Commit 75845206 authored by Zhang, Chen's avatar Zhang, Chen
Browse files

adjust for mo film

parent 56db3334

scripts/train_ntrace.py

+2 −2
Original line number Diff line number Diff line
@@ -8,7 +8,7 @@ if __name__ == "__main__": 
        "n_head": 32,

        "num_encoder_layers": 6,

        "input_dim": 150,

        "output_dim": 17,

        "output_dim": 14,

        "to_log": True,

    }
@@ -23,7 +23,7 @@ if __name__ == "__main__": 
        "optimizer": "Adam",

        "loss": "composite",

        "cache_dir": "data",

        "experiment_name": "nTrace_xx_film_6layer",

        "experiment_name": "nTrace_mo_film_5layer",

        "run_name": "d2048_h32_l6",

        "datadir": "expdata",

    }

src/tgreft/train/generic.py

+3 −3
Original line number Diff line number Diff line
@@ -132,9 +132,9 @@ def visualize_single_epoch( 
        "bulk2_sld",

        "bulk2_thickness",

        "bulk2_roughness",

        "bulk3_sld",

        "bulk3_thickness",

        "bulk3_roughness",

        # "bulk3_sld",

        # "bulk3_thickness",

        # "bulk3_roughness",

        "oxide_sld",

        "oxide_thickness",

        "oxide_roughness",

src/tgreft/train/train_ntrace.py

+1 −2
Original line number Diff line number Diff line 
#!/usr/bin/env python3

"""Train function for the transformer model."""

import os

import shutil

import torch

import mlflow

import logging
@@ -181,7 +180,7 @@ def train( 
            mlflow.log_metric("test_loss", test_loss, step=epoch)



            # evaluate on real data

            system="cu"

            system = "mo"

            real_data_loss = real_data_evaluator.evaluate(

                model=model,

                device=device,

src/tgreft/utils/data/data_loader.py

+35 −37
Original line number Diff line number Diff line
@@ -113,52 +113,50 @@ def generate_data( 
    # )



    # mo_film, 5 layer

    # parameters_ref = np.column_stack(

    #     [

    #         np.random.uniform(-1.0, 7.0, n_dataset),  # electolyte_sld,  I changed the lower bound to -1 to include air and H2O

    #         np.random.uniform(5, 120, n_dataset),  # electolyte_roughness,



    #         np.random.uniform(-5.0, 6.5, n_dataset),  # sei_sld,

    #         np.random.uniform(10, 500, n_dataset),  # sei_thickness,

    #         np.random.uniform(1, 80, n_dataset),  # sei_roughness,



    #         np.random.uniform(-2, 7, n_dataset),  # bulk_3_sld,

    #         np.random.uniform(10, 200, n_dataset),  # material_thickness,

    #         np.random.uniform(1, 55, n_dataset),  # material_roughness,



    #         np.random.uniform(2, 6, n_dataset),  # bulk_2_sld,

    #         np.random.uniform(20, 700, n_dataset),  # cu_thickness,

    #         np.random.uniform(1, 55, n_dataset),  # cu_roughness,



    #         np.random.uniform(1, 4.2, n_dataset),  # oxide_sld,

    #         np.random.uniform(5, 50, n_dataset),  # oxide_thickness,

    #         np.random.uniform(1, 10, n_dataset),  # oxide_roughness,

    #     ]

    # )



    # xx_film, 6 layer model

    parameters_ref = np.column_stack(

        [

            np.random.uniform(-1.0, 7.0, n_dataset),  # electolyte_sld, including air and H2O

            np.random.uniform(

                -1.0, 7.0, n_dataset

            ),  # electolyte_sld,  I changed the lower bound to -1 to include air and H2O

            np.random.uniform(5, 120, n_dataset),  # electolyte_roughness,

            np.random.uniform(-5.0, 6.5, n_dataset),  # sei_sld,

            np.random.uniform(10, 500, n_dataset),  # sei_thickness,

            np.random.uniform(1, 80, n_dataset),  # sei_roughness,

            np.random.uniform(-2, 7, n_dataset),  # bulk_3_sld,

            np.random.uniform(10, 200, n_dataset),  # bulk_3_thickness,

            np.random.uniform(1, 55, n_dataset),  # bulk_3_roughness,

            np.random.uniform(2, 7, n_dataset),  # bulk_2_sld,

            np.random.uniform(20, 700, n_dataset),  # bulk_2_thickness (cu_thickness),

            np.random.uniform(1, 55, n_dataset),  # bulk_2_roughness (cu_roughness),

            np.random.uniform(-3.5, 7, n_dataset),  # bulk_1_sld,

            np.random.uniform(10, 200, n_dataset),  # bulk_1_thickness,

            np.random.uniform(1, 55, n_dataset),  # bulk_1_roughness,

            np.random.uniform(10, 200, n_dataset),  # material_thickness,

            np.random.uniform(1, 55, n_dataset),  # material_roughness,

            np.random.uniform(2, 6, n_dataset),  # bulk_2_sld,

            np.random.uniform(20, 700, n_dataset),  # cu_thickness,

            np.random.uniform(1, 55, n_dataset),  # cu_roughness,

            np.random.uniform(1, 4.2, n_dataset),  # oxide_sld,

            np.random.uniform(5, 50, n_dataset),  # oxide_thickness,

            np.random.uniform(1, 10, n_dataset),  # oxide_roughness,

        ]

    )



    # xx_film, 6 layer model

    # parameters_ref = np.column_stack(

    #     [

    #         np.random.uniform(-1.0, 7.0, n_dataset),  # electolyte_sld, including air and H2O

    #         np.random.uniform(5, 120, n_dataset),  # electolyte_roughness,

    #         np.random.uniform(-5.0, 6.5, n_dataset),  # sei_sld,

    #         np.random.uniform(10, 500, n_dataset),  # sei_thickness,

    #         np.random.uniform(1, 80, n_dataset),  # sei_roughness,

    #         np.random.uniform(-2, 7, n_dataset),  # bulk_3_sld,

    #         np.random.uniform(10, 200, n_dataset),  # bulk_3_thickness,

    #         np.random.uniform(1, 55, n_dataset),  # bulk_3_roughness,

    #         np.random.uniform(2, 7, n_dataset),  # bulk_2_sld,

    #         np.random.uniform(20, 700, n_dataset),  # bulk_2_thickness (cu_thickness),

    #         np.random.uniform(1, 55, n_dataset),  # bulk_2_roughness (cu_roughness),

    #         np.random.uniform(-3.5, 7, n_dataset),  # bulk_1_sld,

    #         np.random.uniform(10, 200, n_dataset),  # bulk_1_thickness,

    #         np.random.uniform(1, 55, n_dataset),  # bulk_1_roughness,

    #         np.random.uniform(1, 4.2, n_dataset),  # oxide_sld,

    #         np.random.uniform(5, 50, n_dataset),  # oxide_thickness,

    #         np.random.uniform(1, 10, n_dataset),  # oxide_roughness,

    #     ]

    # )



    # generate the reference rcurves

    r_curves = np.apply_along_axis(param_to_rcurve, 1, parameters_ref)

    logger.debug(f"r_curves.shape: {r_curves.shape}")
@@ -189,8 +187,8 @@ def param_to_rcurve(param: np.ndarray) -> np.ndarray: 
        {"name": "SEI", "sld": param[2], "isld": 0, "thickness": param[3], "roughness": param[4]},

        {"name": "bulk3", "sld": param[5], "isld": 0, "thickness": param[6], "roughness": param[7]},

        {"name": "bulk2(Cu)", "sld": param[8], "isld": 0, "thickness": param[9], "roughness": param[10]},

        {"name": "bulk1", "sld": param[11], "isld": 0, "thickness": param[12], "roughness": param[13]},

        {"name": "oxide", "sld": param[14], "isld": 0, "thickness": param[15], "roughness": param[16]},

        {"name": "oxide", "sld": param[11], "isld": 0, "thickness": param[12], "roughness": param[13]},

        # {"name": "bulk1", "sld": param[14], "isld": 0, "thickness": param[15], "roughness": param[16]},

        {"name": "substrate", "sld": 2.07, "isld": 0, "thickness": 0, "roughness": 0},

    ]

    return r_generator(config)
@@ -215,8 +213,8 @@ def param_to_sld(param: np.ndarray) -> Tuple[np.ndarray, np.ndarray]: 
        {"name": "SEI", "sld": param[2], "isld": 0, "thickness": param[3], "roughness": param[4]},

        {"name": "bulk3", "sld": param[5], "isld": 0, "thickness": param[6], "roughness": param[7]},

        {"name": "bulk2(Cu)", "sld": param[8], "isld": 0, "thickness": param[9], "roughness": param[10]},

        {"name": "bulk1", "sld": param[11], "isld": 0, "thickness": param[12], "roughness": param[13]},

        {"name": "oxide", "sld": param[14], "isld": 0, "thickness": param[15], "roughness": param[16]},

        {"name": "oxide", "sld": param[11], "isld": 0, "thickness": param[12], "roughness": param[13]},

        # {"name": "bulk1", "sld": param[14], "isld": 0, "thickness": param[15], "roughness": param[16]},

        {"name": "substrate", "sld": 2.07, "isld": 0, "thickness": 0, "roughness": 0},

    ]

    experiment = r_generator.build_experiment_from_config(config)