Elaineok
Elaineok
I think it's OK to use "CAM" and "Pairwise Affinities" capturing instance segmentation masks. Because the "Instance Map" purpose is to distinguish instances, and "Pairwise Affinities" also has this function....
@JialeCao001 Hi,thank you for sharing such a great work! Did you provide the code for the iSAID instance segmentation in this project？For example: How to load the iSAID data for...
Hello, I am prompted that there is no **_BBAM_training_images_nimg_10582_th_0.85_plus_mcg.json_** file when I train the model. Can you provide it? Thanks
@karanchahal I have two problems. 1.During training the model（ train_saliency.py），loss becomes NAN after epoch=4. 2.I run the **visualize.py** but the mask not so good. What's the problem here? `imshow(torchvision.utils.make_grid(masks.cpu().data))` ...
What does “**ctx.num_flags = 4**” mean in the ### prm.functions.peak_stimulation.py？ 
In the Github source code you provided，the test experiment is 45.86%.Can you check it again？
How to get WSSS_maps? I used the pseudo results provided by your DRS article and got 37.5% map. But the result in the paper is 41.8% map. The pseudo result...
Can you download the code from Github project and check out？