Jacob Gildenblat

The really strange thing for me, is that I'm running this on a laptop without a GPU, and still have the same issue.

Yes the assumption is that if class 0 survives the initial filtering (but has a very low probability), it can't survive the next filtering by `classProbThreshold` anyway. Unfortunately this doesn't...

Hi Cristian, thanks a lot for the PR. I think a notebook on using the CAM results for different masks is great, but I think it needs some additions for...

Hi, I tried reproducing it now but it works. I tried using the example in cam.py with resnet, and just repeated the tensor several times. Maybe print input_tensor.shape to be...

Hi i'm traveling right now so can take me another week until I look at this. Yes I'm 99% sure it's because of DataParallel: https://discuss.pytorch.org/t/using-forward-hook-for-data-parallel-with-multiple-gpus/107970 In DataParallel the hook is...

Hi, I couldn't reproduce it even with DataParralel. ```python model = models.resnet50(pretrained=True) model = torch.nn.DataParallel(model) target_layers = [model.module.layer4] ``` Can you please post: 1. How you're craeting the model. 2....

To have any chance at helping, I would need context: what kind of model are you using, does the model forward pass work on an inout tensor? or does it...

Hi, Can you please try `loaded_model.module.convnet[-2]` and tell if it worked? We need the 2D CNN activations before the pooling.

Hi, sorry for the late response, I was traveling.. What does target_layers look like now? What is the output shape you expect from that layer ? The CAM algorithms expect...

Hi, So what is the type of img here? Is it float16? Is there a chance you can modify the source code to do img = np.float32(img) before the resize,...