https://github.com/yeonghyeon/resnext-tf2
TensorFlow implementation of "Aggregated Residual Transformations for Deep Neural Networks"
https://github.com/yeonghyeon/resnext-tf2
convolutional-neural-network convolutional-neural-networks mnist mnist-classification
Last synced: 6 months ago
JSON representation
TensorFlow implementation of "Aggregated Residual Transformations for Deep Neural Networks"
- Host: GitHub
- URL: https://github.com/yeonghyeon/resnext-tf2
- Owner: YeongHyeon
- License: mit
- Created: 2020-02-25T07:51:12.000Z (over 5 years ago)
- Default Branch: master
- Last Pushed: 2020-05-18T04:56:38.000Z (over 5 years ago)
- Last Synced: 2025-03-29T08:43:55.182Z (6 months ago)
- Topics: convolutional-neural-network, convolutional-neural-networks, mnist, mnist-classification
- Language: Python
- Homepage:
- Size: 301 KB
- Stars: 5
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
[TensorFlow 2] Aggregated Residual Transformations for Deep Neural Networks
=====
TensorFlow implementation of "Aggregated Residual Transformations for Deep Neural Networks"
## Related Repositories
ResNet-TF2
WideResNet(WRN)-TF2
ResNet-with-LRWarmUp-TF2
ResNet-with-SGDR-TF2
## Concept
The three ways for construct ResNeXt block [1].
## Performance
|Indicator|Value|
|:---|:---:|
|Accuracy|0.99370|
|Precision|0.99371|
|Recall|0.99364|
|F1-Score|0.99367|
```
Confusion Matrix
[[ 977 0 1 0 0 0 0 0 2 0]
[ 0 1129 2 0 0 0 1 2 1 0]
[ 0 1 1026 0 1 0 0 3 1 0]
[ 0 0 2 1007 0 1 0 0 0 0]
[ 0 0 0 0 976 0 1 0 0 5]
[ 1 0 0 4 0 883 2 0 0 2]
[ 1 1 0 0 1 1 953 0 1 0]
[ 0 1 2 0 0 0 0 1024 1 0]
[ 2 0 2 1 0 0 0 2 965 2]
[ 0 1 0 0 4 2 0 3 2 997]]
Class-0 | Precision: 0.99592, Recall: 0.99694, F1-Score: 0.99643
Class-1 | Precision: 0.99647, Recall: 0.99471, F1-Score: 0.99559
Class-2 | Precision: 0.99130, Recall: 0.99419, F1-Score: 0.99274
Class-3 | Precision: 0.99506, Recall: 0.99703, F1-Score: 0.99604
Class-4 | Precision: 0.99389, Recall: 0.99389, F1-Score: 0.99389
Class-5 | Precision: 0.99549, Recall: 0.98991, F1-Score: 0.99269
Class-6 | Precision: 0.99582, Recall: 0.99478, F1-Score: 0.99530
Class-7 | Precision: 0.99033, Recall: 0.99611, F1-Score: 0.99321
Class-8 | Precision: 0.99178, Recall: 0.99076, F1-Score: 0.99127
Class-9 | Precision: 0.99105, Recall: 0.98811, F1-Score: 0.98958
Total | Accuracy: 0.99370, Precision: 0.99371, Recall: 0.99364, F1-Score: 0.99367
```
## Requirements
* Python 3.7.6
* Tensorflow 2.1.0
* Numpy 1.18.1
* Matplotlib 3.1.3
## Reference
[1] Saining Xi et al. (2016). Aggregated Residual Transformations for Deep Neural Networks. arXiv preprint arXiv:1611.05431.