Mano Bharathi M

Injecting new line : ``` def on_train_epoch_end(self): loss = torch.stack(self.batch_losses).mean() self.log('loss', loss, on_step=False, on_epoch=True, prog_bar=True) print(f"Epoch {self.current_epoch} --> loss{loss.item()}") self.batch_losses.clear() print("") ``` Output will look like this:  @jojje Do...

Hi @dacorvo , My initial approach was 1. quantize the model using quantize function. 2. Iterate the state_dict and check if it's value is tensor type then it's weight so...

If I am not wrong, this is what we need to do it in helper `requantize` `` model = quantize(model) model.load_state_dict(state_dict,assign=True) ``

Thanks, I will think about unit test !

Cal If I am not wrong, test function can be further extended.. > The process is a bit convoluted, as it requires the target model to be quantized first without...