Need help with TensorFlow2.0_ResNet?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

calmisential
211 Stars 75 Forks MIT License 55 Commits 8 Opened issues

Description

A ResNet(ResNet18, ResNet34, ResNet50, ResNet101, ResNet152) implementation using TensorFlow-2.0.

Services available

!
?

Need anything else?

Contributors list

# 55,804
Python
mobilen...
incepti...
tensorf...
53 commits
# 159,447
Shell
cpp11
C
Jupyter...
1 commit

TensorFlow2.0_ResNet

A ResNet(ResNet18, ResNet34, ResNet50, ResNet101, ResNet152) implementation using TensorFlow-2.0

See https://github.com/calmisential/BasicCNNsTensorFlow2.0 for more CNNs.

Train

  1. Requirements:
  2. Python >= 3.6
  3. Tensorflow == 2.0.0
  4. To train the ResNet 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
    
  5. Run the script split_dataset.py to split the raw dataset into train set, valid set and test set.
  6. Change the corresponding parameters in config.py.
  7. 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:

References

  1. The original paper: https://arxiv.org/abs/1512.03385
  2. The TensorFlow official tutorials: https://tensorflow.google.cn/beta/tutorials/quickstart/advanced

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.