n2v-sem-demo: add README and training parameters

models/n2v-sem-demo/README.md

@@ -0,0 +1,14 @@
+## References
+
+This is a demo N2V model, trained on an inverted SEM image (1690x2500px), reference:
+
+> Buchholz, T. et al. - Content-aware image restoration for electron microscopy. Methods in Cell Biology, Volume 152 p.277-289, ISSN 0091-679X (2019) doi: https://doi.org/10.1016/bs.mch.2019.05.001
+
+N2V is a method for unsupervised content aware denoising.
+
+> Krull, A. and Buchholz, T. and Jug, F. Noise2void - learning denoising from single noisy images. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019)  doi: arXiv:1811.10980
+
+## Source code
+
+- N2V in Python: https://github.com/juglab/n2v/
+- N2V in Java (Fiji): https://github.com/juglab/N2V_fiji/

models/n2v-sem-demo/n2v-sem-demo.model.yaml

@@ -15,7 +15,7 @@ license: BSD 3
 format_version: 0.1.0
 language: java
 framework: tensorflow
-source: de.csbdresden.n2v.train.N2VTraining
+source: de.csbdresden.n2v.train.N2VPrediction
 inputs:
 - name: raw
   axes: byxc
@@ -34,6 +34,10 @@ outputs:
     reference_input: raw
     scale: [1, 1, 1, 1]
     offset: [0, 0, 0, 0]
+training:
+  source: de.csbdresden.n2v.train.N2VTraining
+  kwargs: {batchDimLength: 180, batchSize: 64, trainDimensions: 2, neighborhoodRadius: 5, numEpochs: 100,
+    numStepsPerEpoch: 300, patchDimLength: 60, stepsFinished: 30000}
 prediction:
   preprocess:
     spec: de.csbdresden.n2v.predict.N2VPrediction::preprocess