-
我想针对火车票训练一下,数据集我有,应该怎么搞呢?谢谢楼主
szzwy updated
6 months ago
-
您好,我使用的一些车牌小图做训练集,将dense_cnn改为增加了blstm层的那种,然后标签txt文档也改成了我自己的。训练集大概有4万多张图,我是重头训练的,没有加载预训练模型,不管怎么调整lr,训练的acc都是0,测试结果也都是错的。。
请问这需要怎么改呢?
-
Hello, I am also researching covid cough . Can you share the dataset with me? I'm sorry I missed the competition.
-
readme.md里写到有dense的版本,请问最好的效果是crnn的还是dense的版本?
-
I use the original ACELoss to train CRNN based on synth90k dataset, but can not converage. I wonder if LS-ACELoss been used in such training as I mention? And what is the accuracy
-
I want to copy the model by tensorflow
-
请问怎样能识别出字符间空格?尤其是英文单词间,CRNN识别结果都是连在一起的。请指教
-
大神,您好,我使用您提供的transforms替换crnn中的bilstm,效果很差,loss先下降后上升,然后一直不下降,怎么回事呢? @ @opconty
-
For example the good result with short width
![image](https://cloud.githubusercontent.com/assets/16144935/22959941/1ca7138c-f375-11e6-8eee-0a8e56c12340.png)
![image](https://cloud.githubusercontent.…
-
train_loader = torch.utils.data.DataLoader(
traindataset, batch_size=batchSize,
shuffle=False, sampler=None,
num_workers=int(workers),
collate_fn=alignCollate(imgH=imgH, imgW=imgW,…