Comments (1)
Hi @Novicemonk,
well this is nothing related directly to this code repo, so I never mentioned it anywhere. However, both should not be hard to get, or? When you do inference you have predicted label and true label for each image in the validation set. Then you can group by true label and calculate the accuracy for each true class. Further more, once you have the the predicted class for an image just compare against the true label, if it's wrong you store the image path. Both should be straight forward, even with the code provided in e.g. the notebook
from finetune_alexnet_with_tensorflow.
Related Issues (20)
- Initializing problem HOT 1
- Loss function can not converge using the AdamOptimizer HOT 2
- How to visualize filters of connet layers. HOT 1
- Is trainable actually set to False in load_initial_weights? HOT 2
- Fine-Tuning Fails With Exception Between Epoch1 and Epoch2 HOT 1
- A question about the structure HOT 2
- A question about the tf.nn.dropout() HOT 3
- regarding to val.txt format HOT 1
- A question about the train_layers HOT 2
- Hello, what does this mistake mean? HOT 1
- data pre-processing before finetuning, divide by 255? HOT 2
- How
- How to use my .ckpt file to fill the sameple_submission.csv file in the dataset? HOT 1
- While running finetune.py I am getting following errors.Can anyone help me in correcting them HOT 2
- How to improve accuracy HOT 1
- how to find dataset
- ValueError: The initial value's shape (()) is not compatible with the explicitly supplied `shape` argument ([11, 11, 3, 96]).
- ValueError: Dimension size must be evenly divisible by 2 but is 1
- ValueError: Variable relative_positions_keys/embeddings_table already exists, disallowed. Did you mean to set reuse=True or reuse=tf.AUTO_REUSE in VarScope? Originally defined at: HOT 2
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 finetune_alexnet_with_tensorflow.