where does gt.zip come from, and any suggest of this result?

[bygreencn]

1. Train with ICDAR2015 Ch4 with 600 epoch and batch_size change to 32, the log result looks like this: 0.000010 0.394331 0.889751 0.852450 0.000010 0.416218 0.898702 0.863312 0.000010 0.406228 0.874345 0.837213 0.000010 0.378316 0.900977 0.864393

2.Testing found the result some intrersting labels like this:

3. Eval result is Calculated!{"recall": 0.0, "precision": 0.0, "hmean": 0, "AP": 0} Where is wrong, all is following with README, only change the batch_size from 16 to 32, and the train result fit your log recorder.

[float123]

Excuse me, who solved this problem? I used the pre-training model downloaded from Baiduyun to test it. This is also the result.

[float123]

Excuse me, who solved this problem? I used the pre-training model downloaded from Baiduyun to test it. This is also the result.

找到原因了，是路径没设置对

[Mary63]

1. Train with ICDAR2015 Ch4 with 600 epoch and batch_size change to 32, the log result looks like this: 0.000010 0.394331 0.889751 0.852450 0.000010 0.416218 0.898702 0.863312 0.000010 0.406228 0.874345 0.837213 0.000010 0.378316 0.900977 0.864393

2.Testing found the result some intrersting labels like this:

1. Eval result is Calculated!{"recall": 0.0, "precision": 0.0, "hmean": 0, "AP": 0} Where is wrong, all is following with README, only change the batch_size from 16 to 32, and the train result fit your log recorder.

Hi :)

How did you draw these green rectangles? After training and testing, I get the .txt files, but then I don't know how to see these rectangles on my pictures.

Any help would be greatly appreciated.

Mary