-
Please make sure that this is a build/installation issue. As per our [GitHub Policy](https://github.com/tensorflow/tensorflow/blob/master/ISSUES.md), we only address code/doc bugs, performance issues,…
-
hello,everyone.
I used my own dataset to train on Cascade R-CNN Resnet50.After 80 epoch, I run tools/test.py to evalue my model and got results as follows:
Average Precision (AP) @[ IoU=0.50:0.95 …
-
Dear Author:
Hi, is the file "num_shots_v0.5.npy" necessary for training? Can you provide the file?https://github.com/MegviiBaseDetection/DisAlign/blob/eb85ca08d2204c612e5ef1c54534d49a688dc83…
-
Hi,
I am trying to train ESSNet on COCO+LVIS, but seemingly could not find the settings of some parameters (B, k, d) in your paper. Could you give some advice?
Thank you.
-
## ❓ I know that the LVIS model is categorized into 1230.
How can I know the number of 1230 classes and the corresponding class names?
-
I'd like to get experimental results on LVIS dataset with my model.
But i found that i need LVIS v0.5 which is not available anymore.
 in the few-shot transfer learning experiment on LVIS, the 100%-data's performance is not better than the 10%-data's for MDETR over all metrics, why is that ? ( i only fo…
-
In your paper you don't compare against [CascadePSP](https://github.com/hkchengrex/CascadePSP). I was wondering if you could evaluate your method vs theirs? Thanks!
-
I follow the official guide to train a model, however, when the number of iterations reaches 4973, the program will throw this exception, and then the retraining will throw this exception directly,
…