MichaelY

icon location Set your course by the stars, not by the lights of every passing ship.

Results 2 issues of MichaelY

Is the RRDBNet correct?

In the forward function of the RRDBNet def forward(self, x, get_steps=False): fea = self.conv_first(x) block_idxs = opt_get(self.opt, ['network_G', 'flow', 'stackRRDB', 'blocks']) or [] block_results = {} for idx, m in...

Why does the sum of u_batch`and v_batch multiplies batch_size?

Why does the sum of `u_batch` and `v_batch` multiplies `batch_size` ? ``` loss_batch = torch.sum(u_batch)*batch_size + torch.sum(v_batch)*batch_size \ - self.reg_val*torch.sum(torch.exp((torch.reshape(u_batch, (-1, 1)) + torch.reshape(v_batch, (1, -1)) - C_batch) / self.reg_val))...