# tf-examples

**Repository Path**: mirrors_CamDavidsonPilon/tf-examples

## Basic Information

- **Project Name**: tf-examples
- **Description**: my tf examples for now 
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2020-09-24
- **Last Updated**: 2026-03-07

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# README

### Lessons learned

1. If you see oscillating training loss, likely the descent steps are bouncing between two "valleys" - try using MomentumOptimizer.
2. Playing around with the step_size can help avoid non-covergence to nan
3. The std of the random_normal of the initial weights should be quite small (ex: `stddev=0.01`)
4. Also using RMSPropOptimizer really seems to help decrease the obj function (at least, better than the GradientDescent)