haomingHu-dd

In the code, the global average pooling in the SE structure is implemented through average pooling, but the output size is not like 1X1XC in the paper. Is there a...

Excessive gap in mAR indicators

2

I will pull it locally, configure the running environment, get the model file through training, and then use the evaluation.py file to evaluate. The mAP indicators obtained are all greater...

Why in the 2-test.py file, the training set, test set and validation set are not divided when loading the data, but there are divisions in 1-train.py and 3-Evaluation.py

Why there is no label section in the dataset

2

hello，Why there is no label section in the dataset，and how should I divide the training set and the test set？