Skip to content

93% accuracy attained with a simple CNN #14

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
VicHofs wants to merge 12 commits into
base: master
Choose a base branch
from
Open

93% accuracy attained with a simple CNN #14

Changes from all commits
Commits
Show all changes
12 commits
Select commit Hold shift + click to select a range
6c76139
Create conv-net tensorflow model 93%
VicHofs Feb 3, 2020
a611f41
Notebook format
VicHofs Feb 3, 2020
fd3d574
conv-net TensorFlow model full code
VicHofs Feb 3, 2020
94877d7
Update k49 conv-net.ipynb
VicHofs Feb 3, 2020
c19b637
Add notebook format
VicHofs Feb 3, 2020
2b566f6
Delete k49 conv-net.ipynb
VicHofs Feb 3, 2020
72d85d9
Update k49 cnn notebook.ipynb
VicHofs Feb 3, 2020
9b829ce
Delete k49 cnn notebook.ipynb
VicHofs Feb 3, 2020
46e08b0
Add Notebook format
VicHofs Feb 3, 2020
2b063db
Update README.md
VicHofs Feb 3, 2020
abfd519
Delete conv-net tensorflow model
VicHofs Feb 18, 2020
0f53d3d
Delete k49 cnn notebook.ipynb
VicHofs Feb 18, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -91,6 +91,7 @@ Have more results to add to the table? Feel free to submit an [issue](https://gi
|[PCA + 4-kNN](https://github.com/rois-codh/kmnist/issues/10) | 97.76% | 93.98% | 86.80% | [dzisandy](https://github.com/dzisandy)
|[Tuned SVM (RBF kernel)](https://github.com/rois-codh/kmnist/issues/3) | 98.57% | 92.82%\* | 85.61%\* | [TomZephire](https://github.com/TomZephire)
|[Keras Simple CNN Benchmark](benchmarks/kuzushiji_mnist_cnn.py) |99.06% | 94.63% | 89.36% |
|[TensorFlow Simple CNN](https://github.com/VicHofs/kmnist/blob/master/k49%20cnn%20notebook.ipynb)| | | 93.00% | [Victor Hofstetter](https://github.com/VicHofs)
|PreActResNet-18 |99.56% | 97.82%\* |96.64%\*|
|PreActResNet-18 + Input Mixup |99.54% | 98.41%\* |97.04%\*|
|PreActResNet-18 + Manifold Mixup |99.54% | 98.83%\* | 97.33%\* |
Expand Down