PVNet 5.0.14__py3-none-any.whl → 5.0.16__py3-none-any.whl

pvnet/models/base_model.py

@@ -1,5 +1,4 @@
 """Base model for all PVNet submodels"""
-import copy
 import logging
 import os
 import shutil
@@ -12,9 +11,7 @@ import torch
 import yaml
 from huggingface_hub import ModelCard, ModelCardData, snapshot_download
 from huggingface_hub.hf_api import HfApi
-from ocf_data_sampler.numpy_sample.common_types import TensorBatch
 from safetensors.torch import load_file, save_file
-from torchvision.transforms.functional import center_crop
 
 from pvnet.utils import (
     DATA_CONFIG_NAME,
@@ -437,69 +434,6 @@ class BaseModel(torch.nn.Module, HuggingfaceMixin):
         else:
             self.num_output_features = self.forecast_len
 
-    def _adapt_batch(self, batch: TensorBatch) -> TensorBatch:
-        """Slice batches into appropriate shapes for model.
-
-        Returns a new batch dictionary with adapted data, leaving the original batch unchanged.
-        We make some specific assumptions about the original batch and the derived sliced batch:
-        - We are only limiting the future projections. I.e. we are never shrinking the batch from
-          the left hand side of the time axis, only slicing it from the right
-        - We are only shrinking the spatial crop of the satellite and NWP data
-
-        """
-        # Create a copy of the batch to avoid modifying the original
-        new_batch = {key: copy.deepcopy(value) for key, value in batch.items()}
-
-        if "gsp" in new_batch.keys():
-            # Slice off the end of the GSP data
-            gsp_len = self.forecast_len + self.history_len + 1
-            new_batch["gsp"] = new_batch["gsp"][:, :gsp_len]
-            new_batch["gsp_time_utc"] = new_batch["gsp_time_utc"][:, :gsp_len]
-
-        if "site" in new_batch.keys():
-            # Slice off the end of the site data
-            site_len = self.forecast_len + self.history_len + 1
-            new_batch["site"] = new_batch["site"][:, :site_len]
-
-            # Slice all site related datetime coordinates and features
-            site_time_keys = [
-                "site_time_utc",
-                "site_date_sin",
-                "site_date_cos",
-                "site_time_sin",
-                "site_time_cos",
-            ]
-
-            for key in site_time_keys:
-                if key in new_batch.keys():
-                    new_batch[key] = new_batch[key][:, :site_len]
-
-        if self.include_sat:
-            # Slice off the end of the satellite data and spatially crop
-            # Shape: batch_size, seq_length, channel, height, width
-            new_batch["satellite_actual"] = center_crop(
-                new_batch["satellite_actual"][:, : self.sat_sequence_len],
-                output_size=self.sat_encoder.image_size_pixels,
-            )
-
-        if self.include_nwp:
-            # Slice off the end of the NWP data and spatially crop
-            for nwp_source in self.nwp_encoders_dict:
-                # shape: batch_size, seq_len, n_chans, height, width
-                new_batch["nwp"][nwp_source]["nwp"] = center_crop(
-                    new_batch["nwp"][nwp_source]["nwp"],
-                    output_size=self.nwp_encoders_dict[nwp_source].image_size_pixels,
-                )[:, : self.nwp_encoders_dict[nwp_source].sequence_length]
-
-        if self.include_sun:
-            sun_len = self.forecast_len + self.history_len + 1
-            # Slice off end of solar coords
-            for s in ["solar_azimuth", "solar_elevation"]:
-                if s in new_batch.keys():
-                    new_batch[s] = new_batch[s][:, :sun_len]
-
-        return new_batch
-
     def _quantiles_to_prediction(self, y_quantiles: torch.Tensor) -> torch.Tensor:
         """
         Convert network prediction into a point prediction.
@@ -517,4 +451,4 @@ class BaseModel(torch.nn.Module, HuggingfaceMixin):
         """
         # y_quantiles Shape: batch_size, seq_length, num_quantiles
         idx = self.output_quantiles.index(0.5)
-        return y_quantiles[..., idx]
+        return y_quantiles[..., idx]

pvnet/models/late_fusion/encoders/basic_blocks.py

@@ -31,6 +31,7 @@ class AbstractNWPSatelliteEncoder(nn.Module, metaclass=ABCMeta):
         self.out_features = out_features
         self.image_size_pixels = image_size_pixels
         self.sequence_length = sequence_length
+        self.in_channels = in_channels
 
     @abstractmethod
     def forward(self):

pvnet/models/late_fusion/late_fusion.py

@@ -61,7 +61,6 @@ class LateFusionModel(BaseModel):
         nwp_interval_minutes: DictConfig | None = None,
         pv_interval_minutes: int = 5,
         sat_interval_minutes: int = 5,
-        adapt_batches: bool = False,
     ):
         """Neural network which combines information from different sources.
 
@@ -110,9 +109,6 @@ class LateFusionModel(BaseModel):
                 data for each source
             pv_interval_minutes: The interval between each sample of the PV data
             sat_interval_minutes: The interval between each sample of the satellite data
-            adapt_batches: If set to true, we attempt to slice the batches to the expected shape for
-                the model to use. This allows us to overprepare batches and slice from them for the
-                data we need for a model run.
         """
         super().__init__(
             history_minutes=history_minutes,
@@ -134,7 +130,6 @@ class LateFusionModel(BaseModel):
         self.add_image_embedding_channel = add_image_embedding_channel
         self.interval_minutes = interval_minutes
         self.min_sat_delay_minutes = min_sat_delay_minutes
-        self.adapt_batches = adapt_batches
 
         if self.location_id_mapping is None:
             logger.warning(
@@ -272,9 +267,6 @@ class LateFusionModel(BaseModel):
     def forward(self, x: TensorBatch) -> torch.Tensor:
         """Run model forward"""
 
-        if self.adapt_batches:
-            x = self._adapt_batch(x)
-
         if self.use_id_embedding:
             # eg: x['gsp_id'] = [1] with location_id_mapping = {1:0}, would give [0]
             id = torch.tensor(

pvnet/training/lightning_module.py

@@ -15,6 +15,7 @@ from pvnet.data.base_datamodule import collate_fn
 from pvnet.models.base_model import BaseModel
 from pvnet.optimizers import AbstractOptimizer
 from pvnet.training.plots import plot_sample_forecasts, wandb_line_plot
+from pvnet.utils import validate_batch_against_config
 
 
 class PVNetLightningModule(pl.LightningModule):
@@ -42,9 +43,6 @@ class PVNetLightningModule(pl.LightningModule):
         # This setting is only used when lr is tuned with callback
         self.lr = None
 
-        # Set up store for all all validation results so we can log these
-        self.save_all_validation_results = save_all_validation_results
-
     def transfer_batch_to_device(
         self, 
         batch: TensorBatch, 
@@ -105,10 +103,6 @@ class PVNetLightningModule(pl.LightningModule):
         """Run training step"""
         y_hat = self.model(batch)
 
-        # Batch may be adapted in the model forward method, would need adapting here too
-        if self.model.adapt_batches:
-            batch = self.model._adapt_batch(batch)
-
         y = batch[self.model._target_key][:, -self.model.forecast_len :]
 
         losses = self._calculate_common_losses(y, y_hat)
@@ -193,7 +187,7 @@ class PVNetLightningModule(pl.LightningModule):
         self._val_horizon_maes: list[np.array] = []
         if self.current_epoch==0:
             self._val_persistence_horizon_maes: list[np.array] = []
-        
+
         # Plot some sample forecasts
         val_dataset = self.trainer.val_dataloaders.dataset
 
@@ -209,13 +203,17 @@ class PVNetLightningModule(pl.LightningModule):
 
             batch = collate_fn([val_dataset[i] for i in idxs])
             batch = self.transfer_batch_to_device(batch, self.device, dataloader_idx=0)
+
+            # Batch validation check only during sanity check phase - use first batch
+            if self.trainer.sanity_checking and plot_num == 0:
+                validate_batch_against_config(
+                    batch=batch,
+                    model=self.model
+                )
+            
             with torch.no_grad():
                 y_hat = self.model(batch)
             
-            # Batch may be adapted in the model forward method, would need adapting here too
-            if self.model.adapt_batches:
-                batch = self.model._adapt_batch(batch)
-            
             fig = plot_sample_forecasts(
                 batch,
                 y_hat,
@@ -235,9 +233,6 @@ class PVNetLightningModule(pl.LightningModule):
         """Run validation step"""
 
         y_hat = self.model(batch)
-        # Batch may be adapted in the model forward method, would need adapting here too
-        if self.model.adapt_batches:
-            batch = self.model._adapt_batch(batch)
 
         # Internally store the val predictions
         self._store_val_predictions(batch, y_hat)
@@ -317,7 +312,7 @@ class PVNetLightningModule(pl.LightningModule):
             self.log_dict(extreme_error_metrics, on_step=False, on_epoch=True)
 
             # Optionally save all validation results - these are overridden each epoch
-            if self.save_all_validation_results:
+            if self.hparams.save_all_validation_results:
                 # Add attributes
                 ds_val_results.attrs["epoch"] = self.current_epoch
 

pvnet/training/train.py

@@ -26,7 +26,6 @@ from pvnet.utils import (
 log = logging.getLogger(__name__)
 
 
-
 def resolve_monitor_loss(output_quantiles: list | None) -> str:
     """Return the desired metric to monitor based on whether quantile regression is being used.
 

pvnet/utils.py

@@ -1,11 +1,15 @@
 """Utils"""
 import logging
+from typing import TYPE_CHECKING
 
 import rich.syntax
 import rich.tree
 from lightning.pytorch.utilities import rank_zero_only
 from omegaconf import DictConfig, OmegaConf
 
+if TYPE_CHECKING:
+    from pvnet.models.base_model import BaseModel
+
 logger = logging.getLogger(__name__)
 
 
@@ -79,6 +83,7 @@ def print_config(
         branch = tree.add(field, style=style, guide_style=style)
 
         config_section = config.get(field)
+
         branch_content = str(config_section)
         if isinstance(config_section, DictConfig):
             branch_content = OmegaConf.to_yaml(config_section, resolve=resolve)
@@ -86,3 +91,67 @@ def print_config(
         branch.add(rich.syntax.Syntax(branch_content, "yaml"))
 
     rich.print(tree)
+
+
+def validate_batch_against_config(
+    batch: dict, 
+    model: "BaseModel",
+) -> None:
+    """Validates tensor shapes in batch against model configuration."""
+    logger.info("Performing batch shape validation against model config.")
+    
+    # NWP validation
+    if hasattr(model, 'nwp_encoders_dict'):
+        if "nwp" not in batch:
+            raise ValueError(
+                "Model configured with 'nwp_encoders_dict' but 'nwp' data missing from batch."
+            )
+            
+        for source, nwp_data in batch["nwp"].items():
+            if source in model.nwp_encoders_dict:
+
+                enc = model.nwp_encoders_dict[source]                
+                expected_channels = enc.in_channels
+                if model.add_image_embedding_channel:
+                    expected_channels -= 1
+
+                expected = (nwp_data["nwp"].shape[0], enc.sequence_length, 
+                           expected_channels, enc.image_size_pixels, enc.image_size_pixels)
+                if tuple(nwp_data["nwp"].shape) != expected:
+                    actual_shape = tuple(nwp_data['nwp'].shape)
+                    raise ValueError(
+                        f"NWP.{source} shape mismatch: expected {expected}, got {actual_shape}"
+                    )
+
+    # Satellite validation
+    if hasattr(model, 'sat_encoder'):
+        if "satellite_actual" not in batch:
+            raise ValueError(
+                "Model configured with 'sat_encoder' but 'satellite_actual' missing from batch."
+            )
+
+        enc = model.sat_encoder
+        expected_channels = enc.in_channels
+        if model.add_image_embedding_channel:
+            expected_channels -= 1
+
+        expected = (batch["satellite_actual"].shape[0], enc.sequence_length, expected_channels, 
+                enc.image_size_pixels, enc.image_size_pixels)
+        if tuple(batch["satellite_actual"].shape) != expected:
+            actual_shape = tuple(batch['satellite_actual'].shape)
+            raise ValueError(f"Satellite shape mismatch: expected {expected}, got {actual_shape}")
+
+    # GSP/Site validation
+    key = model._target_key
+    if key in batch:
+        total_minutes = model.history_minutes + model.forecast_minutes
+        interval = model.interval_minutes
+        expected_len = total_minutes // interval + 1
+        expected = (batch[key].shape[0], expected_len)
+        if tuple(batch[key].shape) != expected:
+            actual_shape = tuple(batch[key].shape)
+            raise ValueError(
+                f"{key.upper()} shape mismatch: expected {expected}, got {actual_shape}"
+            )
+
+    logger.info("Batch shape validation successful!")

{pvnet-5.0.14.dist-info → pvnet-5.0.16.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: PVNet
-Version: 5.0.14
+Version: 5.0.16
 Summary: PVNet
 Author-email: Peter Dudfield <info@openclimatefix.org>
 Requires-Python: >=3.11
@@ -14,7 +14,6 @@ Requires-Dist: xarray
 Requires-Dist: h5netcdf
 Requires-Dist: torch>=2.0.0
 Requires-Dist: lightning
-Requires-Dist: torchvision
 Requires-Dist: typer
 Requires-Dist: sqlalchemy
 Requires-Dist: fsspec[s3]

{pvnet-5.0.14.dist-info → pvnet-5.0.16.dist-info}/RECORD

@@ -1,19 +1,19 @@
 pvnet/__init__.py,sha256=TAZm88TJ5ieL1XjEyRg1LciIGuSScEucdAruQLfM92I,25
 pvnet/load_model.py,sha256=LzN06O3oXzqhj1Dh_VlschDTxOq_Eea0OWDxrrboSKw,3726
 pvnet/optimizers.py,sha256=1N4b-Xd6QiIrcUU8cbU326bbFC0BvMNIV8VYWtGILJc,6548
-pvnet/utils.py,sha256=h4w9nmx6V_IAtiRp6VQ90TmQZGGTdMzU63WfGmL-pPs,2666
+pvnet/utils.py,sha256=iHG0wlN_cITKXpR16w54fs2R68wkX7vy3a_6f4SuanY,5414
 pvnet/data/__init__.py,sha256=FFD2tkLwEw9YiAVDam3tmaXNWMKiKVMHcnIz7zXCtrg,191
 pvnet/data/base_datamodule.py,sha256=Ibz0RoSr15HT6tMCs6ftXTpMa-NOKAmEd5ky55MqEK0,8615
 pvnet/data/site_datamodule.py,sha256=-KGxirGCBXVwcCREsjFkF7JDfa6NICv8bBDV6EILF_Q,962
 pvnet/data/uk_regional_datamodule.py,sha256=KA2_7DYuSggmD5b-XiXshXq8xmu36BjtFmy_pS7e4QE,1017
 pvnet/models/__init__.py,sha256=owzZ9xkD0DRTT51mT2Dx_p96oJjwDz57xo_MaMIEosk,145
-pvnet/models/base_model.py,sha256=sdVWUuJivQYmfK0CF2wzv8Hm-C50lJ--zttMScRYirY,19203
+pvnet/models/base_model.py,sha256=CnQaaf2kAdOcXqo1319nWa120mHfLQiwOQ639m4OzPk,16182
 pvnet/models/ensemble.py,sha256=1mFUEsl33kWcLL5d7zfDm9ypWxgAxBHgBiJLt0vwTeg,2363
 pvnet/models/late_fusion/__init__.py,sha256=Jf0B-E0_5IvSBFoj1wvnPtwYDxs4pRIFm5qHv--Bbps,26
 pvnet/models/late_fusion/basic_blocks.py,sha256=_cYGVyAIyEJS4wd-DEAXQXu0br66guZJn3ugoebWqZ0,1479
-pvnet/models/late_fusion/late_fusion.py,sha256=Lz4qrhIwVz7hrIR2sOzOoWAL2rKWWmUREIAtQs0zI8c,16131
+pvnet/models/late_fusion/late_fusion.py,sha256=VpP1aY646iO-JBlYkyoBlj0Z-gzsqaHnMgpNzjTqAIo,15735
 pvnet/models/late_fusion/encoders/__init__.py,sha256=bLBQdnCeLYhwISW0t88ZZBz-ebS94m7ZwBcsofWMHR4,51
-pvnet/models/late_fusion/encoders/basic_blocks.py,sha256=N8CZCQUwydmBip10AHY5hSkwrSP12B_Mrvm-5XVcz1s,3005
+pvnet/models/late_fusion/encoders/basic_blocks.py,sha256=DGkFFIZv4S4FLTaAIOrAngAFBpgZQHfkGM4dzezZLk4,3044
 pvnet/models/late_fusion/encoders/encoders3d.py,sha256=i8POpAsdNFwdnx64Hn7Zm9q9bby8qMPn7G7miwhsxGk,6645
 pvnet/models/late_fusion/linear_networks/__init__.py,sha256=16dLdGfH4QWNrI1fUB-cXWx24lArqo2lWIjdUCWbcBY,96
 pvnet/models/late_fusion/linear_networks/basic_blocks.py,sha256=RnwdeuX_-itY4ncM0NphZ5gRSOpogo7927XIlZJ9LM0,2787
@@ -22,11 +22,11 @@ pvnet/models/late_fusion/site_encoders/__init__.py,sha256=QoUiiWWFf12vEpdkw0gO4T
 pvnet/models/late_fusion/site_encoders/basic_blocks.py,sha256=iEB_N7ZL5HMQ1hZM6H32A71GCwP7YbErUx0oQF21PQM,1042
 pvnet/models/late_fusion/site_encoders/encoders.py,sha256=k4z690cfcP6J4pm2KtDujHN-W3uOl7QY0WvBIu1tM8c,11703
 pvnet/training/__init__.py,sha256=FKxmPZ59Vuj5_mXomN4saJ3En5M-aDMxSs6OttTQOcg,49
-pvnet/training/lightning_module.py,sha256=GVqdi5ALFo9-_WRYeyMMj2qH_k4gPxQ2sG6FhL_wRFE,13242
+pvnet/training/lightning_module.py,sha256=TkvLtOPswRtTIwcmAvNOSHg2RvIMzHsJVvs_d0xiRmQ,12891
 pvnet/training/plots.py,sha256=4xID7TBA4IazaARaCN5AoG5fFPJF1wIprn0y6I0C31c,2469
-pvnet/training/train.py,sha256=zj9JMi9C6W68vGsQUBapWkJ4aDzDuJFMv0IVjO73s1k,5215
-pvnet-5.0.14.dist-info/licenses/LICENSE,sha256=tKUnlSmcLBWMJWkHx3UjZGdrjs9LidGwLo0jsBUBAwU,1077
-pvnet-5.0.14.dist-info/METADATA,sha256=FJMwH-1nLPAkE6zsgtdQeofXdWoJn3qzEpUU9ltWn_s,18044
-pvnet-5.0.14.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-pvnet-5.0.14.dist-info/top_level.txt,sha256=4mg6WjeW05SR7pg3-Q4JRE2yAoutHYpspOsiUzYVNv0,6
-pvnet-5.0.14.dist-info/RECORD,,
+pvnet/training/train.py,sha256=1tDA34ianCRfilS0yEeIpR9nsQWaJiiZfTD2qRUmgEc,5214
+pvnet-5.0.16.dist-info/licenses/LICENSE,sha256=tKUnlSmcLBWMJWkHx3UjZGdrjs9LidGwLo0jsBUBAwU,1077
+pvnet-5.0.16.dist-info/METADATA,sha256=d0m-tj088qPWfu3s9CMgUCWNbDaf8LCYXpGP1PN0Idg,18017
+pvnet-5.0.16.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+pvnet-5.0.16.dist-info/top_level.txt,sha256=4mg6WjeW05SR7pg3-Q4JRE2yAoutHYpspOsiUzYVNv0,6
+pvnet-5.0.16.dist-info/RECORD,,