trantuankhoi

Results 8 comments of trantuankhoi

> Delete the labels.cache in each train, val and test folders. I had this exact same problem a few days ago, I had first trained a yolov5 model and that...

Hi @chenj133 , have you resolved your issue?

Hi @Topdu, can you take a look here pls? Thanks in advance

Thanks for your reply and suggestions My batchsize is 96, so I will set the lr = 0.000046875 (based on the paper). About my language dictionary, it has 233 characters,...

Thanks a lot. I will experience one more time follow your suggestions

Hi @Topdu I'm currently training the SVTR_CPPD (base) model and noticed that the `train/loss_edge` metric is significantly higher than the `train/loss_node` metric. I'm not sure if this is normal behavior,...

Hi @marcoslucianops I'm using Ubuntu and got this issue too but the provided weight in your document can run perfectly. It look like the weights trained by ultralytics are causing...