Giter Club home page Giter Club logo

Comments (11)

yalecyu avatar yalecyu commented on July 28, 2024 2

图片不一样,尺寸就不一样,最后的time_step就不一样,你可以参考前面的压缩维度更改后面的参数。

from crnn.caffe.

ziqiangchen avatar ziqiangchen commented on July 28, 2024

I0809 07:53:56.976981 4128 net.cpp:131] Top shape: 523 512 2 16 (8568832)
I0809 07:53:56.977007 4128 net.cpp:139] Memory required for data: 3418995348
I0809 07:53:56.977032 4128 layer_factory.hpp:77] Creating layer reshape

我这边读入的图片维度是正确的,是按照制作h5文件的时候的维度读入的32*128,但是后来在reshape之前,我的维度是523 512 2 16,不过你们是reshape成了523 512 24,我这边就有维度的差异了,你们的维度都是523 512 2 12吗?有点迷呀。。。。

from crnn.caffe.

ziqiangchen avatar ziqiangchen commented on July 28, 2024

src/caffe/3rdparty/reduce.cu(44): error: identifier "__shfl_down" is undefined. 麻烦问下,这个问题你有碰到过吗?我在编译的时候,发现这个问题。。。。。

from crnn.caffe.

suntim avatar suntim commented on July 28, 2024

time_step是不是要跟最后的俩个数相乘结果一样啊?

from crnn.caffe.

yalecyu avatar yalecyu commented on July 28, 2024

@ziqiangchen 没有遇到过,可能是cuda版本之类的问题。

from crnn.caffe.

yalecyu avatar yalecyu commented on July 28, 2024

@suntim 是的。我这里time_step = h * w

from crnn.caffe.

jiawenhao2015 avatar jiawenhao2015 commented on July 28, 2024

@ziqiangchen 我碰到了跟您一模一样的问题。。。维度不匹配,想问一下您是怎么解决的呢?
I0809 07:53:56.976981 4128 net.cpp:131] Top shape: 523 512 2 16 (8568832)
I0809 07:53:56.977007 4128 net.cpp:139] Memory required for data: 3418995348
I0809 07:53:56.977032 4128 layer_factory.hpp:77] Creating layer reshape

from crnn.caffe.

ziqiangchen avatar ziqiangchen commented on July 28, 2024

@jiawenhao2015 OK..你该下timesteps,改成32。。因为你是523×512×2×26 将后两个维度压缩成第一维了。所以是2×16

from crnn.caffe.

jiawenhao2015 avatar jiawenhao2015 commented on July 28, 2024

@ziqiangchen 嗯呢 多谢回复了哈 刚刚看了一下log 之前是523×512×4×16然后经过了一个卷积层 尺寸为3*3 步长为1,但是默认的参数给的pad_w为1,而不是pad为1,然后就导致了宽度没变然后高度变为原来的一半了, 也就是523×512×2×16。刚刚把pad_w改成了pad就可以啦 然后也改了后边对应的尺寸。现在正在跑~训练数据集也都是按examples/crnn下的脚本生成的。。
都是默认的目前已经迭代了3600次ctc的loss发现已经降了一些,但是为啥accuracy一直是0呢。。。

from crnn.caffe.

liuyiyiyiyi avatar liuyiyiyiyi commented on July 28, 2024

@ziqiangchen 嗯呢 多谢回复了哈 刚刚看了一下log 之前是523×512×4×16然后经过了一个卷积层 尺寸为3*3 步长为1,但是默认的参数给的pad_w为1,而不是pad为1,然后就导致了宽度没变然后高度变为原来的一半了, 也就是523×512×2×16。刚刚把pad_w改成了pad就可以啦 然后也改了后边对应的尺寸。现在正在跑~训练数据集也都是按examples/crnn下的脚本生成的。。
都是默认的目前已经迭代了3600次ctc的loss发现已经降了一些,但是为啥accuracy一直是0呢。。。

请问你解决了吗,我的accuracy也一直是0

from crnn.caffe.

guweixin avatar guweixin commented on July 28, 2024

src/caffe/3rdparty/reduce.cu(44): error: identifier "__shfl_down" is undefined.
这个问题请问解决了么?
我是cuda10,cudnn7.5

from crnn.caffe.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.