ctc init #63
Closed
ctc init #63
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
qingqing01
reviewed
Jun 4, 2017
ctc/model.py
Outdated
| stride_x=1, | ||
| stride_y=1, | ||
| block_x=1, | ||
| block_y=3) |
There was a problem hiding this comment.
依据 PaddlePaddle/Paddle#2296 这里看conv_features的 输出的特征c=128, h=11, w=3， block_y应该是11，估计这块设置不对，导致了GPU内存问题，以及issues #2296 的问题。
|
训练的配置写好了，基本可以 PR 了。 |
qingqing01
requested changes
Jul 4, 2017
ctc/README.md
Outdated
| # CTC (Connectionist Temporal Classification) 模型CRNN教程 | ||
| ## 背景简介 | ||
|
|
||
| 现实世界中的序列学习任务需要从连续的输入序列中预测出对应标签序列， |
There was a problem hiding this comment.
序列学习任务需要从连续的输入序列中预测出对应标签序列
连续的输入准确吗？ 机器翻译的输入不连续吧？
ctc/README.md
Outdated
| ## 背景简介 | ||
|
|
||
| 现实世界中的序列学习任务需要从连续的输入序列中预测出对应标签序列， | ||
| 比如语音识别任务从连续的语音中得到对应文字序列，类似于seq2seq任务； |
There was a problem hiding this comment.
seq2seq任务如果是个专有名字需要加链接。
ctc/README.md
Outdated
| CTC相关模型就是实现此类seq2seq任务的的一类算法，具体地，CTC模型为输入序列中每个时间步做一次分类输出一个标签（CTC中 Classification的来源）， | ||
| 最终对输出的标签序列处理成对应的输出序列（具体算法参见下文）。 | ||
|
|
||
| CTC 算法在很多领域中有应用，比如手写数字识别、语音识别、手势识别、连续图像文字识别等，除去不同任务中的专业知识不同， |
ctc/README.md
Outdated
| CTC 算法在很多领域中有应用，比如手写数字识别、语音识别、手势识别、连续图像文字识别等，除去不同任务中的专业知识不同， | ||
| 所有任务均为连续序列输入，标签序列输出。 | ||
|
|
||
| 本文将针对 **场景文字识别 (STR, Scene Text Recognition)** 任务，演示如何用 PaddlePaddle 实现 一个一站式 CTC 的模型 **CRNN(Convolutional Recurrent Neural Network)** |
ctc/README.md
Outdated
| CTC 算法在很多领域中有应用，比如手写数字识别、语音识别、手势识别、连续图像文字识别等，除去不同任务中的专业知识不同， | ||
| 所有任务均为连续序列输入，标签序列输出。 | ||
|
|
||
| 本文将针对 **场景文字识别 (STR, Scene Text Recognition)** 任务，演示如何用 PaddlePaddle 实现 一个一站式 CTC 的模型 **CRNN(Convolutional Recurrent Neural Network)** |
ctc/data_provider.py
Outdated
|
|
||
|
|
||
| if __name__ == '__main__': | ||
| image_file_list = '/home/disk1/yanchunwei/90kDICT32px/train_all.txt' |
There was a problem hiding this comment.
这个脚本需要有下载数据的过程，这个路径可以换成下载之后的路径。
ctc/README.md
Outdated
| ### 图像数据及处理 | ||
| 本任务使用数据集\[[4](#参考文献)\]，数据中包括了图片数据和对应的目标文本，其中预测的目标文本需要转化为一维的ID列表，我们用如下类来实现 | ||
|
|
||
| ```python |
There was a problem hiding this comment.
这块不用粘贴这么多代码，告诉用户是在哪个脚本和函数即可。
ctc/data_provider.py
Outdated
| if self.fixed_shape: | ||
| image = cv2.resize( | ||
| image, self.fixed_shape, interpolation=cv2.INTER_CUBIC) | ||
| # image = to_chw(image) |
There was a problem hiding this comment.
image = to_chw(image)
注释的代码去掉。
ctr/model.py
Outdated
| @@ -0,0 +1,76 @@ | |||
| #!/usr/bin/env python | |||
There was a problem hiding this comment.
CTR和DSSM部分代码和文档可以从这个PR里去掉吗？
ctc/train.py
Outdated
|
|
||
| trainer.train( | ||
| reader=paddle.batch( | ||
| paddle.reader.shuffle(dataset.train, buf_size=100), |
There was a problem hiding this comment.
buf_size可以增大点，加大shuffle范围吧。
This was referenced Sep 14, 2017
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
出现 gpu allocate 多次的问题