Yanshuang

@longgang123 @mikuxworld hello! how did you solved this error? when i training the end-to-end vgg16 version, i meet the same problem. some infomation of mine: CUDA8.0.61+cuDNN.v6+GTX1080TI. ``` F0122 10:50:04.063930 28593...

it is probably the problem of the version of cuda/cudnn, I solved this issue by changing to cuda8.0.61/cudnn v5.1. but I still don't understand the real reason behind......good luck to...

@lixiang-ucas i encountered the same problem, it seems that cfg assignments in function train_rpn() and train_fast_rcnn() don't work. how did you solve it?

I want to initialize model with the trained icdar2015 model provided by author, and just set the parameter below is: ``` tf.app.flags.DEFINE_boolean('restore', True, 'whether to resotre from checkpoint') ``` and...

refer to: https://github.com/whai362/PSENet/issues/23.

pixel value in training_mask: 0-->ignored text regions(containing '###'), 1-->other regions @hust-kevin

@YoungminBaek Could you share the lr details? e.g. base_lr and lr_decay_scheduler ? I set the base lr is 1e-3 and multiply 0.1 every epoch in SynthText，But the performance is not...

Thanks for your reply so much @YoungminBaek

I meet the same question. I trained ATSS detector with ReoLKNet31B and batch_size 1(2080Ti GPU, 11 GB memory..., and 'use_checkpoint' seems to be not compatible with DDP): * when use...

But when I replace internlm model with `qwen1.4-4b-chat`，it works... ## content of `internlm_chat_7b_qlora_colorist_e5.py` ```python # Copyright (c) OpenMMLab. All rights reserved. import torch from datasets import load_dataset from mmengine.dataset import...