-
Where to put the data path?Can you provide the data path?I have kaggle's data set, and I don't know how to put it in, and I can't pre-process it. Can you give me a hand?thank you
-
Hi @antonilo
Thank you for sharing your impressive work. I ran your code and got results similar to yours.
However, I have some doubts about how you can ensure that the network learns the moving se…
lliuz updated
5 years ago
-
Hi,
I am having the following issues/doubts:
1. My system gets hanged when i try to run the saliency part of the code, for both test.py and predict.py. I use the pretrained model shared. Can you pl…
-
run example/resnet/attention.ipynb
and change to the model with my custom resnet50 like this:
model_path = os.path.join('../../../saved_models', 'res50transfer_learning.h5')
model = load_mod…
-
Hi, I've been trying the code for a while and have a couple of questions about the gradients.
To give some context here, I would like to identify which feature maps are the most relevant for a specif…
-
Hi! Thanks for your amazing work here. You've really made testing out gradcam a breeze.
I have a question regarding the usage of these modules. When I create a saliency map using a model I have fi…
-
##### System information (version)
- OpenCV => 4.2.1 + opencv_contrib cloned from repo
- Operating System / Platform => Ubuntu Linux 19.10
- Compiler => GCC 7
##### Detailed description
```
$ …
-
I have been trying to map pixels to the objects (i.e. ball, paddle, bricks) in breakout. But, for some reason, the ball position in the state json is always very off and paddle positions are sometimes…
-
if some dimensions of input are not specified, for example `(None, None, None, 3)`
Method `elrp` works fine, but `deeplift` raises an error. (Both traditional API and Explainer API.)
TypeError: '…
-
Thank for your work.
If I run de.explain multiple times, it becomes slower and slower.
This problem has not been solved in v0.2.