LvJC

What is the real batch size in multiple_gpu_cnn.py???

1

In Line 180 of `multiple_gpu_cnn.py`, the real batch size is `batch_size * num_gpus` or still `batch_size `.

`warmup_lr` is computed incorrectly in `step_ReduceLROnPlateau`

8

I wonder whether you forgot to modify like the line shown below in: https://github.com/ildoonet/pytorch-gradual-warmup-lr/blob/6b5e8953a80aef5b324104dc0c2e9b8c34d622bd/warmup_scheduler/scheduler.py#L44 ``` + warmup_lr = self.get_lr() - warmup_lr = [base_lr * ((self.multiplier - 1.) * self.last_epoch /...

Why stuck in 'Predicting saliency maps for sample_images/'?

1

Download your codes and I just want to test if it works well. But when I run `main.py` as so: `python main.py test sample_images/` Codes can work till it prints...

can't load the pre-trained model.

11

always inform me of _different tensor name not found_ error every time I press `run`. For example, 1. `NotFoundError (see above for traceback): Tensor name "scale5/block3/c/scale5/block3/c/moving_variance/biased" not found in checkpoint...