Github action: auto-update.

neuraloperator · Jan 14, 2025 · cd17408 · cd17408
1 parent 7616357
commit cd17408
Show file tree

Hide file tree

Showing 38 changed files with 179 additions and 179 deletions.
diff --git a/dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip b/dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip
diff --git a/dev/_downloads/0d78e075dd52a34e158d7f5f710dfe89/plot_incremental_FNO_darcy.zip b/dev/_downloads/0d78e075dd52a34e158d7f5f710dfe89/plot_incremental_FNO_darcy.zip
diff --git a/dev/_downloads/20c43dd37baf603889c4dc23e93bdb60/plot_count_flops.zip b/dev/_downloads/20c43dd37baf603889c4dc23e93bdb60/plot_count_flops.zip
diff --git a/dev/_downloads/3864a2d85c7ce11adeac9580559229ab/plot_darcy_flow.zip b/dev/_downloads/3864a2d85c7ce11adeac9580559229ab/plot_darcy_flow.zip
diff --git a/dev/_downloads/3faf9d2eaee5cc8e9f1c631c002ce544/plot_darcy_flow_spectrum.zip b/dev/_downloads/3faf9d2eaee5cc8e9f1c631c002ce544/plot_darcy_flow_spectrum.zip
diff --git a/dev/_downloads/4e1cba46bb51062a073424e1efbaad57/plot_DISCO_convolutions.zip b/dev/_downloads/4e1cba46bb51062a073424e1efbaad57/plot_DISCO_convolutions.zip
diff --git a/dev/_downloads/5e60095ce99919773daa83384f767e02/plot_SFNO_swe.zip b/dev/_downloads/5e60095ce99919773daa83384f767e02/plot_SFNO_swe.zip
diff --git a/dev/_downloads/645da00b8fbbb9bb5cae877fd0f31635/plot_FNO_darcy.zip b/dev/_downloads/645da00b8fbbb9bb5cae877fd0f31635/plot_FNO_darcy.zip
diff --git a/dev/_downloads/6f1e7a639e0699d6164445b55e6c116d/auto_examples_jupyter.zip b/dev/_downloads/6f1e7a639e0699d6164445b55e6c116d/auto_examples_jupyter.zip
diff --git a/dev/_downloads/7296405f6df7c2cfe184e9b258cee33e/checkpoint_FNO_darcy.zip b/dev/_downloads/7296405f6df7c2cfe184e9b258cee33e/checkpoint_FNO_darcy.zip
diff --git a/dev/_downloads/cefc537c5730a6b3e916b83c1fd313d6/plot_UNO_darcy.zip b/dev/_downloads/cefc537c5730a6b3e916b83c1fd313d6/plot_UNO_darcy.zip
diff --git a/dev/_images/sphx_glr_plot_SFNO_swe_001.png b/dev/_images/sphx_glr_plot_SFNO_swe_001.png
diff --git a/dev/_images/sphx_glr_plot_SFNO_swe_thumb.png b/dev/_images/sphx_glr_plot_SFNO_swe_thumb.png
diff --git a/dev/_images/sphx_glr_plot_UNO_darcy_001.png b/dev/_images/sphx_glr_plot_UNO_darcy_001.png
diff --git a/dev/_images/sphx_glr_plot_UNO_darcy_thumb.png b/dev/_images/sphx_glr_plot_UNO_darcy_thumb.png
diff --git a/dev/_images/sphx_glr_plot_darcy_flow_spectrum_001.png b/dev/_images/sphx_glr_plot_darcy_flow_spectrum_001.png
diff --git a/dev/_images/sphx_glr_plot_darcy_flow_spectrum_thumb.png b/dev/_images/sphx_glr_plot_darcy_flow_spectrum_thumb.png
diff --git a/dev/_sources/auto_examples/plot_DISCO_convolutions.rst.txt b/dev/_sources/auto_examples/plot_DISCO_convolutions.rst.txt
@@ -357,7 +357,7 @@ in order to compute the convolved image, we need to first bring it into the righ
  .. code-block:: none
 
 
-    <matplotlib.colorbar.Colorbar object at 0x7f44118dad50>
+    <matplotlib.colorbar.Colorbar object at 0x7f5bc149ed50>
 
 
 
@@ -448,7 +448,7 @@ in order to compute the convolved image, we need to first bring it into the righ
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (0 minutes 33.625 seconds)
+   **Total running time of the script:** (0 minutes 33.080 seconds)
 
 
 .. _sphx_glr_download_auto_examples_plot_DISCO_convolutions.py:

diff --git a/dev/_sources/auto_examples/plot_FNO_darcy.rst.txt b/dev/_sources/auto_examples/plot_FNO_darcy.rst.txt
@@ -248,13 +248,13 @@ Training the model
     )
 
     ### SCHEDULER ###
-     <torch.optim.lr_scheduler.CosineAnnealingLR object at 0x7f44176c56d0>
+     <torch.optim.lr_scheduler.CosineAnnealingLR object at 0x7f5bbea88910>
 
     ### LOSSES ###
 
-     * Train: <neuralop.losses.data_losses.H1Loss object at 0x7f44176c6490>
+     * Train: <neuralop.losses.data_losses.H1Loss object at 0x7f5bbea8a0d0>
 
-     * Test: {'h1': <neuralop.losses.data_losses.H1Loss object at 0x7f44176c6490>, 'l2': <neuralop.losses.data_losses.LpLoss object at 0x7f44176c7c50>}
+     * Test: {'h1': <neuralop.losses.data_losses.H1Loss object at 0x7f5bbea8a0d0>, 'l2': <neuralop.losses.data_losses.LpLoss object at 0x7f5bbea88690>}
 
 
 
@@ -311,22 +311,22 @@ Then train the model on our small Darcy-Flow dataset:
     Training on 1000 samples
     Testing on [50, 50] samples         on resolutions [16, 32].
     Raw outputs of shape torch.Size([32, 1, 16, 16])
-    [0] time=2.48, avg_loss=0.6956, train_err=21.7383
+    [0] time=2.44, avg_loss=0.6956, train_err=21.7383
     Eval: 16_h1=0.4298, 16_l2=0.3487, 32_h1=0.5847, 32_l2=0.3542
-    [3] time=2.49, avg_loss=0.2103, train_err=6.5705
+    [3] time=2.44, avg_loss=0.2103, train_err=6.5705
     Eval: 16_h1=0.2030, 16_l2=0.1384, 32_h1=0.5075, 32_l2=0.1774
-    [6] time=2.48, avg_loss=0.1911, train_err=5.9721
+    [6] time=2.44, avg_loss=0.1911, train_err=5.9721
     Eval: 16_h1=0.2099, 16_l2=0.1374, 32_h1=0.4907, 32_l2=0.1783
-    [9] time=2.48, avg_loss=0.1410, train_err=4.4073
+    [9] time=2.45, avg_loss=0.1410, train_err=4.4073
     Eval: 16_h1=0.2052, 16_l2=0.1201, 32_h1=0.5268, 32_l2=0.1615
     [12] time=2.47, avg_loss=0.1422, train_err=4.4434
     Eval: 16_h1=0.2131, 16_l2=0.1285, 32_h1=0.5413, 32_l2=0.1741
-    [15] time=2.54, avg_loss=0.1198, train_err=3.7424
+    [15] time=2.45, avg_loss=0.1198, train_err=3.7424
     Eval: 16_h1=0.1984, 16_l2=0.1137, 32_h1=0.5255, 32_l2=0.1569
-    [18] time=2.51, avg_loss=0.1104, train_err=3.4502
+    [18] time=2.47, avg_loss=0.1104, train_err=3.4502
     Eval: 16_h1=0.2039, 16_l2=0.1195, 32_h1=0.5062, 32_l2=0.1603
 
-    {'train_err': 2.9605126455426216, 'avg_loss': 0.0947364046573639, 'avg_lasso_loss': None, 'epoch_train_time': 2.4854582740000524}
+    {'train_err': 2.9605126455426216, 'avg_loss': 0.0947364046573639, 'avg_lasso_loss': None, 'epoch_train_time': 2.4835143990000006}
 
 
 
@@ -476,7 +476,7 @@ are other ways to scale the outputs of the FNO to train a true super-resolution
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (0 minutes 50.864 seconds)
+   **Total running time of the script:** (0 minutes 50.349 seconds)
 
 
 .. _sphx_glr_download_auto_examples_plot_FNO_darcy.py:

diff --git a/dev/_sources/auto_examples/plot_SFNO_swe.rst.txt b/dev/_sources/auto_examples/plot_SFNO_swe.rst.txt
@@ -234,13 +234,13 @@ Creating the losses
     )
 
     ### SCHEDULER ###
-     <torch.optim.lr_scheduler.CosineAnnealingLR object at 0x7f4424acd550>
+     <torch.optim.lr_scheduler.CosineAnnealingLR object at 0x7f5bcfdd1550>
 
     ### LOSSES ###
 
-     * Train: <neuralop.losses.data_losses.LpLoss object at 0x7f4424acef90>
+     * Train: <neuralop.losses.data_losses.LpLoss object at 0x7f5bcfdd2f90>
 
-     * Test: {'l2': <neuralop.losses.data_losses.LpLoss object at 0x7f4424acef90>}
+     * Test: {'l2': <neuralop.losses.data_losses.LpLoss object at 0x7f5bcfdd2f90>}
 
 
 
@@ -297,22 +297,22 @@ Train the model on the spherical SWE dataset
     Training on 200 samples
     Testing on [50, 50] samples         on resolutions [(32, 64), (64, 128)].
     Raw outputs of shape torch.Size([4, 3, 32, 64])
-    [0] time=3.56, avg_loss=2.6878, train_err=10.7511
-    Eval: (32, 64)_l2=2.0013, (64, 128)_l2=2.4464
-    [3] time=3.57, avg_loss=0.4203, train_err=1.6812
-    Eval: (32, 64)_l2=0.4162, (64, 128)_l2=2.7454
-    [6] time=3.50, avg_loss=0.2803, train_err=1.1213
-    Eval: (32, 64)_l2=0.3612, (64, 128)_l2=2.6383
-    [9] time=3.53, avg_loss=0.2307, train_err=0.9230
-    Eval: (32, 64)_l2=0.3089, (64, 128)_l2=2.6235
-    [12] time=3.52, avg_loss=0.2006, train_err=0.8024
-    Eval: (32, 64)_l2=0.2687, (64, 128)_l2=2.5915
-    [15] time=3.47, avg_loss=0.1704, train_err=0.6818
-    Eval: (32, 64)_l2=0.2401, (64, 128)_l2=2.5568
-    [18] time=3.53, avg_loss=0.1463, train_err=0.5853
-    Eval: (32, 64)_l2=0.2272, (64, 128)_l2=2.5580
+    [0] time=3.43, avg_loss=2.6140, train_err=10.4559
+    Eval: (32, 64)_l2=1.5768, (64, 128)_l2=2.4202
+    [3] time=3.45, avg_loss=0.3724, train_err=1.4896
+    Eval: (32, 64)_l2=0.3977, (64, 128)_l2=2.4189
+    [6] time=3.38, avg_loss=0.2915, train_err=1.1659
+    Eval: (32, 64)_l2=0.3378, (64, 128)_l2=2.3679
+    [9] time=3.39, avg_loss=0.2507, train_err=1.0026
+    Eval: (32, 64)_l2=0.2562, (64, 128)_l2=2.3166
+    [12] time=3.38, avg_loss=0.2074, train_err=0.8296
+    Eval: (32, 64)_l2=0.2287, (64, 128)_l2=2.3166
+    [15] time=3.38, avg_loss=0.1902, train_err=0.7608
+    Eval: (32, 64)_l2=0.1995, (64, 128)_l2=2.2783
+    [18] time=3.36, avg_loss=0.1740, train_err=0.6961
+    Eval: (32, 64)_l2=0.2096, (64, 128)_l2=2.2698
 
-    {'train_err': 0.55643718957901, 'avg_loss': 0.1391092973947525, 'avg_lasso_loss': None, 'epoch_train_time': 3.4575020479999807}
+    {'train_err': 0.6447638177871704, 'avg_loss': 0.1611909544467926, 'avg_lasso_loss': None, 'epoch_train_time': 3.366909286000009}
 
 
 
@@ -383,7 +383,7 @@ In practice we would train a Neural Operator on one or multiple GPUs
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (1 minutes 25.958 seconds)
+   **Total running time of the script:** (1 minutes 23.215 seconds)
 
 
 .. _sphx_glr_download_auto_examples_plot_SFNO_swe.py:

diff --git a/dev/_sources/auto_examples/plot_UNO_darcy.rst.txt b/dev/_sources/auto_examples/plot_UNO_darcy.rst.txt
@@ -345,13 +345,13 @@ Creating the losses
     )
 
     ### SCHEDULER ###
-     <torch.optim.lr_scheduler.CosineAnnealingLR object at 0x7f441fd34410>
+     <torch.optim.lr_scheduler.CosineAnnealingLR object at 0x7f5bcfb34410>
 
     ### LOSSES ###
 
-     * Train: <neuralop.losses.data_losses.H1Loss object at 0x7f4424bc2f90>
+     * Train: <neuralop.losses.data_losses.H1Loss object at 0x7f5bcfec6a50>
 
-     * Test: {'h1': <neuralop.losses.data_losses.H1Loss object at 0x7f4424bc2f90>, 'l2': <neuralop.losses.data_losses.LpLoss object at 0x7f441fd351d0>}
+     * Test: {'h1': <neuralop.losses.data_losses.H1Loss object at 0x7f5bcfec6a50>, 'l2': <neuralop.losses.data_losses.LpLoss object at 0x7f5bcfb351d0>}
 
 
 
@@ -410,22 +410,22 @@ Actually train the model on our small Darcy-Flow dataset
     Training on 1000 samples
     Testing on [50, 50] samples         on resolutions [16, 32].
     Raw outputs of shape torch.Size([32, 1, 16, 16])
-    [0] time=10.13, avg_loss=0.6277, train_err=19.6169
-    Eval: 16_h1=0.3908, 16_l2=0.2531, 32_h1=0.8497, 32_l2=0.5628
-    [3] time=10.01, avg_loss=0.2390, train_err=7.4677
-    Eval: 16_h1=0.2661, 16_l2=0.1821, 32_h1=0.7915, 32_l2=0.5232
-    [6] time=10.06, avg_loss=0.2445, train_err=7.6407
-    Eval: 16_h1=0.2785, 16_l2=0.1834, 32_h1=0.7741, 32_l2=0.4839
-    [9] time=9.96, avg_loss=0.2181, train_err=6.8151
-    Eval: 16_h1=0.2662, 16_l2=0.1616, 32_h1=0.7805, 32_l2=0.4683
-    [12] time=10.12, avg_loss=0.1823, train_err=5.6964
-    Eval: 16_h1=0.3160, 16_l2=0.2223, 32_h1=0.7456, 32_l2=0.4743
-    [15] time=9.97, avg_loss=0.1574, train_err=4.9193
-    Eval: 16_h1=0.2520, 16_l2=0.1663, 32_h1=0.7680, 32_l2=0.4271
-    [18] time=10.01, avg_loss=0.1625, train_err=5.0769
-    Eval: 16_h1=0.2389, 16_l2=0.1537, 32_h1=0.7389, 32_l2=0.4555
+    [0] time=9.94, avg_loss=0.6462, train_err=20.1926
+    Eval: 16_h1=0.3830, 16_l2=0.2502, 32_h1=0.8540, 32_l2=0.6235
+    [3] time=9.82, avg_loss=0.2409, train_err=7.5296
+    Eval: 16_h1=0.2677, 16_l2=0.1713, 32_h1=0.8255, 32_l2=0.5751
+    [6] time=9.82, avg_loss=0.2110, train_err=6.5926
+    Eval: 16_h1=0.2473, 16_l2=0.1585, 32_h1=0.8126, 32_l2=0.5537
+    [9] time=9.85, avg_loss=0.2067, train_err=6.4586
+    Eval: 16_h1=0.3001, 16_l2=0.2035, 32_h1=0.8125, 32_l2=0.5389
+    [12] time=9.87, avg_loss=0.2028, train_err=6.3389
+    Eval: 16_h1=0.3074, 16_l2=0.1954, 32_h1=0.8299, 32_l2=0.4869
+    [15] time=9.84, avg_loss=0.1606, train_err=5.0182
+    Eval: 16_h1=0.2506, 16_l2=0.1702, 32_h1=0.7811, 32_l2=0.5287
+    [18] time=9.89, avg_loss=0.1676, train_err=5.2381
+    Eval: 16_h1=0.2629, 16_l2=0.1638, 32_h1=0.8032, 32_l2=0.4799
 
-    {'train_err': 4.322231197729707, 'avg_loss': 0.13831139832735062, 'avg_lasso_loss': None, 'epoch_train_time': 10.025138579000043}
+    {'train_err': 4.385094230994582, 'avg_loss': 0.14032301539182662, 'avg_lasso_loss': None, 'epoch_train_time': 9.902361848000055}
 
 
 
@@ -499,7 +499,7 @@ In practice we would train a Neural Operator on one or multiple GPUs
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (3 minutes 23.580 seconds)
+   **Total running time of the script:** (3 minutes 20.840 seconds)
 
 
 .. _sphx_glr_download_auto_examples_plot_UNO_darcy.py:

diff --git a/dev/_sources/auto_examples/plot_count_flops.rst.txt b/dev/_sources/auto_examples/plot_count_flops.rst.txt
@@ -80,7 +80,7 @@ This output is organized as a defaultdict object that counts the FLOPS used in e
 
  .. code-block:: none
 
-    defaultdict(<function FlopTensorDispatchMode.__init__.<locals>.<lambda> at 0x7f4424a76d40>, {'': defaultdict(<class 'int'>, {'convolution.default': 2982150144, 'bmm.default': 138412032}), 'lifting': defaultdict(<class 'int'>, {'convolution.default': 562036736}), 'lifting.fcs.0': defaultdict(<class 'int'>, {'convolution.default': 25165824}), 'lifting.fcs.1': defaultdict(<class 'int'>, {'convolution.default': 536870912}), 'fno_blocks': defaultdict(<class 'int'>, {'convolution.default': 2147483648, 'bmm.default': 138412032}), 'fno_blocks.fno_skips.0': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.fno_skips.0.conv': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.convs.0': defaultdict(<class 'int'>, {'bmm.default': 34603008}), 'fno_blocks.channel_mlp.0': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.channel_mlp.0.fcs.0': defaultdict(<class 'int'>, {'convolution.default': 134217728}), 'fno_blocks.channel_mlp.0.fcs.1': defaultdict(<class 'int'>, {'convolution.default': 134217728}), 'fno_blocks.fno_skips.1': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.fno_skips.1.conv': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.convs.1': defaultdict(<class 'int'>, {'bmm.default': 34603008}), 'fno_blocks.channel_mlp.1': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.channel_mlp.1.fcs.0': defaultdict(<class 'int'>, {'convolution.default': 134217728}), 'fno_blocks.channel_mlp.1.fcs.1': defaultdict(<class 'int'>, {'convolution.default': 134217728}), 'fno_blocks.fno_skips.2': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.fno_skips.2.conv': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.convs.2': defaultdict(<class 'int'>, {'bmm.default': 34603008}), 'fno_blocks.channel_mlp.2': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.channel_mlp.2.fcs.0': defaultdict(<class 'int'>, {'convolution.default': 134217728}), 'fno_blocks.channel_mlp.2.fcs.1': defaultdict(<class 'int'>, {'convolution.default': 134217728}), 'fno_blocks.fno_skips.3': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.fno_skips.3.conv': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.convs.3': defaultdict(<class 'int'>, {'bmm.default': 34603008}), 'fno_blocks.channel_mlp.3': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.channel_mlp.3.fcs.0': defaultdict(<class 'int'>, {'convolution.default': 134217728}), 'fno_blocks.channel_mlp.3.fcs.1': defaultdict(<class 'int'>, {'convolution.default': 134217728}), 'projection': defaultdict(<class 'int'>, {'convolution.default': 272629760}), 'projection.fcs.0': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'projection.fcs.1': defaultdict(<class 'int'>, {'convolution.default': 4194304})})
+    defaultdict(<function FlopTensorDispatchMode.__init__.<locals>.<lambda> at 0x7f5bcfd7ad40>, {'': defaultdict(<class 'int'>, {'convolution.default': 2982150144, 'bmm.default': 138412032}), 'lifting': defaultdict(<class 'int'>, {'convolution.default': 562036736}), 'lifting.fcs.0': defaultdict(<class 'int'>, {'convolution.default': 25165824}), 'lifting.fcs.1': defaultdict(<class 'int'>, {'convolution.default': 536870912}), 'fno_blocks': defaultdict(<class 'int'>, {'convolution.default': 2147483648, 'bmm.default': 138412032}), 'fno_blocks.fno_skips.0': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.fno_skips.0.conv': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.convs.0': defaultdict(<class 'int'>, {'bmm.default': 34603008}), 'fno_blocks.channel_mlp.0': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.channel_mlp.0.fcs.0': defaultdict(<class 'int'>, {'convolution.default': 134217728}), 'fno_blocks.channel_mlp.0.fcs.1': defaultdict(<class 'int'>, {'convolution.default': 134217728}), 'fno_blocks.fno_skips.1': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.fno_skips.1.conv': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.convs.1': defaultdict(<class 'int'>, {'bmm.default': 34603008}), 'fno_blocks.channel_mlp.1': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.channel_mlp.1.fcs.0': defaultdict(<class 'int'>, {'convolution.default': 134217728}), 'fno_blocks.channel_mlp.1.fcs.1': defaultdict(<class 'int'>, {'convolution.default': 134217728}), 'fno_blocks.fno_skips.2': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.fno_skips.2.conv': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.convs.2': defaultdict(<class 'int'>, {'bmm.default': 34603008}), 'fno_blocks.channel_mlp.2': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.channel_mlp.2.fcs.0': defaultdict(<class 'int'>, {'convolution.default': 134217728}), 'fno_blocks.channel_mlp.2.fcs.1': defaultdict(<class 'int'>, {'convolution.default': 134217728}), 'fno_blocks.fno_skips.3': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.fno_skips.3.conv': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.convs.3': defaultdict(<class 'int'>, {'bmm.default': 34603008}), 'fno_blocks.channel_mlp.3': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.channel_mlp.3.fcs.0': defaultdict(<class 'int'>, {'convolution.default': 134217728}), 'fno_blocks.channel_mlp.3.fcs.1': defaultdict(<class 'int'>, {'convolution.default': 134217728}), 'projection': defaultdict(<class 'int'>, {'convolution.default': 272629760}), 'projection.fcs.0': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'projection.fcs.1': defaultdict(<class 'int'>, {'convolution.default': 4194304})})
 
 
 
@@ -125,7 +125,7 @@ To check the maximum FLOPS used during the forward pass, let's create a recursiv
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (0 minutes 3.150 seconds)
+   **Total running time of the script:** (0 minutes 3.098 seconds)
 
 
 .. _sphx_glr_download_auto_examples_plot_count_flops.py:

diff --git a/dev/_sources/auto_examples/plot_darcy_flow.rst.txt b/dev/_sources/auto_examples/plot_darcy_flow.rst.txt
@@ -163,7 +163,7 @@ Visualizing the data
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (0 minutes 0.317 seconds)
+   **Total running time of the script:** (0 minutes 0.319 seconds)
 
 
 .. _sphx_glr_download_auto_examples_plot_darcy_flow.py:

diff --git a/dev/_sources/auto_examples/plot_darcy_flow_spectrum.rst.txt b/dev/_sources/auto_examples/plot_darcy_flow_spectrum.rst.txt
@@ -219,7 +219,7 @@ Loading the Navier-Stokes dataset in 128x128 resolution
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (0 minutes 0.186 seconds)
+   **Total running time of the script:** (0 minutes 0.164 seconds)
 
 
 .. _sphx_glr_download_auto_examples_plot_darcy_flow_spectrum.py:

diff --git a/dev/_sources/auto_examples/plot_incremental_FNO_darcy.rst.txt b/dev/_sources/auto_examples/plot_incremental_FNO_darcy.rst.txt
@@ -240,15 +240,15 @@ Set up the losses
     )
 
     ### SCHEDULER ###
-     <torch.optim.lr_scheduler.CosineAnnealingLR object at 0x7f442548c2b0>
+     <torch.optim.lr_scheduler.CosineAnnealingLR object at 0x7f5bd617fce0>
 
     ### LOSSES ###
 
     ### INCREMENTAL RESOLUTION + GRADIENT EXPLAINED ###
 
-     * Train: <neuralop.losses.data_losses.H1Loss object at 0x7f44176ea5d0>
+     * Train: <neuralop.losses.data_losses.H1Loss object at 0x7f5bbead2850>
 
-     * Test: {'h1': <neuralop.losses.data_losses.H1Loss object at 0x7f44176ea5d0>, 'l2': <neuralop.losses.data_losses.LpLoss object at 0x7f4425d7bce0>}
+     * Test: {'h1': <neuralop.losses.data_losses.H1Loss object at 0x7f5bbead2850>, 'l2': <neuralop.losses.data_losses.LpLoss object at 0x7f5bd617ed70>}
 
 
 
@@ -333,7 +333,7 @@ Train the model
     Eval: 16_h1=0.8702, 16_l2=0.5536, 32_h1=0.9397, 32_l2=0.5586
     [1] time=0.21, avg_loss=0.7589, train_err=10.8413
     Eval: 16_h1=0.7880, 16_l2=0.5167, 32_h1=0.9011, 32_l2=0.5234
-    [2] time=0.21, avg_loss=0.6684, train_err=9.5484
+    [2] time=0.20, avg_loss=0.6684, train_err=9.5484
     Eval: 16_h1=0.7698, 16_l2=0.4235, 32_h1=0.9175, 32_l2=0.4405
     [3] time=0.21, avg_loss=0.6082, train_err=8.6886
     Eval: 16_h1=0.7600, 16_l2=0.4570, 32_h1=1.0126, 32_l2=0.5005
@@ -354,26 +354,26 @@ Train the model
     Incre Res Update: change res to 16
     [10] time=0.27, avg_loss=0.5158, train_err=7.3681
     Eval: 16_h1=0.5133, 16_l2=0.3167, 32_h1=0.6120, 32_l2=0.3022
-    [11] time=0.26, avg_loss=0.4536, train_err=6.4795
+    [11] time=0.25, avg_loss=0.4536, train_err=6.4795
     Eval: 16_h1=0.4680, 16_l2=0.3422, 32_h1=0.6436, 32_l2=0.3659
-    [12] time=0.27, avg_loss=0.4155, train_err=5.9358
+    [12] time=0.26, avg_loss=0.4155, train_err=5.9358
     Eval: 16_h1=0.4119, 16_l2=0.2692, 32_h1=0.5285, 32_l2=0.2692
-    [13] time=0.27, avg_loss=0.3724, train_err=5.3195
+    [13] time=0.26, avg_loss=0.3724, train_err=5.3195
     Eval: 16_h1=0.4045, 16_l2=0.2569, 32_h1=0.5620, 32_l2=0.2747
-    [14] time=0.27, avg_loss=0.3555, train_err=5.0783
+    [14] time=0.26, avg_loss=0.3555, train_err=5.0783
     Eval: 16_h1=0.3946, 16_l2=0.2485, 32_h1=0.5278, 32_l2=0.2523
-    [15] time=0.27, avg_loss=0.3430, train_err=4.8998
+    [15] time=0.26, avg_loss=0.3430, train_err=4.8998
     Eval: 16_h1=0.3611, 16_l2=0.2323, 32_h1=0.5079, 32_l2=0.2455
-    [16] time=0.27, avg_loss=0.3251, train_err=4.6438
+    [16] time=0.26, avg_loss=0.3251, train_err=4.6438
     Eval: 16_h1=0.3433, 16_l2=0.2224, 32_h1=0.4757, 32_l2=0.2351
-    [17] time=0.27, avg_loss=0.3072, train_err=4.3888
+    [17] time=0.26, avg_loss=0.3072, train_err=4.3888
     Eval: 16_h1=0.3458, 16_l2=0.2226, 32_h1=0.4776, 32_l2=0.2371
-    [18] time=0.27, avg_loss=0.2982, train_err=4.2593
+    [18] time=0.26, avg_loss=0.2982, train_err=4.2593
     Eval: 16_h1=0.3251, 16_l2=0.2116, 32_h1=0.4519, 32_l2=0.2245
-    [19] time=0.27, avg_loss=0.2802, train_err=4.0024
+    [19] time=0.26, avg_loss=0.2802, train_err=4.0024
     Eval: 16_h1=0.3201, 16_l2=0.2110, 32_h1=0.4533, 32_l2=0.2245
 
-    {'train_err': 4.002395851271493, 'avg_loss': 0.2801677095890045, 'avg_lasso_loss': None, 'epoch_train_time': 0.27010723700004746, '16_h1': tensor(0.3201), '16_l2': tensor(0.2110), '32_h1': tensor(0.4533), '32_l2': tensor(0.2245)}
+    {'train_err': 4.002395851271493, 'avg_loss': 0.2801677095890045, 'avg_lasso_loss': None, 'epoch_train_time': 0.26419909200001257, '16_h1': tensor(0.3201), '16_l2': tensor(0.2110), '32_h1': tensor(0.4533), '32_l2': tensor(0.2245)}
 
 
 
@@ -447,7 +447,7 @@ In practice we would train a Neural Operator on one or multiple GPUs
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (0 minutes 6.625 seconds)
+   **Total running time of the script:** (0 minutes 6.578 seconds)
 
 
 .. _sphx_glr_download_auto_examples_plot_incremental_FNO_darcy.py: