stealth0414

修改efficientnet输出层

2

## Env - GPU, nano - OS, Ubuntu18.04 - Cuda version 10.2 - TensorRT version 8.0 ## About this repo - which branch/tag/commit are you using? efficientnet - which model?...

efficientnet make failed

3

## Env - GPU, TX2 - OS Ubuntu18.04 - Cuda version 10.2 - TensorRT version 8.2.1.8 ## About this repo - efficientnet - make ## Your problem When i make...

Train my own recognition model

3

i want to use english_g2.pth to train my own recognition model,is there any Tutorial? The deep-text-recognition-benchmark model looks like 200MB,It's a little big for me,thanks

CUDA error: device-side assert triggered

2

when i train my own model in epoch 100,it has error in loss so that stop training /pytorch/aten/src/ATen/native/cuda/Loss.cu:115: operator(): block: [1237,0,0], thread: [25,0,0] Assertion `input_val >= zero && input_val =...

想使用torch自带的dcn，代替代码中的DCN编译算子，请问大家如何下手？还是建议不修改

1

感觉每次在新环境中编译DCN算子时会担心编译失败

eval.py 报错：RuntimeError: Attempted to set the storage of a tensor on device "cuda:0" to a storage on different device "cpu". This is no longer allowed; the devices must match.

8

用自己的数据集训练完成后尝试运行eval.py，发现报错 Traceback (most recent call last): File "eval.py", line 193, in main() File "eval.py", line 79, in main Eval(experiment, experiment_args, cmd=args, verbose=args['verbose']).eval(args['visualize']) File "eval.py", line 164, in eval model =...