purlvin / machinelearning Goto Github PK
View Code? Open in Web Editor NEWMachine Learning Sourcecodes
Machine Learning Sourcecodes
您好,我按照您README.md文件中描述的步骤,使用现有模型能够正常运行。但训练模型时总是报错。提示如下:
python train.py -c conf/wave.yml
INFO:tensorflow:Scale of 0 disables regularizer.
Traceback (most recent call last):
File "train.py", line 134, in <module>
main(FLAGS)
File "train.py", line 25, in main
style_features_t = losses.get_style_features(FLAGS)
File "/home/ubuntu/MachineLearning/fast_neural_style-tensorflow/losses.py", line 46, in get_style_features
images = tf.pack([image_preprocessing_fn(image, size, size)])
AttributeError: module 'tensorflow' has no attribute 'pack'
不知道是我设置不对还是什么原因?
我个人怀疑有可能是这么几个原因:
1、TensorFlow-Slim我没有安装。这个需要另外安装吗?
2、由于使用的TensorFlow1.0.0版,某个函数相较于老版本发生了变化。就像您在hzy46/fast-neural-style-tensorflow#9
中提到的函数参数位置发生了变化(可参考hzy46/fast-neural-style-tensorflow#2 )。
3、下载了COCO dataset之后,建立符号链接这句描述我不太确定是什么含义
cd <this repo>
ln -s <your path to the folder "train2014"> train2014
我的COCO dataset 放在 ~/MachineLearning/fast_neural_style-tensorflow/models/train2014,我一开始使用
cd ~/MachineLearning/fast_neural_style-tensorflow/models/train2014
ln -s ~/MachineLearning/fast_neural_style-tensorflow/models/train2014 train2014
在数据集文件夹train2014内部建立了符号链接,然后返回到fast_neural_style-tensorflow文件夹,
python train.py -c conf/wave.yml
报前述错误。
后来我又在fast_neural_style-tensorflow文件夹下
ln -s ~/MachineLearning/fast_neural_style-tensorflow/models/train2014 train2014
建立了符号链接train2014,
再 python train.py -c conf/wave.yml
还是报前述同样的错误。
我是否建立链接的位置不对?
TensorFlow初学者,写得太多了,占用了您的宝贵时间,非常渴望得到您的指点。
万分感谢!
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.