Jad

有一起讨论的嘛，加vx一起探讨下，拉个群an10246115 After training PNet, run gen_hard_example to generate training data(Face Detection Part) for RNet

这个代码是完整的嘛？可以训练了嘛？Cannot compile lanms: /home/yana/OCR/FOTS.PyTorch/utils/lanms

22

上面的问题怎么解决？an10246115,这是微信，可以拉个群大家一起讨论一下

RuntimeError:set_storage is not allowed on Tensor created from .data or .detach()

1

This is my config.json { "name": "FOTS", "cuda": true, "gpus": [0,1,2,3], "data_loader": { "dataset":"icdar2015", "data_dir": "./text_data/2015/training", "batch_size": 24, "shuffle": true, "workers": 4 }, "validation": { "validation_split": 0.2, "shuffle": true },...

why? How? train error 0%| | 0/100000 [00:00<?, ?it/s]

6

Traceback (most recent call last): File "/root/anaconda3/envs/CornerNet_Lite/lib/python3.7/multiprocessing/queues.py", line 236, in _feed obj = _ForkingPickler.dumps(obj) File "/root/anaconda3/envs/CornerNet_Lite/lib/python3.7/multiprocessing/reduction.py", line 51, in dumps cls(buf, protocol).dump(obj) File "/root/anaconda3/envs/CornerNet_Lite/lib/python3.7/site-packages/torch/multiprocessing/reductions.py", line 295, in reduce_storage fd, size...

训练多少epoches PFLD_Ultralight 0.25 112 NME可以达到0.06101?

14

训练了200epoches，NME是0.07467567288161081