Upload README.md with huggingface_hub

README.md

@@ -1,25 +1,59 @@
 ---
+language:
+- en
+license: apache-2.0
 library_name: keras
----
+tags:
+- doe2vec
+- exploratory-landscape-analysis
+- autoencoders
+datasets:
+- doe2vec-d2-m8-ls24-VAE-kl0.001
+metrics:
+- mse
 
 ## Model description
 
-More information needed
+DoE2Vec model that can transform any design of experiments (function landscape) to a feature vector.  
+For different input dimensions or sample size you require a different model.  
+Each model name is build up like doe2vec-d{dimension\}-m{sample size}-ls{latent size}-{AE or VAE}-kl{Kl loss weight}
 
-## Intended uses & limitations
+Example code of loading this huggingface model using the doe2vec package.
 
-More information needed
+First install the package
 
-## Training and evaluation data
+    pip install doe2vec
 
-More information needed
+Then import and load the model.
 
-## Training procedure
 
-### Training hyperparameters
+    from doe2vec import doe_model
+
+    obj = doe_model(
+        2,
+        8,
+        latent_dim=24,
+        kl_weight=0.001,
+        model_type="VAE"
+    )
+    obj.load_from_huggingface()
+    #test the model
+    obj.plot_label_clusters_bbob()
+
+## Intended uses & limitations
+
+The model is intended to be used to generate feature representations for optimization function landscapes.
+The representations can then be used for downstream tasks such as automatic optimization pipelines and meta-learning.
+
+
+## Training procedure
 
-The following hyperparameters were used during training:
+The model is trained using a weighed KL loss and mean squared error reconstruction loss.
+The model is trained using 250.000 randomly generated functions (see the dataset) over 100 epochs.
 
-| name | learning_rate | decay | beta_1 | beta_2 | epsilon | amsgrad | training_precision |
-|----|-------------|-----|------|------|-------|-------|------------------|
-|Adam|0.0010000000474974513|0.0|0.8999999761581421|0.9990000128746033|1e-07|False|float32|
+co2_eq_emissions:
+  emissions: 0.0363
+  source: "code carbon"
+  training_type: "pre-training"
+  geographical_location: "Leiden, The Netherlands"
+  hardware_used: "1 Tesla T4"