mengrang / dfl-cnn-tensorflow Goto Github PK
View Code? Open in Web Editor NEWTF-Implementation of "Learning a Discriminative Filter Bank within a CNN for Fine-grained Recognition"
dfl-cnn-tensorflow's People
Contributors
Stargazers
Watchers
Forkers
tqdavid fxle mhgcc zgsxwsdxg doublezies yuzhang0122 sankin1770 hit-hancg zongking123 zccdl chaucergit monoloxo shadowclouds alphagowisdom wlp1996 hanrui56 yc139464127dfl-cnn-tensorflow's Issues
训练问题
您好，大概看了一下您的源码。您在训练的时候，train_op = tf.group([train_fc,train_net]),这个操作我没理解错的话，是不是先优化一次全连接层，然后优化一次整个网络。常规的做法不是先只优化全连接层，然后最后fine-tuing entire network吗？
您好，请问数据集的文件目录是怎么组织的啊
我按照您的代码和数据集，训练的时候
feed_dict={input_images: batch_x, y_true: batch_y,keep_prob: 1., learning_rate: lr,clip_value: clipvalue})
部分报错，发现是input_images和batch_x的格式对不上，一个是(12, 448, 448, 3)，一个是(12,)。我检查了很久，没有明白那个数据集里图片哪里读取错误。我是直接把train和valid两个压缩包解压放在一个plants文件夹下的。您的数据集文件组织是怎样的啊
关于数据集
您好，您是对数据集进行了什么处理吗？因为我看 trainingset 和 validationset 中图片数量与 config.py 文件中定义的数量并不一致，想知道您进行了什么处理。还有在运行 dfb_train.py 文件时，会报错误：ValueError: setting an array element with a sequence. 这和上面的问题有关系吗？谢谢！
About Accuracy
hi,
I`m working on reimplementing "Learning a Discriminative Filter Bank Within a CNN for Fine-Grained Recognition" now, but I cannot get the result in the paper, do you get the same accuracy listed in the paper?
Ian
没有环境的编号
没有环境的编号
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.