Upload folder using huggingface_hub

README.md

@@ -1,3 +1,55 @@
 ---
+language: en
 license: mit
+library_name: pytorch
 ---
+
+
+
+
+
+
+# PVNet2
+
+## Model Description
+
+<!-- Provide a longer summary of what this model is/does. -->
+This model class uses satellite data, numericl weather predictions, and recent Grid Service Point( GSP) PV power output to forecast the near-term (~8 hours) PV power output at all GSPs. More information can be found in the model repo [1] and experimental notes in [this google doc](https://docs.google.com/document/d/1fbkfkBzp16WbnCg7RDuRDvgzInA6XQu3xh4NCjV-WDA/edit?usp=sharing).
+
+- **Developed by:** openclimatefix
+- **Model type:** Fusion model
+- **Language(s) (NLP):** en
+- **License:** mit
+
+
+# Training Details
+
+## Data
+
+<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+The model is trained on data from 2017-2020 and validated on data from 2021. See experimental notes in the [the google doc](https://docs.google.com/document/d/1fbkfkBzp16WbnCg7RDuRDvgzInA6XQu3xh4NCjV-WDA/edit?usp=sharing) for more details.
+
+
+### Preprocessing
+
+Data is prepared with the `ocf_datapipes.training.pvnet` datapipe [2].
+
+
+## Results
+
+The training logs for the current model can be found [here on wandb](https://wandb.ai/openclimatefix/pvnet2.1/runs/None).
+
+The training logs for all model runs of PVNet2 can be found [here](https://wandb.ai/openclimatefix/pvnet2.1).
+
+Some experimental notes can be found at in [the google doc](https://docs.google.com/document/d/1fbkfkBzp16WbnCg7RDuRDvgzInA6XQu3xh4NCjV-WDA/edit?usp=sharing)
+
+
+### Hardware
+
+Trained on a single NVIDIA Tesla T4
+
+### Software
+
+- [1] https://github.com/openclimatefix/PVNet
+- [2] https://github.com/openclimatefix/ocf_datapipes

config.json

@@ -0,0 +1,65 @@
+{
+    "_target_": "pvnet.models.multimodal.multimodal.Model",
+    "output_quantiles": [
+        0.02,
+        0.1,
+        0.25,
+        0.5,
+        0.75,
+        0.9,
+        0.98
+    ],
+    "interval_minutes": 15,
+    "nwp_encoders_dict": {
+        "ecmwf": {
+            "_target_": "pvnet.models.multimodal.encoders.encoders3d.DefaultPVNet",
+            "_partial_": true,
+            "in_channels": 14,
+            "out_features": 256,
+            "number_of_conv3d_layers": 6,
+            "conv3d_channels": 32,
+            "image_size_pixels": 32
+        }
+    },
+    "wind_encoder": {
+        "_target_": "pvnet.models.multimodal.site_encoders.encoders.SingleAttentionNetwork",
+        "_partial_": true,
+        "num_sites": 1,
+        "out_features": 40,
+        "num_heads": 4,
+        "kdim": 40,
+        "id_embed_dim": 20
+    },
+    "output_network": {
+        "_target_": "pvnet.models.multimodal.linear_networks.networks.ResFCNet2",
+        "_partial_": true,
+        "fc_hidden_features": 128,
+        "n_res_blocks": 6,
+        "res_block_layers": 2,
+        "dropout_frac": 0.0
+    },
+    "embedding_dim": 16,
+    "include_sun": false,
+    "include_gsp_yield_history": false,
+    "forecast_minutes": 2880,
+    "history_minutes": 60,
+    "min_sat_delay_minutes": 60,
+    "sat_history_minutes": 90,
+    "nwp_history_minutes": {
+        "ecmwf": 60
+    },
+    "nwp_forecast_minutes": {
+        "ecmwf": 2880
+    },
+    "wind_history_minutes": 60,
+    "target_key": "wind",
+    "optimizer": {
+        "_target_": "pvnet.optimizers.EmbAdamWReduceLROnPlateau",
+        "lr": 0.0001,
+        "weight_decay": 0.01,
+        "amsgrad": true,
+        "patience": 5,
+        "factor": 0.1,
+        "threshold": 0.002
+    }
+}

data_config.yaml

@@ -0,0 +1,40 @@
+general:
+  description: Config for training the saved PVNet model
+  name: PVNet current
+input_data:
+  data_source_which_defines_geospatial_locations: wind
+  default_forecast_minutes: 2880
+  default_history_minutes: 60
+  nwp:
+    ecmwf:
+      forecast_minutes: 2880
+      history_minutes: 60
+      nwp_channels:
+      - hcc
+      - lcc
+      - mcc
+      - prate
+      - sde
+      - sr
+      - t2m
+      - tcc
+      - u10
+      - u100
+      - u200
+      - v10
+      - v100
+      - v200
+      nwp_image_size_pixels_height: 32
+      nwp_image_size_pixels_width: 32
+      nwp_provider: ecmwf
+      nwp_zarr_path: PLACEHOLDER.zarr
+      time_resolution_minutes: 60
+      x_dim_name: longitude
+      y_dim_name: latitude
+  wind:
+    get_center: true
+    n_wind_systems_per_example: 1
+    wind_files_groups:
+    - label: india
+      wind_filename: /mnt/storage_ssd_4tb/india_wind_data.nc
+      wind_metadata_filename: /mnt/storage_ssd_4tb/india_wind_metadata.csv

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6375c39f86d26aa0819ddf8d50e36f74b0870a2f56f1eb356154c8352ae6943
+size 330267466