NP Extensions¶
Compatibility¶
set_np([shape, array]) |
Setting NumPy shape and array semantics at the same time. |
reset_np() |
Deactivate NumPy shape and array semantics at the same time. |
is_np_array
use_np_array
is_np_shape
use_np_shape
np_array
np_shape
Devices¶
cpu([device_id]) |
Returns a CPU context. |
cpu_pinned([device_id]) |
Returns a CPU pinned memory context. |
gpu([device_id]) |
Returns a GPU context. |
gpu_memory_info([device_id]) |
Query CUDA for the free and total bytes of GPU global memory. |
current_context() |
Returns the current context. |
num_gpus() |
Query CUDA for the number of GPUs present. |
Nerual networks¶
activation([data, act_type, out, name]) |
Applies an activation function element-wise to the input. |
batch_norm([data, gamma, beta, moving_mean, …]) |
Batch normalization. |
convolution([data, weight, bias, kernel, …]) |
Compute N-D convolution on (N+2)-D input. |
dropout([data, p, mode, axes, cudnn_off, …]) |
Applies dropout operation to input array. |
embedding([data, weight, input_dim, …]) |
Maps integer indices to vector representations (embeddings). |
fully_connected([data, weight, bias, …]) |
Applies a linear transformation: \(Y = XW^T + b\). |
layer_norm([data, gamma, beta, axis, eps, …]) |
Layer normalization. |
pooling([data, kernel, pool_type, …]) |
Performs pooling on the input. |
rnn([data, parameters, state, state_cell, …]) |
Applies recurrent layers to input data. |
leaky_relu([data, gamma, act_type, slope, …]) |
Applies Leaky rectified linear unit activation element-wise to the input. |
multibox_detection([cls_prob, loc_pred, …]) |
Convert multibox detection predictions. |
multibox_prior([data, sizes, ratios, clip, …]) |
Generate prior(anchor) boxes from data, sizes and ratios. |
multibox_target([anchor, label, cls_pred, …]) |
Compute Multibox training targets |
roi_pooling([data, rois, pooled_size, …]) |
Performs region of interest(ROI) pooling on the input array. |
More operators¶
sigmoid([data, out, name]) |
Computes sigmoid of x element-wise. |
smooth_l1([data, scalar, out, name]) |
Calculate Smooth L1 Loss(lhs, scalar) by summing |
softmax([data, length, axis, temperature, …]) |
Applies the softmax function. |
threading |
Thread module emulating a subset of Java’s threading model. |
topk([data, axis, k, ret_typ, is_ascend, …]) |
Returns the indices of the top k elements in an input array along the given |
waitall() |
Wait for all async operations to finish in MXNet. |
load(file) |
Loads an array from file. |
save(file, arr) |
Saves a list of ndarray`s or a dict of `str->`ndarray` to file. |
one_hot([indices, depth, on_value, …]) |
Returns a one-hot array. |
pick([data, index, axis, keepdims, mode, …]) |
Picks elements from an input array according to the input indices along the given axis. |
reshape_like([lhs, rhs, lhs_begin, lhs_end, …]) |
Reshape some or all dimensions of lhs to have the same shape as some or all dimensions of rhs. |
batch_flatten([data, out, name]) |
Flattens the input array into a 2-D array by collapsing the higher dimensions. |
batch_dot([lhs, rhs, transpose_a, …]) |
Batchwise dot product. |
gamma([data, out, name]) |
Returns the gamma function (extension of the factorial function to the reals), computed element-wise on the input array. |
sequence_mask([data, sequence_length, …]) |
Sets all elements outside the sequence to a constant value. |
seed