-
**Describe the bug**
When testing the visualization tool using a custom pre-trained CNN that performs Binary Classification, the error "AttributeError: 'NoneType' object has no attribute 'shape'" cro…
-
If so, are there any requirements for the model?
-
Is it possible to provide Your pre-trained model? "best_epoch-138_acc-0.9107_loss-0.1300.pt"
Did You trained it on DUTS-TR?
-
I use your pre-trained model on HKU-IS and test on the result which has 0.030 MAE and 0.99 max F_beta!!(save and load the saliency map) Do I use the wrong way to test? Could you share how you test?
-
Could captum be used for the saliency maps of Image Segmentation model? Such as UNet or Mask R-CNN?
-
Hi, Jing,
Thank you for sharing the wonderful work.
I have tested the trained model you uploaded. But the results are different from the paper. Is the uploaded model your final result of your paper?
-
##### System information (version)
- OpenCV => 4.5.0
- Operating System / Platform => GNU/Linux Debian 10
- Compiler =>cmake 3.13.4
- Cuda => 10.1
- GPU => GTX 1650
##### Detailed descri…
-
I've been working on this code base for quite a while, but I have still yet to see a working example. I've played with calculating the loss function differently, all sorts of hyperparameters, and diff…
-
Hi, I get different results every time I run the Spectral Residue method. Is there a way to define the random state here? thanks.
-
**Problem Faced:**
Backprop visualize doesn't consider models with grayscale input.
**Description:**
Refer to this line:
https://github.com/MisaOgura/flashtorch/blob/ba5e3db3911afee583180bead91…