quant_loss inconsistent with paper

[cx-333]

In src/IBQ/modules/vqvae/quantize.py, the quantization loss is computed as:

    quant_loss = torch.mean((z_q - z)**2) + torch.mean((z_q_2.detach()-z)**2) + self.beta * \
               torch.mean((z_q_2 - z.detach()) ** 2)

However, in the paper, the equation is:

Does this affect the results?