3D-convolutional-speaker-recognition-pytorch
3D-convolutional-speaker-recognition-pytorch copied to clipboard
A question about the parameter in enrollment
output_numpy = np.zeros(shape=[num_enrollment,40,128],dtype=np.float32)
model = np.zeros(shape=[40,128],dtype=np.float32)
outputs = net(inputs) # shape is (batch_size,128)
output_numpy[i] = outputs.cpu().data.numpy()
Here‘s the code in enrollment.py. I'm confused about the parameter 40. It seems that it has to be equal to the batch size, or it does not work. But the batch size in the code is 64.