public override _Tensor[] ForwardPass(_Tensor[] inputs)
{
results[0] = (NN_Utils.GEMM(kernel, inputs[0])) + bias;
activationFunction.Activate(ref results[0]);
return(results);
}
/// <summary>
/// Computes the probability of choosing an action given a stack of frames and the value function
/// </summary>
/// <param name="inputTensor">
/// Input tensor of shape HxWxM
/// </param>
public double[,] Predict(double[,,] inputTensor)
{
double[,,] dw_h_conv1 = NN_Utils.DepthWiseConv(inputTensor, W_DW_conv1, W_conv1_size[4]);
double[,,] h_conv1 = NN_Utils.PointWiseConv(dw_h_conv1, PW_conv1);
NN_Utils.ReLU(ref h_conv1);
double[,,] dw_h_conv2 = NN_Utils.DepthWiseConv(h_conv1, W_DW_conv2, W_conv2_size[4]);
double[,,] h_conv2 = NN_Utils.PointWiseConv(dw_h_conv2, PW_conv2);
NN_Utils.ReLU(ref h_conv2);
double[,] h_conv3_flat = NN_Utils.Flatten(h_conv2);
double[,] h_fc1 = new double[1, W_fc1_size[1]];
double[,] action_output = new double[1, W_fc2_size[1]];
NN_Utils.GEMM(h_conv3_flat, W_fc_1, ref h_fc1);
NN_Utils.ReLU(ref h_fc1);
NN_Utils.GEMM(h_fc1, W_fc_2, ref action_output);
NN_Utils.Softmax(ref action_output);
Value_funtion = 0d;
for (int i = 0; i < h_fc1.GetLength(0); i++)
{
for (int j = 0; j < h_fc1.GetLength(1); j++)
{
Value_funtion += h_fc1[i, j];
}
}
return(action_output);
}
