Here are the hands-on materials to practice deep learning segmentation with UNet (Keras/TF2): TP_UNET_TF2.zip
This archive contains jupyter notebooks and necessary functions (i.e. all the code in python). See another post to install TF2/Keras with conda.
The data are available here: dlss21_ho4_data.tar.gz
The command line to extract the data is:
$ tar xzf dlss21_ho4_data.tar.gz
The pre-trained model is here : Unet_f32_b16_l5_do0.1_Std_BN_input96.h5
The following big archive (581MB) contains everything (notebooks, data, pre-trained network) that can be ran out of the box: TP_UNET_TF2_FULL.zip