class nbla::BinaryConnectAffine

template<typename T>
class BinaryConnectAffine : public nbla::BaseFunction<int, float>

BinaryConnectAffine BinaryConnect network version of an affine layer, using deterministic quantization to -1 and 1.

Reference: M. Courbariaux, Y. Bengio, and J.-P. David. “BinaryConnect:

Training Deep Neural Networks with binary weights during propagations.” Advances in Neural Information Processing Systems. 2015.

NOTES:

1) if you would like to share weights between some layers, please make sure to share the standard, floating value weights (input parameter #2) and not the binarized weights (input parameter #3)

2) Only after a call to forward() the weights and the binary weights are in sync, not after a call to backward(). If wanting to store the parameters of the network, remember to call forward() once before doing so, otherwise the weights and the binary weights will not be in sync.

\[ {\mathbf y} = {\mathbf A} {\mathbf x} + {\mathbf b}. \]

Inputs ( \(B\) is base_axis):

  • Input N-D array with shape ( \(M_0 \times ... \times M_{B-1} \times D_B \times ... \times D_N\)). Dimensions before and after base_axis are flattened as if it is a matrix.

  • Weight matrix with shape ( \((D_B \times ... \times D_N) \times L\))

  • Binarized weight matrix with shape ( \((D_B \times ... \times D_N) \times L\))

  • (optional) Bias vector ( \(L\))

Outputs:

  • \((B + 1)\)-D array. ( \( M_0 \times ... \times M_{B-1} \times L \))

Template Parameters:

T – Data type for computation.

Param base_axis:

Base axis of BinaryConnectAffine operation. Dimensions up to base_axis is treated as sample dimension.

Param quantize_zero_to:

Input value at zero is quantized to this value.

Public Functions

inline virtual shared_ptr<Function> copy() const

Copy another instance of Function with the same context.

inline virtual vector<dtypes> in_types()

Get input dtypes.

Last in_type will be used repeatedly if size of in_types is smaller than size of inputs

inline virtual vector<dtypes> out_types()

Get output dtypes.

Last out_type will be used repeatedly if size of out_types is smaller than size of outputs

inline virtual int min_inputs()

Get minimum number of inputs.

This is meant to be used in setup function with in_types which is used to get maximum number of inputs.

inline virtual int min_outputs()

Get minimum number of outputs.

This is meant to be used in setup function with out_types which is used to get max number of outputs.

inline virtual string name()

Get function name in string.

inline virtual vector<string> allowed_array_classes()

Get array classes that are allowed to be specified by Context.

inline virtual bool grad_depends_output_data(int i, int o) const

Dependency flag for checking if in-grad depends on out-data.

Checking if i-th input’ gradient computation requires o-th output’s data or not.

Note

If any of inputs requires an output variable data when computing its gradient, this function must be overridden to return appropriate boolean value. Otherwise, backward computation will be incorrect.

Parameters:

  • i – [in] Input variable index.

  • o – [in] Output variable index.