarray.flatten
          • swapaxes
          • ndarray.T
          • transpose
          • moveaxis
          • expand_dims
          • squeeze
          • broadcast_to
          • broadcast_arrays
          • concatenate
          • stack
          • dstack
          • vstack
          • split
          • hsplit
          • vsplit
          • tile
          • repeat
          • unique
          • reshape
          • flip
          • roll
          • rot90
        • Input and output
          • genfromtxt
        • Linear algebra (numpy.linalg)
          • dot
          • vdot
          • inner
          • outer
          • tensordot
          • einsum
          • svd
          • norm
          • trace
        • Mathematical functions
          • sin
          • cos
          • tan
          • arcsin
          • arccos
          • arctan
          • degrees
          • radians
          • hypot
          • arctan2
          • deg2rad
          • rad2deg
          • sinh
          • cosh
          • tanh
          • arcsinh
          • arccosh
          • arctanh
          • rint
          • fix
          • floor
          • ceil
          • trunc
          • around
          • sum
          • prod
          • cumsum
          • exp
          • expm1
          • log
          • log10
          • log2
          • log1p
          • ldexp
          • lcm
          • add
          • reciprocal
          • negative
          • divide
          • power
          • subtract
          • mod
          • multiply
          • true_divide
          • remainder
          • clip
          • sqrt
          • cbrt
          • square
          • absolute
          • sign
          • maximum
          • minimum
        • np.random
          • choice
          • shuffle
          • normal
          • uniform
          • rand
          • randint
        • Sorting, searching, and counting
          • argmax
          • argmin
        • Statistics
          • min
          • max
          • mean
          • std
          • var
          • histogram
      • NP Extensions
        • set_np
        • reset_np
        • cpu
        • cpu_pinned
        • gpu
        • gpu_memory_info
        • current_context
        • num_gpus
        • activation
        • batch_norm
        • convolution
        • dropout
        • embedding
        • fully_connected
        • layer_norm
        • pooling
        • rnn
        • leaky_relu
        • multibox_detection
        • multibox_prior
        • multibox_target
        • roi_pooling
        • sigmoid
        • smooth_l1
        • softmax
        • mxnet.npx.threading
        • topk
        • waitall
        • load
        • save
        • one_hot
        • pick
        • reshape_like
        • batch_flatten
        • batch_dot
        • gamma
        • sequence_mask
    • Gluon reference
      • Creating Nerual Networks
        • Block objects
          • Block
          • Block.forward
          • Block.__call__
          • Block.initialize
          • Block.save_parameters
          • Block.load_parameters
          • Block.collect_params
          • Block.cast
          • Block.apply
          • Block.summary
          • Block.name_scope
          • Block.register_child
          • Block.register_forward_hook
          • Block.register_forward_pre_hook
          • Block.name
          • Block.params
          • Block.prefix
          • Block.save_params
          • Block.load_params
          • HybridBlock
          • HybridBlock.hybridize
          • HybridBlock.hybrid_forward
          • SymbolBlock
        • Container objects
          • Sequential
          • HybridSequential
          • Concurrent
          • HybridConcurrent
        • Feedforward Layers
          • Dense
          • Activation
          • Dropout
          • Flatten
          • Lambda
          • HybridLambda
          • Conv1D
          • Conv2D
          • Conv3D
          • Conv1DTranspose
          • Conv2DTranspose
          • Conv3DTranspose
          • MaxPool1D
          • MaxPool2D
          • MaxPool3D
          • AvgPool1D
          • AvgPool2D
          • AvgPool3D
          • GlobalMaxPool1D
          • GlobalMaxPool2D
          • GlobalMaxPool3D
          • GlobalAvgPool1D
          • GlobalAvgPool2D
          • GlobalAvgPool3D
          • ReflectionPad2D
          • BatchNorm
          • InstanceNorm
          • LayerNorm
          • SyncBatchNorm
          • Embedding
          • SparseEmbedding
          • LeakyReLU
          • PReLU
          • ELU
          • SELU
          • Swish
        • Recurrent Layers
          • LSTMCell
          • GRUCell
          • RecurrentCell
          • SequentialRNNCell
          • BidirectionalCell
          • DropoutCell
          • ZoneoutCell
          • ResidualCell
          • Conv1DRNNCell
          • Conv2DRNNCell
          • Conv3DRNNCell
          • Conv1DLSTMCell
          • Conv2DLSTMCell
          • Conv3DLSTMCell
          • Conv1DGRUCell
          • Conv2DGRUCell
          • Conv3DGRUCell
          • VariationalDropoutCell
          • LSTMPCell
          • RNN
          • LSTM
          • GRU
      • Parameters
        • Parameter
          • Parameter.initialize
          • Parameter.data
          • Parameter.list_data
          • Parameter.list_row_sparse_data
          • Parameter.row_sparse_data
          • Parameter.set_data
          • Parameter.shape
          • Parameter.grad
          • Parameter.list_grad
          • Parameter.zero_grad
          • Parameter.grad_req
          • Parameter.cast
          • Parameter.list_ctx
          • Parameter.reset_ctx
          • Parameter.var
        • ParameterDict
          • ParameterDict.load
          • ParameterDict.save
          • ParameterDict.get
          • ParameterDict.get_constant
          • ParameterDict.items
          • ParameterDict.keys
          • ParameterDict.values
          • ParameterDict.initialize
          • ParameterDict.setattr
          • ParameterDict.update
          • ParameterDict.reset_ctx
          • ParameterDict.zero_grad
          • ParameterDict.prefix
        • mxnet.initializer
          • Bilinear
          • Constant
          • FusedRNN
          • InitDesc
          • Initializer
          • LSTMBias
          • Load
          • MSRAPrelu
          • Mixed
          • Normal
          • One
          • Orthogonal
          • Uniform
          • Xavier
          • Zero
          • register
      • Loss functions
        • Loss
        • L2Loss
        • L1Loss
        • SigmoidBinaryCrossEntropyLoss
        • SoftmaxCrossEntropyLoss
        • KLDivLoss
        • HuberLoss
        • HingeLoss
        • SquaredHingeLoss
        • LogisticLoss
        • TripletLoss
        • CTCLoss
      • Training
        • Trainer
          • Trainer.step
          • Trainer.allreduce_grads
          • Trainer.update
          • Trainer.load_states
          • Trainer.save_states
          • Trainer.learning_rate
          • Trainer.set_learning_rate
        • mxnet.autograd
          • backward
          • get_symbol
          • grad
          • is_recording
          • is_training
          • mark_variables
          • pause
          • predict_mode
          • record
          • set_recording
          • set_training
          • train_mode
          • Function
        • mxnet.optimizer
          • AdaDelta
          • AdaGrad
          • Adam
          • Adamax
          • DCASGD
          • FTML
          • Ftrl
          • LBSGD
          • NAG
          • Nadam
          • Optimizer
          • RMSProp
          • SGD
          • SGLD
          • Signum
          • Updater
        • mxnet.lr_scheduler
          • LRScheduler
          • FactorScheduler
          • MultiFactorScheduler
          • PolyScheduler
          • CosineScheduler
      • Loading Data
        • Dataset
        • ArrayDataset
        • RecordFileDataset
        • Sampler
        • SequentialSampler
        • RandomSampler
        • BatchSampler
        • DataLoader
      • Model Zoo
        • get_model
        • resnet18_v1
        • resnet34_v1
        • resnet50_v1
        • resnet101_v1
        • resnet152_v1
        • resnet18_v2
        • resnet34_v2
        • resnet50_v2
        • resnet101_v2
        • resnet152_v2
        • ResNetV1
        • ResNetV2
        • BasicBlockV1
        • BasicBlockV2
        • BottleneckV1
        • BottleneckV2
        • get_resnet
        • vgg11
        • vgg13
        • vgg16
        • vgg19
        • vgg11_bn
        • vgg13_bn
        • vgg16_bn
        • vgg19_bn
        • VGG
        • get_vgg
        • AlexNet
        • densenet121
        • densenet161
        • densenet169
        • densenet201
        • DenseNet
        • squeezenet1_0
        • squeezenet1_1
        • SqueezeNet
        • inception_v3
        • Inception3
        • mobilenet1_0
        • mobilenet0_75
        • mobilenet0_5
        • mobilenet0_25
        • mobilenet_v2_1_0
        • mobilenet_v2_0_75
        • mobilenet_v2_0_5
        • mobilenet_v2_0_25
        • MobileNet
        • MobileNetV2
      • Utility functions
        • split_data
        • split_and_load
        • clip_global_norm
        • download
        • check_sha1

GuideΒΆ

  • Getting started with NP on MXNet
  • What is NP on MXNet
Previous
Apache MXNet (incubating) documents
Next
Getting started with NP on MXNet