-
When used ade20k data, the ground truth is 3 channel, which corresponding to classes. I wonder if we need generate grayscale image firstly, and then read the gt image to train the model?
Thanks!
-
Hello! Thank you for your wonderful project!
When I trained ADE20k data set, some problems appeared. What is the value of-use _ vae10 in ade20k.sh? I set 10 to start training, but the speed is very s…
-
Hello,
I followed the instructions and ran eval_all.m on the ADE20K Validation Dataset (the one from the Challenge). Unfortunately the results are very bad:
Mean IoU over 150 classes: 0.0007
Pix…
pjohh updated
6 years ago
-
-
Hi, I wanna know where can I download "ade20k_rna-a1_cls150_s8_ep-0001.params" ? I read through readme in detail, but still didn't find the link for it. can you give me the link?? thank you very much…
ghost updated
6 years ago
-
For the results of resnest on ade20k, what is the base-size and crop-size? Thanks for your reply!
-
Hi,
Can you also upload the pretrained model for ADE20K dataset?
Thank you.
-
[10/28 17:59:24] d2.engine.defaults INFO: Evaluation results for openvocab_pascal_ctx459_sem_seg_val in csv format:
[10/28 17:59:24] d2.evaluation.testing INFO: copypaste: Task: sem_seg
[10/28 17:59…
-
Hello,
I've been attempting to deploy the mask2former_flash_internimage_s_640_160k_ade20k_ss model using the provided deploy.py script from the internimage repository, located in the segmentation f…
-
Hi, I am trying to reproduce your evaluation on _"ade20k_panoptic_val"_ dataset, but there is issue with the visual prompts generation. The script is looking for _anns[ann['id']] = ann_ and giving _Ke…