-
Hello! I want to ask a question.
Is there a reason why the model is not trained for color recognition when the dataset contained annotations for color?
-
We had faced an issue where the kubernetes `Webmodule` container suddenly crashed.
The automatic container restarts were starting and failing. We tried restarting the cluster and containers, but th…
-
Hi! It is a great job.
In your paper, I notice that PA-100K dataset is divided into training set, validation set and testing set. However, training set and validation set are combined together to tra…
-
Hi, What changes are required to run the model in python3. So far, I've changed the `cpickle` instances to `pickle`
from `import cPickle to pickle` to `import pickle`
and added binary mode whil…
-
-
hi，大家好，非常高兴的告诉大家，百度飞桨论文复现赛第六期已经开始了，本次**论文复现赛**共将有100+篇的经典&前沿论文供大家复现，以及新增了**飞桨特色模型挑战赛**，详细信息可以参考[AI Studio](https://aistudio.baidu.com/aistudio/competition/detail/205/0/introduction)，大家是否已经迫不及待了呢~
…
-
Hello,Do you have a corresponding paper？
-
Hello, thank you for this awesome repo !
This is not an issue, everything works. Its more of a question. I havent worked much with encoders, but i like its performance compared to running secondary…
-
According to formula 5 and formula 6 in the paper, the class-specific residual attention (CSRA) feature _f_ should be sent to
the classifier to obtain the final logits, but in your code, you use the …
-
@chufengt i had few queries on the backbone
1. what was the reason of choice for using BN inception, since when i enable BNinception their is a boost in accuracy but since its heavier we get a drop…