pytorch-grad-cam

pytorch-grad-cam copied to clipboard

yqj0919

Problem generating CAMs using the saved model

2

Hi, I am facing a problem generating CAMs using the saved pre-trained VGG-13 model. The model is loaded correctly and verified using the message "**All keys matched successfully**." I also...

Q512147211

Replcae accross with across

anthonyweidai

I'm opening a new issue to revive this one: https://github.com/jacobgil/pytorch-grad-cam/issues/198 This is the error I'm getting, it's the same as the issue above: ``` grayscale_cam = cam(input_tensor=input_tensor, targets=targets) File ".../lib/python3.8/site-packages/pytorch_grad_cam/base_cam.py",...

Christophe-Foyer

Address cv2.resize float16 issue in scale_cam_image

1

https://github.com/jacobgil/pytorch-grad-cam/issues/198 https://github.com/jacobgil/pytorch-grad-cam/issues/493 Putting in a PR to go along with my issue post. cv2.resize doesn't support float16 which causes this step to break. This fixes the issue with not downstream...

Christophe-Foyer

How should I assign a value to the "targets" when I draw the heatmap of yolov8-pose?

1

 I don't think "targets=None" is right. in the "base_cam.py", ``` if targets is None: target_categories = np.argmax(outputs.cpu().data.numpy(), axis=-2) targets = [ClassifierOutputTarget( category) for category in target_categories] ``` obviously, "pose"...

Xavier-W

the example in README need to update

1

this link ：https://jacobgil.github.io/pytorch-gradcam-book/Class%20Activation%20Maps%20for%20Semantic%20Segmentation.html  i found now the code can automatic use the same device of model： ``` class BaseCAM: def __init__(self, model: torch.nn.Module, target_layers: List[torch.nn.Module], reshape_transform: Callable = None,...

578223592

Traceback (most recent call last): File "test.py", line 156, in main result = indicator(**test_input) File "../code/indicator/learning_indicator/_base.py", line 93, in _call_impl score = self.get_result(**required_inputs) File "../code/indicator/learning_indicator/DecomCam_PP/DecomCam_PP.py", line 62, in get_result cam...

Wud1

How to extract cam during training without creating issues to the bakpropagation

3

Hi, I'm implementing the following custom function: > def return_cam_from_model(model, target_layer, batch, targets , cam_name = "gradcam"): > > model.eval() # da rimettere in .train() se nel training loop >...

PietroManganelliConforti

What is the different colors mean?

3

I found that the color of eyes,mouth of the face if blue and other part of the face is red. Does it mean that the eyes,mouth are not important in...

liuxiangchao369