Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -8,7 +8,7 @@ tags:
|
|
8 |
- exploratory-landscape-analysis
|
9 |
- autoencoders
|
10 |
datasets:
|
11 |
-
-
|
12 |
metrics:
|
13 |
- mse
|
14 |
co2_eq_emissions:
|
@@ -29,23 +29,26 @@ Example code of loading this huggingface model using the doe2vec package.
|
|
29 |
|
30 |
First install the package
|
31 |
|
32 |
-
|
|
|
|
|
33 |
|
34 |
Then import and load the model.
|
35 |
|
|
|
|
|
36 |
|
37 |
-
|
38 |
-
|
39 |
-
|
40 |
-
|
41 |
-
|
42 |
-
|
43 |
-
|
44 |
-
|
45 |
-
|
46 |
-
|
47 |
-
|
48 |
-
obj.plot_label_clusters_bbob()
|
49 |
|
50 |
## Intended uses & limitations
|
51 |
|
@@ -58,3 +61,6 @@ The representations can then be used for downstream tasks such as automatic opti
|
|
58 |
The model is trained using a weighed KL loss and mean squared error reconstruction loss.
|
59 |
The model is trained using 250.000 randomly generated functions (see the dataset) over 100 epochs.
|
60 |
|
|
|
|
|
|
|
|
8 |
- exploratory-landscape-analysis
|
9 |
- autoencoders
|
10 |
datasets:
|
11 |
+
- BasStein/250000-randomfunctions-2d
|
12 |
metrics:
|
13 |
- mse
|
14 |
co2_eq_emissions:
|
|
|
29 |
|
30 |
First install the package
|
31 |
|
32 |
+
```zsh
|
33 |
+
pip install doe2vec
|
34 |
+
```
|
35 |
|
36 |
Then import and load the model.
|
37 |
|
38 |
+
```python
|
39 |
+
from doe2vec import doe_model
|
40 |
|
41 |
+
obj = doe_model(
|
42 |
+
2,
|
43 |
+
8,
|
44 |
+
latent_dim=24,
|
45 |
+
kl_weight=0.001,
|
46 |
+
model_type="VAE"
|
47 |
+
)
|
48 |
+
obj.load_from_huggingface()
|
49 |
+
#test the model
|
50 |
+
obj.plot_label_clusters_bbob()
|
51 |
+
```
|
|
|
52 |
|
53 |
## Intended uses & limitations
|
54 |
|
|
|
61 |
The model is trained using a weighed KL loss and mean squared error reconstruction loss.
|
62 |
The model is trained using 250.000 randomly generated functions (see the dataset) over 100 epochs.
|
63 |
|
64 |
+
- **Hardware:** 1x Tesla T4 GPU
|
65 |
+
- **Optimizer:** Adam
|
66 |
+
|