update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language: en
|
3 |
+
license: apache-2.0
|
4 |
+
library_name: diffusers
|
5 |
+
tags: []
|
6 |
+
datasets: huggan/flowers-102-categories
|
7 |
+
metrics: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information the training script had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# ddpm-ema-flowers-64
|
14 |
+
|
15 |
+
## Model description
|
16 |
+
|
17 |
+
This diffusion model is trained with the [🤗 Diffusers](https://github.com/huggingface/diffusers) library
|
18 |
+
on the `huggan/flowers-102-categories` dataset.
|
19 |
+
|
20 |
+
## Intended uses & limitations
|
21 |
+
|
22 |
+
#### How to use
|
23 |
+
|
24 |
+
```python
|
25 |
+
# TODO: add an example code snippet for running this diffusion pipeline
|
26 |
+
```
|
27 |
+
|
28 |
+
#### Limitations and bias
|
29 |
+
|
30 |
+
[TODO: provide examples of latent issues and potential remediations]
|
31 |
+
|
32 |
+
## Training data
|
33 |
+
|
34 |
+
[TODO: describe the data used to train the model]
|
35 |
+
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 0.0001
|
40 |
+
- train_batch_size: 16
|
41 |
+
- eval_batch_size: 16
|
42 |
+
- gradient_accumulation_steps: 1
|
43 |
+
- optimizer: AdamW with betas=(0.95, 0.999), weight_decay=1e-06 and epsilon=1e-08
|
44 |
+
- lr_scheduler: cosine
|
45 |
+
- lr_warmup_steps: 500
|
46 |
+
- ema_inv_gamma: 1.0
|
47 |
+
- ema_inv_gamma: 0.75
|
48 |
+
- ema_inv_gamma: 0.9999
|
49 |
+
- mixed_precision: no
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
📈 [TensorBoard logs](https://huggingface.co/anton-l/ddpm-ema-flowers-64/tensorboard?#scalars)
|
54 |
+
|