metadata
library_name: tf-keras
pipeline_tag: text-to-image
tags:
- keras-dreambooth
- nature
- cat
title: Dreambooth Seymour Cat Model
emoji: 🐱
colorFrom: orange
colorTo: brown
pinned: false
Model description
This is a model trained on pictures of Seymour, an orange cat. It was trained by Pedro Pacheco. The HuggingFace Space for this can be found here.
Intended uses & limitations
This was made for the March 2023 HuggingFace Keras Dreambooth Sprint.
Training and evaluation data
5 pictures of Seymour.
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
| Hyperparameters | Value |
|---|---|
| inner_optimizer.class_name | Custom>RMSprop |
| inner_optimizer.config.name | RMSprop |
| inner_optimizer.config.weight_decay | None |
| inner_optimizer.config.clipnorm | None |
| inner_optimizer.config.global_clipnorm | None |
| inner_optimizer.config.clipvalue | None |
| inner_optimizer.config.use_ema | False |
| inner_optimizer.config.ema_momentum | 0.99 |
| inner_optimizer.config.ema_overwrite_frequency | 100 |
| inner_optimizer.config.jit_compile | True |
| inner_optimizer.config.is_legacy_optimizer | False |
| inner_optimizer.config.learning_rate | 0.0010000000474974513 |
| inner_optimizer.config.rho | 0.9 |
| inner_optimizer.config.momentum | 0.0 |
| inner_optimizer.config.epsilon | 1e-07 |
| inner_optimizer.config.centered | False |
| dynamic | True |
| initial_scale | 32768.0 |
| dynamic_growth_steps | 2000 |
| training_precision | mixed_float16 |