hybrid model compression #4445
Unanswered
akshata-pixel
asked this question in
Q&A
Replies: 1 comment 3 replies
-
The source reason of this error is that |
Beta Was this translation helpful? Give feedback.
3 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
i am using hybrid descriptor for model training. My model is trained but does not get compressed getting following error: File "/home/akshata/deepmdkit-2/bin/dp", line 10, in
sys.exit(main())
^^^^^^
File "/home/akshata/deepmdkit-2/lib/python3.12/site-packages/deepmd/main.py", line 927, in main
deepmd_main(args)
File "/home/akshata/deepmdkit-2/lib/python3.12/site-packages/deepmd/tf/entrypoints/main.py", line 86, in main
compress(**dict_args)
File "/home/akshata/deepmdkit-2/lib/python3.12/site-packages/deepmd/tf/entrypoints/compress.py", line 166, in compress
train(
File "/home/akshata/deepmdkit-2/lib/python3.12/site-packages/deepmd/tf/entrypoints/train.py", line 185, in train
_do_work(jdata, run_opt, is_compress)
File "/home/akshata/deepmdkit-2/lib/python3.12/site-packages/deepmd/tf/entrypoints/train.py", line 262, in _do_work
model.build(train_data, stop_batch, origin_type_map=origin_type_map)
File "/home/akshata/deepmdkit-2/lib/python3.12/site-packages/deepmd/tf/train/trainer.py", line 229, in build
self.model.enable_compression()
File "/home/akshata/deepmdkit-2/lib/python3.12/site-packages/deepmd/tf/model/model.py", line 726, in enable_compression
self.descrpt.enable_compression(
File "/home/akshata/deepmdkit-2/lib/python3.12/site-packages/deepmd/tf/descriptor/hybrid.py", line 343, in enable_compression
ii.enable_compression(
File "/home/akshata/deepmdkit-2/lib/python3.12/site-packages/deepmd/tf/descriptor/se_r.py", line 354, in enable_compression
self.table = DPTabulate(
^^^^^^^^^^^
File "/home/akshata/deepmdkit-2/lib/python3.12/site-packages/deepmd/tf/utils/tabulate.py", line 155, in init
self.bias = self._get_bias()
^^^^^^^^^^^^^^^^
File "/home/akshata/deepmdkit-2/lib/python3.12/site-packages/deepmd/tf/utils/tabulate.py", line 241, in _get_bias
node = self.embedding_net_nodes[
^^^^^^^^^^^^^^^^^^^^^^^^^
KeyError: 'filter_type_0_1/bias_1_0'
my input file is : {
"_comment": " model parameters",
"model": {
"type_map": ["X", "Y"],
"descriptor" :{
"type": "hybrid",
"list": [
{
"type": "se_e2_a",
"sel": [60,115],
"rcut_smth": 0.50,
"rcut": 7.00,
"neuron": [20, 40, 80],
"resnet_dt": false,
"axis_neuron": 8,
"type_one_side": true,
"precision": "float64",
"seed": 1,
"_comment": " that's all"
},
{
"type": "se_e2_r",
"sel": [60,115 ],
"rcut_smth": 0.50,
"rcut": 6.00,
"neuron": [5,10,20],
"resnet_dt": false,
"type_one_side": true,
"precision": "float64",
"seed": 1,
"_comment3": " that's all"
}
]
},
"fitting_net" : {
"neuron": [240, 240, 240],
"resnet_dt": true,
"seed": 1,
"_comment": " that's all"
},
"_comment": " that's all"
},
}
Beta Was this translation helpful? Give feedback.
All reactions