-
Notifications
You must be signed in to change notification settings - Fork 29
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Alexandria add download bash script (#281)
* bash script to download dataset * download dataset updated * exclude download of index.html * try-cath exceptions in alexandria example fixed * formatting fixed * natoms count fixed * fix json files --------- Co-authored-by: Massimiliano Lupo Pasini <mlupopa@login10.frontier.olcf.ornl.gov> Co-authored-by: Massimiliano Lupo Pasini <mlupopa@andes-login1.olcf.ornl.gov> Co-authored-by: Jong Choi <choij@ornl.gov>
- Loading branch information
1 parent
d1fb63d
commit 42b1a68
Showing
4 changed files
with
205 additions
and
119 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,58 +1,78 @@ | ||
{ | ||
"Verbosity": { | ||
"level": 2 | ||
}, | ||
"NeuralNetwork": { | ||
"Architecture": { | ||
"model_type": "EGNN", | ||
"equivariance": true, | ||
"radius": 5.0, | ||
"max_neighbours": 100000, | ||
"num_gaussians": 50, | ||
"envelope_exponent": 5, | ||
"int_emb_size": 64, | ||
"basis_emb_size": 8, | ||
"out_emb_size": 128, | ||
"num_after_skip": 2, | ||
"num_before_skip": 1, | ||
"num_radial": 6, | ||
"num_spherical": 7, | ||
"num_filters": 126, | ||
"edge_features": ["length"], | ||
"hidden_dim": 50, | ||
"num_conv_layers": 3, | ||
"output_heads": { | ||
"graph":{ | ||
"num_sharedlayers": 2, | ||
"dim_sharedlayers": 50, | ||
"num_headlayers": 2, | ||
"dim_headlayers": [50,25] | ||
} | ||
}, | ||
"task_weights": [1.0] | ||
}, | ||
"Variables_of_interest": { | ||
"input_node_features": [0, 1, 2, 3], | ||
"output_names": ["energy"], | ||
"output_index": [0], | ||
"output_dim": [1], | ||
"type": ["graph"] | ||
}, | ||
"Training": { | ||
"num_epoch": 50, | ||
"perc_train": 0.8, | ||
"loss_function_type": "mae", | ||
"batch_size": 32, | ||
"continue": 0, | ||
"Optimizer": { | ||
"type": "AdamW", | ||
"learning_rate": 1e-3 | ||
} | ||
"Verbosity": { | ||
"level": 2 | ||
}, | ||
"NeuralNetwork": { | ||
"Architecture": { | ||
"model_type": "EGNN", | ||
"equivariance": true, | ||
"radius": 5, | ||
"max_neighbours": 100000, | ||
"num_gaussians": 50, | ||
"envelope_exponent": 5, | ||
"int_emb_size": 64, | ||
"basis_emb_size": 8, | ||
"out_emb_size": 128, | ||
"num_after_skip": 2, | ||
"num_before_skip": 1, | ||
"num_radial": 6, | ||
"num_spherical": 7, | ||
"num_filters": 126, | ||
"edge_features": [ | ||
"length" | ||
], | ||
"hidden_dim": 50, | ||
"num_conv_layers": 3, | ||
"output_heads": { | ||
"graph": { | ||
"num_sharedlayers": 2, | ||
"dim_sharedlayers": 50, | ||
"num_headlayers": 2, | ||
"dim_headlayers": [ | ||
50, | ||
25 | ||
] | ||
} | ||
}, | ||
"task_weights": [ | ||
1 | ||
] | ||
}, | ||
"Variables_of_interest": { | ||
"input_node_features": [ | ||
0, | ||
1, | ||
2, | ||
3 | ||
], | ||
"output_names": [ | ||
"energy" | ||
], | ||
"output_index": [ | ||
0 | ||
], | ||
"output_dim": [ | ||
1 | ||
], | ||
"type": [ | ||
"graph" | ||
] | ||
}, | ||
"Visualization": { | ||
"plot_init_solution": true, | ||
"plot_hist_solution": false, | ||
"create_plots": true | ||
"Training": { | ||
"num_epoch": 50, | ||
"perc_train": 0.8, | ||
"loss_function_type": "mae", | ||
"batch_size": 32, | ||
"continue": 0, | ||
"Optimizer": { | ||
"type": "AdamW", | ||
"learning_rate": 0.001 | ||
} | ||
} | ||
} | ||
}, | ||
"Visualization": { | ||
"plot_init_solution": true, | ||
"plot_hist_solution": false, | ||
"create_plots": true | ||
} | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,58 +1,78 @@ | ||
{ | ||
"Verbosity": { | ||
"level": 2 | ||
}, | ||
"NeuralNetwork": { | ||
"Architecture": { | ||
"model_type": "EGNN", | ||
"equivariance": true, | ||
"radius": 5.0, | ||
"max_neighbours": 100000, | ||
"num_gaussians": 50, | ||
"envelope_exponent": 5, | ||
"int_emb_size": 64, | ||
"basis_emb_size": 8, | ||
"out_emb_size": 128, | ||
"num_after_skip": 2, | ||
"num_before_skip": 1, | ||
"num_radial": 6, | ||
"num_spherical": 7, | ||
"num_filters": 126, | ||
"edge_features": ["length"], | ||
"hidden_dim": 50, | ||
"num_conv_layers": 3, | ||
"output_heads": { | ||
"node": { | ||
"num_headlayers": 2, | ||
"dim_headlayers": [200,200], | ||
"type": "mlp" | ||
} | ||
}, | ||
"task_weights": [1.0] | ||
}, | ||
"Variables_of_interest": { | ||
"input_node_features": [0, 1, 2, 3], | ||
"output_names": ["forces"], | ||
"output_index": [2], | ||
"output_dim": [3], | ||
"type": ["node"] | ||
}, | ||
"Training": { | ||
"num_epoch": 50, | ||
"EarlyStopping": true, | ||
"perc_train": 0.9, | ||
"loss_function_type": "mae", | ||
"batch_size": 32, | ||
"continue": 0, | ||
"Optimizer": { | ||
"type": "AdamW", | ||
"learning_rate": 1e-3 | ||
} | ||
"Verbosity": { | ||
"level": 2 | ||
}, | ||
"NeuralNetwork": { | ||
"Architecture": { | ||
"model_type": "EGNN", | ||
"equivariance": true, | ||
"radius": 5, | ||
"max_neighbours": 100000, | ||
"num_gaussians": 50, | ||
"envelope_exponent": 5, | ||
"int_emb_size": 64, | ||
"basis_emb_size": 8, | ||
"out_emb_size": 128, | ||
"num_after_skip": 2, | ||
"num_before_skip": 1, | ||
"num_radial": 6, | ||
"num_spherical": 7, | ||
"num_filters": 126, | ||
"edge_features": [ | ||
"length" | ||
], | ||
"hidden_dim": 50, | ||
"num_conv_layers": 3, | ||
"output_heads": { | ||
"node": { | ||
"num_headlayers": 2, | ||
"dim_headlayers": [ | ||
200, | ||
200 | ||
], | ||
"type": "mlp" | ||
} | ||
}, | ||
"task_weights": [ | ||
1 | ||
] | ||
}, | ||
"Variables_of_interest": { | ||
"input_node_features": [ | ||
0, | ||
1, | ||
2, | ||
3 | ||
], | ||
"output_names": [ | ||
"forces" | ||
], | ||
"output_index": [ | ||
2 | ||
], | ||
"output_dim": [ | ||
3 | ||
], | ||
"type": [ | ||
"node" | ||
] | ||
}, | ||
"Visualization": { | ||
"plot_init_solution": true, | ||
"plot_hist_solution": false, | ||
"create_plots": true | ||
"Training": { | ||
"num_epoch": 50, | ||
"EarlyStopping": true, | ||
"perc_train": 0.9, | ||
"loss_function_type": "mae", | ||
"batch_size": 32, | ||
"continue": 0, | ||
"Optimizer": { | ||
"type": "AdamW", | ||
"learning_rate": 0.001 | ||
} | ||
} | ||
} | ||
}, | ||
"Visualization": { | ||
"plot_init_solution": true, | ||
"plot_hist_solution": false, | ||
"create_plots": true | ||
} | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,25 @@ | ||
#!/bin/bash | ||
|
||
# URL to download from | ||
URL="https://alexandria.icams.rub.de/data/" | ||
|
||
# Directory where files will be saved | ||
OUTPUT_DIR="./dataset/compressed_data" | ||
|
||
# Create output directory if it doesn't exist | ||
mkdir -p "$OUTPUT_DIR" | ||
|
||
# Use wget to recursively download all files and directories | ||
wget --recursive \ | ||
--no-parent \ | ||
--continue \ | ||
--no-clobber \ | ||
--convert-links \ | ||
--cut-dirs=1 \ | ||
--no-check-certificate \ | ||
--reject-regex="(/older/|/geo_opt_paths/)" \ | ||
--reject "*index.html*" \ | ||
--directory-prefix="$OUTPUT_DIR" \ | ||
"$URL" | ||
|
||
echo "Download complete. All files saved to $OUTPUT_DIR." |
Oops, something went wrong.