4.4. Descriptor "se_e3"
Note
Supported backends: TensorFlow
The notation of The three-body embedding DeepPot-SE descriptor incorporates bond-angle information, making the model more accurate. The descriptor \(\mathcal{D}^i\) can be represented as where \(N_c\) is the expected maximum number of neighboring atoms, which is the same constant for all atoms over all frames. \(\mathcal{R}^i\) is constructed as Currently, only the full information case of \(\mathcal{R}^i\) is supported by the three-body embedding. Each element of \(\mathcal{G}^i \in \mathbb{R}^{N_c \times N_c \times M}\) comes from \(M\) nodes from the output layer of an NN \(\mathcal{N}_{e,3}\) function: where \((\theta_i)_ {jk} = (\mathcal{R}^i)_ {j,\\{2,3,4\\}}\cdot (\mathcal{R}^i)_ {k,\\{2,3,4\\}}\) considers the angle form of two neighbours (\(j\) and \(k\)). The notation \(:\) in the equation indicates the contraction between matrix \(\mathcal{R}^i(\mathcal{R}^i)^T\) and the first two dimensions of tensor \(\mathcal{G}^i\).[1] A complete training input script of this example can be found in the directory The training input script is very similar to that of The type of the descriptor is set by the key type.se_e3
is short for the Deep Potential Smooth Edition (DeepPot-SE) constructed from all information (both angular and radial) of atomic configurations. The embedding takes bond angles between a central atom and its two neighboring atoms as input (denoted by e3
).4.4.1. Theory
4.4.2. Instructions
$deepmd_source_dir/examples/water/se_e3/input.json
se_e2_a
. The only difference lies in the descriptor <model/descriptor>
section "descriptor": {
"type": "se_e3",
"sel": [40, 80],
"rcut_smth": 0.50,
"rcut": 6.00,
"neuron": [2, 4, 8],
"resnet_dt": false,
"seed": 1,
"_comment": " that's all"
},