-
When generate cam, you use the ground truth label to get the channel weight of fully connected layer. But I think the predict class of model is the right choice.
-
## The problem
Appium cannot parse page elements when connected to iOS devices, and the element tree has no corresponding content.
## Environment
Appium version (or git revision) that exhibit…
-
I cant find this folder **train_log/scoremaps/** for CUB dataset. I am trying to use your evaluation only script. Could you please tell me the procedure to run this code on heatmaps. How do we genera…
-
Hi, I used your config params to train resnet50 vanilla cam, I cannot reach your reported accuracy.
Here's my configurations:
`
CUDA_VISIBLE_DEVICES=6 python train.py --dataset_name CUB --archite…
-
Hi,
Thanks for this great work done. I have two questions:
(1) When I run: python evaluation_test.py, it outputs:
FAIL: test_compute_bboxes_from_scoremaps_degenerate (__main__.EvalUtilTes…
-
Getting the above issue after running the following commands
!git clone https://github.com/clovaai/wsolevaluation.git
os.chdir("wsolevaluation")
!bash dataset/prepare_cub.sh
!python main.py --…
-
Hi! In your work, you proposed a self-supervised training mechanism. But in the code, I observed that both VGG and SEResNet use a network pretrained on ImageNet and then train your net.
（1）As far a…
-
I am trying to understand the paper. Just clear out my confusion. I am confused whether the newly added datasets are used for training or not, after the optimal hyperparameters are selected.
For exa…
-
The following produces a working solve via solve() but not via LinearSolver, which complains that the matrix has type nest, although I passed in mat_type:aij.
```python
import firedrake as fd
me…
-
Dear authors,
Thank you very much for this dedicated reop! This is extremely helpful to the WSOL community!
Some questions:
1) Are jobs covered by this repo all only require one GPU to train an…