-
the link there is not a valid clickable link to access your predicted saliency map.
please release the map for comparison.
thanks
-
@VainF Hi, when I prune the yolov7 backbone, it failed and said:
`group_imp = torch.stack(group_imp, dim=0)`
`RuntimeError: stack expects each tensor to be equal size, but got [512] at entry 0 and […
-
## 🚀 Feature
Saliency and IG to explore the features driving graph prediction using DGL
## Motivation
Very few alternatives for explainability of graph level predictions are available in DGL. W…
-
I want to train simultaneously with three pseudo-labels or more fake labels. How should I modify the code?
Thank you！
-
Thanks for your work! I've been working on image saliency prediction recently. A few days ago, I reproduced deepgazeII using pytorch. But I found the loss is difficult to converge. The loss function I…
-
Hi @lukemelas, fascinating work, thank you for your contribution!
While looking at the semantic segmentation results, I got several questions regarding the baselines used.
> Additionally, we g…
-
Would it be possible to handle networks trained for timeseries classification? Example CNN below:
```
class Cnn1d(nn.Module):
def __init__(self, outputs=2):
super(Cnn1d, self).__init…
-
Currently it seems sentences are rebuilt from the token strings by simply joining them together with spaces in between, and there is no clean way to customize this. Often this is not what you want, I'…
-
Compiling a bunch of ideas for the front end here as a draft... Can discuss tomorrow and move concrete ones to Trello.
## Image upload
- Option to provide a URL for an image? See http://places2…
-
I am very interested in your proposal and would love to use it.
However, since I cannot create a Baidu account, can you distribute the trained model with other cloud services?
Thank you for your w…