VisionLAN

VisionLAN copied to clipboard

你好，这个地方 https://github.com/wangyuxin87/VisionLAN/blob/main/train_LF_2.py#L74-L76 通过id来选择不同参数，我通过print打印，第一组参数是空，也就是没有匹配到id_total的参数，是哪里有问题吗？

andyjiang1116

eval.py问题

1

感谢您的代码，运行“CUDA_VISIBLE_DEVICES=0 python eval.py”命令后，报出如下错误： Traceback (most recent call last): File "eval.py", line 11, in import cfgs.cfgs_eval as cfgs File "/workspace/VisionLAN-main/cfgs/cfgs_eval.py", line 5, in from data.dataset_scene import * File "/workspace/VisionLAN-main/data/dataset_scene.py", line 16,...

swqsyy

论文里的ST数据集就是mjsynth数据集吗

1

SLTK1

utils.py中的cha_encdec类在编码时将字典中不存在的符号编码为len(self.dict)+1，这将导致训练程序中的crossentropyloss函数报错

Huntersdeng

关于单字符label

1

 单字符label不需要语义信息，但是也会经过这个函数，采样的change_id=0，imput_lable = imput_lable[:change_id] 责imput_lable=‘ ’，即像这样  在训练过程中会发生错误 

developWmark

关于eval.py

1

 你好我用了readme给的测试集，但是我发现评测效果并没有论文表述的一样，请问一下我哪里操作有问题吗

developWmark

How can we get a demo for recognition of a single image?

2

lc1314555

Question about Visualization character-wise mask map

1

Thanks for your excellent contributions! I try to use your pre-trained LF_2 model to visualize the mask map, I pick the same image that was shown in the Visualization character-wise...

GaoXinJian-USTC

Training problems about CTCloss and Chinese training.

1

Dear yuxin, sorry to bother you again. When I use your code, I found two new questions: 1. When I executed `python train_LF_1.py`, I got a CUDA error in `ClassNLLCriterion.cu`....

PkuDavidGuan

How you occlude the characters, i.e. Which Tools?

1

I wonder how you occlude the characters of the image? Which tools? Can you Please explain?

zobeirraisi