0.9.0 rc rebase 1

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -31,7 +31,7 @@ body:
     attributes:
       label: Version
       description: What version of Modulus are you running?
-      placeholder: "example: 0.8.0"
+      placeholder: "example: 0.9.0"
     validations:
       required: true
 

CHANGELOG.md

@@ -6,7 +6,23 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [0.9.0a0] - 2024-11-XX
+## [0.10.0a0] - 2025-01-XX
+
+### Added
+
+### Changed
+
+### Deprecated
+
+### Removed
+
+### Fixed
+
+### Security
+
+### Dependencies
+
+## [0.9.0] - 2024-12-04
 
 ### Added
 
@@ -32,16 +48,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Extended the checkpointing utility to store metadata.
 - Corrected missing export of loggin function used by transolver model
 
-### Deprecated
-
-### Removed
-
-### Fixed
-
-### Security
-
-### Dependencies
-
 ## [0.8.0] - 2024-09-24
 
 ### Added

modulus/__init__.py

@@ -19,4 +19,4 @@
 from .models.meta import ModelMetaData
 from .models.module import Module
 
-__version__ = "0.9.0a0"
+__version__ = "0.10.0a0"

modulus/datapipes/healpix/data_modules.py

@@ -285,7 +285,7 @@ def create_time_series_dataset_classic(
     for variable in all_variables:
         file_name = _get_file_name(src_directory, prefix, variable, suffix)
         logger.debug("open nc dataset %s", file_name)
-        if "sample" in list(xr.open_dataset(file_name).dims.keys()):
+        if "sample" in list(xr.open_dataset(file_name).sizes.keys()):
             ds = xr.open_dataset(file_name, chunks={"sample": batch_size}).rename(
                 {"sample": "time"}
             )

modulus/datapipes/healpix/timeseries_dataset.py

@@ -303,8 +303,8 @@ def _get_time_index(self, item):
             if self.forecast_mode
             else (item + 1) * self.batch_size + self._window_length
         )
-        if not self.drop_last and max_index > self.ds.dims["time"]:
-            batch_size = self.batch_size - (max_index - self.ds.dims["time"])
+        if not self.drop_last and max_index > self.ds.sizes["time"]:
+            batch_size = self.batch_size - (max_index - self.ds.sizes["time"])
         else:
             batch_size = self.batch_size
         return (start_index, max_index), batch_size

test/datapipes/test_lagrangian.py

@@ -60,8 +60,9 @@ def test_lagrangian_dataset_constructor(data_dir, device, pytestconfig):
     assert graph.ndata["y"].shape[-1] > 0  # node targets
 
 
+@import_or_fail(["tensorflow", "dgl"])
 @pytest.mark.parametrize("device", ["cuda:0", "cpu"])
-def test_graph_construction(device):
+def test_graph_construction(device, pytestconfig):
     from modulus.datapipes.gnn.lagrangian_dataset import compute_edge_index
 
     mesh_pos = torch.tensor([[0.0, 0.0], [0.01, 0.0], [1.0, 1.0]], device=device)

test/models/dlwp_healpix/test_healpix_layers.py

@@ -154,38 +154,34 @@ def test_HEALPixLayer_initialization(device, multiplier):
 def test_HEALPixLayer_forward(device, multiplier):
     layer = HEALPixLayer(layer=MulX, multiplier=multiplier)
 
+    kernel_size = 3
+    dilation = 2
+    in_channels = 4
+    out_channels = 8
+
     tensor_size = torch.randint(low=2, high=4, size=(1,)).tolist()
-    tensor_size = [24, 4, *tensor_size, *tensor_size]
+    tensor_size = [24, in_channels, *tensor_size, *tensor_size]
     invar = torch.rand(tensor_size, device=device)
     outvar = layer(invar)
 
     assert common.compare_output(outvar, invar * multiplier)
 
-    # test nhwc mode and dilation
     layer = HEALPixLayer(
         layer=torch.nn.Conv2d,
-        in_channels=4,
-        out_channels=8,
-        kernel_size=3,
+        in_channels=in_channels,
+        out_channels=out_channels,
+        kernel_size=kernel_size,
         device=device,
-        # dilation=4,
-    )
-
-    outvar = layer(invar)
-
-    layer = HEALPixLayer(
-        layer=torch.nn.Conv2d,
-        in_channels=4,
-        out_channels=8,
-        kernel_size=3,
-        device=device,
-        dilation=1,
+        dilation=dilation,
         enable_healpixpad=True,
         enable_nhwc=True,
     )
 
-    assert outvar.shape == layer(invar).shape
-    assert outvar.stride() != layer(invar).stride()
+    # size of the padding added byu HEALPixLayer
+    expected_shape = [24, out_channels, tensor_size[-1], tensor_size[-1]]
+    expected_shape = torch.Size(expected_shape)
+
+    assert expected_shape == layer(invar).shape
 
     del layer, outvar, invar
     torch.cuda.empty_cache()