BBC

Errors when testing on CPU

11

``` layer_name: , total_params: 15121584, total_traina_params: 15121584, n_layers: 39 device: cpu Traceback (most recent call last): File "main.py", line 208, in test(epoch) File "main.py", line 189, in test outputs =...

Select net from command args. Add train/test modes. Add pruning. Add nohup version. Add args input and pruning. Save on GPU, test on CPU.

Hi Dr. Shibuya, I really love your work! Regarding > The horizontal translation is useful for difficult curve handling (i.e. the one after the bridge). I don't quite understand this,...

Does the "weights" here in get_cam_weights() https://github.com/jacobgil/pytorch-grad-cam/blob/2183a9cbc1bd5fc1d8e134b4f3318c3b6db5671f/pytorch_grad_cam/ablation_cam.py#L148 refer to model's pretrained weights or the values for the class activation map? Thanks!

``` group = DG.get_pruning_group(model_.layer4[0].conv2, tp.prune_conv_out_channels, idxs=idxs_ ) ``` ``` -------------------------------- Pruning Group -------------------------------- [0] prune_out_channels on layer4.0.conv2 (Conv2d(512, 1, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)) => prune_out_channels on layer4.0.conv2...

How to Manually Selecting Negative Samples

2

Thanks for the awesome framework! It seems that negative samples are by default the ones from a different class, is there a way to manually choose negative samples? For instance,...