articles/Machine_Learning/code_examples at master · foobar167/articles

Name		Name	Last commit message	Last commit date
parent directory ..
2020.01.22_Logistic_Regression.ipynb		2020.01.22_Logistic_Regression.ipynb
ReadMe.md		ReadMe.md
callbacks_usage_in_training.ipynb		callbacks_usage_in_training.ipynb
deep_residual_unet_segmentation.ipynb		deep_residual_unet_segmentation.ipynb
tf_lite_conversion_examples.ipynb		tf_lite_conversion_examples.ipynb
unet_segmentation.ipynb		unet_segmentation.ipynb

ReadMe.md

Several callback examples (shareable link). Callbacks are used to stop training to avoid overfitting or if learning rate is enough.
U-Net segmentation (shareable link) is a convolutional neural network that was developed for biomedical image segmentation at the Computer Science Department of the University of Freiburg, Germany. Wiki link. The network is based on the fully convolutional network and its architecture was modified and extended to work with fewer training images and to yield more precise segmentations. Segmentation of a 512*512 image takes less than a second on a modern GPU.
Deep Residual U-Net (ResUNet) (shareable link) is based on residual neural network and U-Net.
TensorFlow Lite conversion examples for video course Introduction to TensorFlow Lite.
Logistic Regression (shareable link) is a fundamental classification technique. It’s a relatively uncomplicated linear classifier.