NPX: NumPy Neural Network Extension¶
Compatibility¶
|
Setting NumPy shape and array semantics at the same time. |
|
Deactivate NumPy shape and array and deafult dtype semantics at the same time. |
is_np_array
use_np_array
is_np_shape
use_np_shape
np_array
np_shape
Devices¶
|
Returns a CPU device. |
|
Returns a CPU pinned memory device. |
|
Returns a GPU device. |
|
Query CUDA for the free and total bytes of GPU global memory. |
Returns the current device. |
|
|
Query CUDA for the number of GPUs present. |
Nerual networks¶
|
Applies an activation function element-wise to the input. |
|
Batch normalization. |
|
Compute N-D convolution on (N+2)-D input. |
|
Applies dropout operation to input array. |
|
Maps integer indices to vector representations (embeddings). |
|
Applies a linear transformation: \(Y = XW^T + b\). |
|
Layer normalization. |
|
Performs pooling on the input. |
|
Applies recurrent layers to input data. |
|
Applies Leaky rectified linear unit activation element-wise to the input. |
|
Convert multibox detection predictions. |
|
Generate prior(anchor) boxes from data, sizes and ratios. |
|
Compute Multibox training targets |
|
Performs region of interest(ROI) pooling on the input array. |
More operators¶
|
Computes sigmoid of x element-wise. |
|
Computes rectified linear activation. |
|
Calculate Smooth L1 Loss(lhs, scalar) by summing |
|
Applies the softmax function. |
|
Computes the log softmax of the input. |
|
Returns the indices of the top k elements in an input array along the given |
|
Wait for all async operations to finish in MXNet. |
|
Load arrays from |
|
Save an array to a binary file in NumPy |
|
Returns a one-hot array. |
|
Picks elements from an input array according to the input indices along the given axis. |
|
Reshape some or all dimensions of lhs to have the same shape as some or all dimensions of rhs. |
|
Flattens the input array into a 2-D array by collapsing the higher dimensions. |
|
Batchwise dot product. |
|
Returns the gamma function (extension of the factorial function to the reals), computed element-wise on the input array. |
|
Sets all elements outside the sequence to a constant value. |
seed