Add trained models

Author: mengliu1998

OpenDFT/QHBench/QH9/README.md

@@ -1,29 +1,29 @@
 # QH9: A Quantum Hamiltonian Prediction Benchmark
 
-[[Paper]](https://arxiv.org/abs/2306.09549)
+[[Paper]](https://arxiv.org/abs/2306.09549)(**NeurIPS**, Track on Datasets and Benchmarks, 2023)
 
 ## Introduction
 
 QH9 provides precise DFT-calculated Hamiltonian matrices for **2,399 molecular dynamics trajectories** and **130,831  stable molecular geometries**, based on the [QM9](http://quantum-machine.org/datasets/) dataset.
 
-In this repo, we provide both the QH9 dataset and the baseline models, which can be highly valuable for developing machine learning methods and accelerating molecular and materials design for scientific and technological applications.
+In this repo, we provide both the QH9 dataset and the benchmark code, which can be highly valuable for developing machine learning methods and accelerating molecular and materials design for scientific and technological applications.
 
 
 ## Tasks
 
 To comprehensively evaluate the quantum Hamiltonian prediction performance, we define the following tasks based on the obtained stable and dynamic geometries in the QH9 dataset. Please refer to our paper for details of these task setups.
 
-* **QH-stable-iid** 
-* **QH-stable-ood** 
-* **QH-dynamic-geo** 
-* **QH-dynamic-mol** 
+* **QH9-stable-id** 
+* **QH9-stable-ood** 
+* **QH9-dynamic-geo** 
+* **QH9-dynamic-mol** 
 
 | Task | # Total geometries | # Total molecules | # Training/validation/testing geometries|
 | -------- | -------- | -------- | -------- |
-|**QH-stable-iid** | 130, 831 | 130, 831 | 104, 664/13, 083/13, 084|
-|**QH-stable-ood** | 130, 831 | 130, 831 | 104, 001/17, 495/9, 335|
-|**QH-dynamic-geo** | 143, 940 | 2, 399 | 119, 950/11, 995/11, 995|
-|**QH-dynamic-mol** | 143, 940 | 2, 399 | 115, 140/14, 340/14, 460|
+|**QH9-stable-id** | 130, 831 | 130, 831 | 104, 664/13, 083/13, 084|
+|**QH9-stable-ood** | 130, 831 | 130, 831 | 104, 001/17, 495/9, 335|
+|**QH9-dynamic-geo** | 143, 940 | 2, 399 | 119, 950/11, 995/11, 995|
+|**QH9-dynamic-mol** | 143, 940 | 2, 399 | 115, 140/14, 340/14, 460|
 
 ## Requirement
 
@@ -38,17 +38,17 @@ Meanwhile, we provide the installation file, and you can build the environment b
 
 
 ## Dataset Usage
-We provide the datasets as commonly used PyG datasets. Here are simple examples to load our datasets with a few lines of code. Prior to that, you can download the `datasets` folder, which includes the raw data files `QH9Stable.db` and `QH9Dynamic.db`, via [this Google Drive link](https://drive.google.com/drive/folders/13pPgBh3XvN2FCpowfnA8TT4VJ0OTceNM?usp=sharing) and [OneDrive Link](https://tamucs-my.sharepoint.com/:f:/g/personal/haiyang_tamu_edu/Ev4XIVcumhVFtaI8lUkIHXABHkKnKgWSJ5LYZOo67UKO0g?e=tsXkT1). Meanwhile, we provide the zip files of the datasets in this [google drive link](https://drive.google.com/drive/u/0/folders/1LXTC8uaOQzmb76FsuGfwSocAbK5Hshfj).
+We provide the datasets as commonly used PyG datasets. Here are simple examples to load our datasets with a few lines of code. Prior to that, you can download the `datasets` folder, which includes the raw data files `QH9Stable.db` and `QH9Dynamic.db`, via [this Google Drive link](https://drive.google.com/drive/folders/13pPgBh3XvN2FCpowfnA8TT4VJ0OTceNM?usp=sharing) or [OneDrive Link](https://tamucs-my.sharepoint.com/:f:/g/personal/haiyang_tamu_edu/Ev4XIVcumhVFtaI8lUkIHXABHkKnKgWSJ5LYZOo67UKO0g?e=tsXkT1). Meanwhile, we provide the zip files of the datasets in this [google drive link](https://drive.google.com/drive/u/0/folders/1LXTC8uaOQzmb76FsuGfwSocAbK5Hshfj).
 
 ```python
 from torch_geometric.loader import DataLoader
 from datasets import QH9Stable, QH9Dynamic
 
 ### Use one of the following lines to Load the specific dataset
-dataset = QH9Stable(split='random')  # QH-stable-iid
-dataset = QH9Stable(split='size_ood')  # QH-stable-ood
-dataset = QH9Dynamic(split='geometry')  # QH-dynamic-geo
-dataset = QH9Dynamic(split='mol')  # QH-dynamic-mol
+dataset = QH9Stable(split='random')  # QH9-stable-id
+dataset = QH9Stable(split='size_ood')  # QH9-stable-ood
+dataset = QH9Dynamic(split='geometry')  # QH9-dynamic-geo
+dataset = QH9Dynamic(split='mol')  # QH9-dynamic-mol
 
 ### Get the training/validation/testing subsets
 train_dataset = dataset[dataset.train_mask]
@@ -62,17 +62,20 @@ test_data_loader = DataLoader(test_dataset, batch_size=32, shuffle=False)
 ```
 
 ## Baselines
-Equivariant quantum tensor network QHNet is selected as the main baseline method in the QH9 benchmark currently. QHNet has an extendable expansion module that is built upon intermediate full orbital matrices, enabling its capability to effectively handle different molecules. This flexibility allows QHNet to accommodate various molecules in the QH9 benchmark.
+Equivariant quantum tensor network [QHNet](https://arxiv.org/abs/2306.04922) is selected as the main baseline method in the QH9 benchmark currently. QHNet has an extendable expansion module that is built upon intermediate full orbital matrices, enabling its capability to effectively handle different molecules. This flexibility allows QHNet to accommodate various molecules in the QH9 benchmark.
 
 * Train the QHNet model
+
 ```shell script
 ### Modify the configurations in config/config.yaml (or pass the configurations as args) as needed, and then run
-python main.py datasets=QH9-stable datasets.split=random # QH-stable-iid
-python main.py datasets=QH9-stable datasets.split=size_ood # QH-stable-ood
-python main.py datasets=QH9-dynamic datasets.split=geometry # QH-stable-iid
-python main.py datasets=QH9-dynamic datasets.split=mol # QH-stable-iid
+python main.py datasets=QH9-stable datasets.split=random # QH9-stable-id
+python main.py datasets=QH9-stable datasets.split=size_ood # QH9-stable-ood
+python main.py datasets=QH9-dynamic datasets.split=geometry # QH9-stable-iid
+python main.py datasets=QH9-dynamic datasets.split=mol # QH9-stable-iid
 ```
 
+**Trained models**: our trained QHNet models on the defined tasks are available via [this Google Drive link](https://drive.google.com/drive/folders/10ebqIWLrZ672A9bFg9wLe48F-nsz7za3?usp=share_link).
+
 * Evaluate the trained model (in terms of MAE on Hamiltonian matrix, MAE on occupied orbital energies, and  cosine similarity of orbital coefficients)
 ```shell script
 ### Modify the configurations in config/config.yaml (or pass the configurations as args) as needed (including the trained_model arg), and then run