Comments (11)
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.
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.
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.
time_step是不是要跟最后的俩个数相乘结果一样啊?
from crnn.caffe.
@ziqiangchen 没有遇到过,可能是cuda版本之类的问题。
from crnn.caffe.
@suntim 是的。我这里time_step = h * w
from crnn.caffe.
@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.
@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.
@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.
@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.
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)
- Wrong accuracy when I change test_iter HOT 1
- 测试结果出现了很大问题 HOT 9
- 测试例子出现问题 HOT 5
- 标签问题 HOT 4
- ContinuationIndicator出自哪里?
- your model doesn't match to your deploy.txt HOT 4
- 图片是不是必须这个格式,多一点边框都不行吗? HOT 1
- 自制数据集,过拟合的问题 HOT 7
- accuracy is 0 HOT 5
- example core dump
- 测试结果的问题 HOT 3
- test_accuracy和模型实际测试的值不同
- Alphabets in label's questions HOT 2
- 将CNN换成densenet结构后,BN层设置问题
- CNN结构替换成denseNet时遇到的问题
- make fail with protobuf/stubs/common.h not found
- 训练你的代码出现维度不匹配
- check failed: registry.count(type)==1(0 vs 1) unknown layer type:
- 你好,训练自己数据的时候准确率和loss都为0 HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from crnn.caffe.