Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/calmiLovesAI/TensorFlow2.0_InceptionV3
A TensorFlow_2.0 implementation of InceptionV3.
https://github.com/calmiLovesAI/TensorFlow2.0_InceptionV3
Last synced: 2 months ago
JSON representation
A TensorFlow_2.0 implementation of InceptionV3.
- Host: GitHub
- URL: https://github.com/calmiLovesAI/TensorFlow2.0_InceptionV3
- Owner: calmiLovesAI
- License: mit
- Created: 2019-08-18T12:24:42.000Z (over 5 years ago)
- Default Branch: master
- Last Pushed: 2019-11-05T07:12:04.000Z (about 5 years ago)
- Last Synced: 2024-10-04T20:02:37.865Z (3 months ago)
- Language: Python
- Homepage:
- Size: 35.2 KB
- Stars: 34
- Watchers: 4
- Forks: 11
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- Awesome-Tensorflow2 - calmisential/TensorFlow2.0_InceptionV3
README
# TensorFlow2.0_InceptionV3
A TensorFlow_2.0 implementation of InceptionV3.
See https://github.com/calmisential/Basic_CNNs_TensorFlow2.0 for more CNNs.
## Train
1. Requirements:
+ Python >= 3.6
+ Tensorflow == 2.0.0-rc2
2. To train the InceptionV3 on your own dataset, you can put the dataset under the folder **original dataset**, and the directory should look like this:
```
|——original dataset
|——class_name_0
|——class_name_1
|——class_name_2
|——class_name_3
```
3. Run the script **split_dataset.py** to split the raw dataset into train set, valid set and test set. The dataset directory will be like this:
```
|——dataset
|——train
|——class_name_1
|——class_name_2
......
|——class_name_n
|——valid
|——class_name_1
|——class_name_2
......
|——class_name_n
|—-test
|——class_name_1
|——class_name_2
......
|——class_name_n
```
4. Change the corresponding parameters in **config.py**.
5. Run **train.py** to start training.
## Evaluate
Run **evaluate.py** to evaluate the model's performance on the test dataset.
## The networks I have implemented with tensorflow2.0:
+ [ResNet34, ResNet50, ResNet101, ResNet152](https://github.com/calmisential/TensorFlow2.0_ResNet)
+ [InceptionV3](https://github.com/calmisential/TensorFlow2.0_InceptionV3)
## References
1. The original paper :https://arxiv.org/abs/1512.00567
2. Google official implementation of InceptionV3 (TensorFlow 1.x): https://github.com/tensorflow/models/blob/master/research/slim/nets/inception_v3.py
3. https://www.jianshu.com/p/3bbf0675cfce
4. Official PyTorch implementation of InceptionV3 : https://github.com/pytorch/vision/blob/master/torchvision/models/inception.py