Update results for coGN on formation energy.

Author: PatReis

changelog.md

@@ -2,14 +2,14 @@ v3.0.1
 
 * Removed deprecated molecules.
 * Fix error in ``kgcnn.data.transform.scaler.serial``
-* Fix error in ``QMDataset`` for if attributes have been chosen. Now `set_attributes` does not cause an error.
+* Fix error in ``QMDataset`` if attributes have been chosen. Now `set_attributes` does not cause an error.
 * Fix error in ``QMDataset`` with labels without SDF file.
 * Fix error in ``kgcnn.layers.conv.GraphSageNodeLayer`` .
 * Add ``reverse_edge_indices`` option to `GraphDict.from_networkx` . Fixed error in connection with `kgcnn.crystal` .
-* Started with ``kgcnn.io.file`` . Experimental.
+* Started with ``kgcnn.io.file`` . Experimental. Will get more updates.
 * Fix error with `StandardLabelScaler` inheritance.
 * Added workflow notebook examples. 
-* 
+* Fix error in import ``kgcnn.crystal.periodic_table`` to now properly include package data.
 
 
 v3.0.0

kgcnn/io/file.py

@@ -29,6 +29,7 @@ def _check_for_inner_shape(array_list: List[np.ndarray]) -> Union[None, tuple, l
 
 
 class RaggedTensorNumpyFile:
+    """Class representing a NumPy '.npz' file to store a ragged tensor on disk."""
 
     _device = '/cpu:0'
 
@@ -105,6 +106,7 @@ def exists(self):
 
 
 class RaggedTensorHDFile:
+    """Class representing a HDF '.hdf5' file to store a ragged tensor on disk."""
 
     _device = '/cpu:0'
 

training/hyper/hyper_mp_jdft2d.py

@@ -511,16 +511,27 @@
             "cross_validation": {"class_name": "KFold",
                                  "config": {"n_splits": 5, "random_state": 42, "shuffle": True}},
             "fit": {
-                "batch_size": 32, "epochs": 1000, "validation_freq": 10, "verbose": 2,
+                "batch_size": 64, "epochs": 800, "validation_freq": 10, "verbose": 2,
                 "callbacks": [
-                    {"class_name": "kgcnn>LinearLearningRateScheduler", "config": {
-                        "learning_rate_start": 0.0005, "learning_rate_stop": 0.5e-05, "epo_min": 100, "epo": 1000,
-                        "verbose": 0}
-                     }
+                    # {"class_name": "kgcnn>LinearLearningRateScheduler", "config": {
+                    #     "learning_rate_start": 0.0005, "learning_rate_stop": 0.5e-05, "epo_min": 0, "epo": 800,
+                    #     "verbose": 0}
+                    #  }
                 ]
             },
             "compile": {
-                "optimizer": {"class_name": "Adam", "config": {"lr": 0.0005}},
+                "optimizer": {
+                    "class_name": "Adam",
+                    "config": {
+                        "learning_rate": {
+                            "class_name": "kgcnn>KerasPolynomialDecaySchedule",
+                            "config": {
+                                "dataset_size": 106.201, "batch_size": 64, "epochs": 800,
+                                "lr_start": 0.0005, "lr_stop": 1.0e-05
+                            }
+                        }
+                    }
+                },
                 "loss": "mean_absolute_error"
             },
             "scaler": {

training/results/MatProjectEFormDataset/coGN/coGN_MatProjectEFormDataset_score.yaml

@@ -0,0 +1,124 @@
+data_unit: eV/atom
+date_time: '2023-05-18 22:54:14'
+epochs:
+- 800
+- 800
+- 800
+- 800
+- 800
+execute_folds:
+- 4
+kgcnn_version: 3.0.1
+loss:
+- 0.0008860895759426057
+- 0.0008905278518795967
+- 0.0009073111577890813
+- 0.0009844396263360977
+- 0.0009256843477487564
+max_loss:
+- 0.17345885932445526
+- 0.17859020829200745
+- 0.1676129251718521
+- 0.17198680341243744
+- 0.17687316238880157
+max_scaled_mean_absolute_error:
+- 0.20188768208026886
+- 0.20766201615333557
+- 0.1948785036802292
+- 0.20020614564418793
+- 0.20556315779685974
+max_scaled_root_mean_squared_error:
+- 0.32694771885871887
+- 0.33746638894081116
+- 0.3113785982131958
+- 0.3249269425868988
+- 0.339813232421875
+max_val_loss:
+- 0.04921264201402664
+- 0.04789257422089577
+- 0.04781835153698921
+- 0.051487576216459274
+- 0.046009182929992676
+max_val_scaled_mean_absolute_error:
+- 0.057278186082839966
+- 0.055688779801130295
+- 0.05559692159295082
+- 0.059935588389635086
+- 0.053472232073545456
+max_val_scaled_root_mean_squared_error:
+- 0.0925888791680336
+- 0.09510543197393417
+- 0.09771958738565445
+- 0.09067843109369278
+- 0.10363566875457764
+min_loss:
+- 0.0008860895759426057
+- 0.0008905278518795967
+- 0.0009073111577890813
+- 0.0009844396263360977
+- 0.0009256843477487564
+min_scaled_mean_absolute_error:
+- 0.0010313139064237475
+- 0.0010354919359087944
+- 0.0010549012804403901
+- 0.0011459658853709698
+- 0.0010758370626717806
+min_scaled_root_mean_squared_error:
+- 0.009279688820242882
+- 0.009094045497477055
+- 0.008167327381670475
+- 0.008846502751111984
+- 0.008383971638977528
+min_val_loss:
+- 0.01455119252204895
+- 0.01417975127696991
+- 0.014507561922073364
+- 0.014709792099893093
+- 0.014524188823997974
+min_val_scaled_mean_absolute_error:
+- 0.016936026513576508
+- 0.016488006338477135
+- 0.01686747744679451
+- 0.01712336204946041
+- 0.016880128532648087
+min_val_scaled_root_mean_squared_error:
+- 0.041658543050289154
+- 0.04964727163314819
+- 0.04548873007297516
+- 0.04854537919163704
+- 0.05381939187645912
+model_class: make_model
+model_name: coGN
+model_version: ''
+multi_target_indices: null
+number_histories: 5
+scaled_mean_absolute_error:
+- 0.0010313139064237475
+- 0.0010354919359087944
+- 0.0010549012804403901
+- 0.0011459658853709698
+- 0.0010758370626717806
+scaled_root_mean_squared_error:
+- 0.009279688820242882
+- 0.009094045497477055
+- 0.008167327381670475
+- 0.008849424310028553
+- 0.008383971638977528
+val_loss:
+- 0.014554254710674286
+- 0.014186271466314793
+- 0.014507561922073364
+- 0.014712574891746044
+- 0.014524188823997974
+val_scaled_mean_absolute_error:
+- 0.01693958416581154
+- 0.01649557054042816
+- 0.01686747744679451
+- 0.017126601189374924
+- 0.016880128532648087
+val_scaled_root_mean_squared_error:
+- 0.04193956032395363
+- 0.05034559220075607
+- 0.045685552060604095
+- 0.04965636134147644
+- 0.054531652480363846

training/results/MatProjectEFormDataset/coGN/coGN_hyper.json

@@ -0,0 +1 @@
+{"model": {"module_name": "kgcnn.literature.coGN", "class_name": "make_model", "config": {"name": "coGN", "inputs": {"offset": {"shape": [null, 3], "name": "offset", "dtype": "float32", "ragged": true}, "cell_translation": null, "affine_matrix": null, "voronoi_ridge_area": null, "atomic_number": {"shape": [null], "name": "atomic_number", "dtype": "int32", "ragged": true}, "frac_coords": null, "coords": null, "multiplicity": {"shape": [null], "name": "multiplicity", "dtype": "int32", "ragged": true}, "lattice_matrix": null, "edge_indices": {"shape": [null, 2], "name": "edge_indices", "dtype": "int32", "ragged": true}, "line_graph_edge_indices": null}}}, "training": {"cross_validation": {"class_name": "KFold", "config": {"n_splits": 5, "random_state": 42, "shuffle": true}}, "fit": {"batch_size": 64, "epochs": 800, "validation_freq": 10, "verbose": 2, "callbacks": []}, "compile": {"optimizer": {"class_name": "Adam", "config": {"learning_rate": {"class_name": "kgcnn>KerasPolynomialDecaySchedule", "config": {"dataset_size": 106201, "batch_size": 64, "epochs": 800, "lr_start": 0.0005, "lr_stop": 1e-05}}}}, "loss": "mean_absolute_error"}, "scaler": {"class_name": "StandardScaler", "module_name": "kgcnn.data.transform.scaler.standard", "config": {"with_std": true, "with_mean": true, "copy": true}}, "multi_target_indices": null}, "data": {"dataset": {"class_name": "MatProjectEFormDataset", "module_name": "kgcnn.data.datasets.MatProjectEFormDataset", "config": {}, "methods": [{"set_representation": {"pre_processor": {"class_name": "KNNAsymmetricUnitCell", "module_name": "kgcnn.crystal.preprocessor", "config": {"k": 24}}, "reset_graphs": false}}]}, "data_unit": "eV/atom"}, "info": {"postfix": "", "postfix_file": "", "kgcnn_version": "3.0.1"}}