DeepSharp.Learners.Networks
Where a DeepSharp network meets a DeepSharp pipeline: a network learns from the rows the pipeline hands over from its training split, every feature on one scale, is judged by its validation rows and never sees its test rows; the pipeline's report measures it in the answer's own units; what it predicts for a row served later comes back as a value, a probability, a price or a count, as the pipeline's way back gives it. The network and the pipeline it was trained behind are one file, which refuses to be read beside any other fit of that pipeline — and a checkpoint is the same file with what the run needs to go on.
Activity
- Latest release
- 3d ago
- Total releases
- 15
- Cadence
- ~daily
- Last 12 months
- 15
Details
- License
- MIT
- First release
- Sep 30, 2026
Releases
| Version | Released | |
|---|---|---|
0.17.0
minor
| ||
0.16.0
minor
| ||
0.15.0
minor
| ||
0.14.0
minor
| ||
0.13.0
minor
| ||
0.12.0
minor
| ||
0.11.0
minor
| ||
0.10.0
minor
| ||
0.9.0
minor
| ||
0.8.0
minor
| ||
0.7.1
patch
| ||
0.7.0
minor
| ||
0.6.1
minor
| ||
0.5.0
minor
| ||
0.4.0
initial
|