This commit is contained in:
Yin Li 2020-04-21 12:34:14 -04:00
parent 5adf6cbac6
commit 356e28c31f

View File

@ -2,6 +2,16 @@
Neural network emulators to transform field/map data
* [Installation](#installation)
* [Usage](#usage)
* [Data](#data)
* [Data normalization](#data-normalization)
* [Model](#model)
* [Training](#training)
* [Files generated](#files-generated)
* [Tracking](#tracking)
## Installation
Install in editable mode
@ -17,7 +27,7 @@ Take a look at the examples in `scripts/*.slurm`, and the command line options
in `map2map/args.py` or by `m2m.py -h`.
### data
### Data
Structure your data to start with the channel axis and then the spatial
dimensions.
@ -25,13 +35,13 @@ Put each sample in one file.
Specify the data path with glob patterns.
#### data normalization
#### Data normalization
Input and target (output) data can be normalized by functions defined in
`map2map2/data/norms/`.
### model
### Model
Find the models in `map2map/models/`.
Customize the existing models, or add new models there and edit the `__init__.py`.