Quan Nguyen
Quan Nguyen
my classnum is 31. So i can't use his pretrained weights. Btw i generated gray images for training.
> @zhenx I need to find it. there are so many versions code, I will check it and upload it. hi @backtime92 . did you upload it ?
@shocoladka did you fix that bug ?
i have just fixed it. you just need to comment "if cls.rnn_cell is None: " line and everything will be ok.
> me too，the output channel should be 2 but not 16 > See the original pytorch impl: > > ``` > self.conv_cls = nn.Sequential( > nn.Conv2d(32, 32, kernel_size=3, padding=1), nn.ReLU(inplace=True),...
@yukang2017 @AutoVision-cloud hi, I want to train PV-RCNN_FSA model on v100 - 16gb on colab pro. But I can't train because of out of memory error even with batch size...
"son", "song",...
i trained similar dataset before, my task was OCR mrz on idcard. i started tuning model with yolov5s so i can tune faster then u can try yolov5m for better...
@diegotecrede 1. `box: 0.05 # box loss gain cls: 0.3 # cls loss gain obj: 0.7 # obj loss gain (scale with pixels)` 2. u can change yolov5-p34.yaml