Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
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" output should not use "ClassifierOutputTarget"
I don't think "targets=None" is right. in the "base_cam.py",
obviously, "pose" output should not use "ClassifierOutputTarget"