WillNuyen228/auramask-sketchv1

Prompt

input

Prompt

target

Prompt

output

Training logs here

Model Description

This model uses a modified vnet for 2D input/output implemented here with the following configuration.

{
    "D": [
        1,
        1,
        1,
        1,
        1
    ],
    "E": [
        1,
        1,
        2,
        3,
        5
    ],
    "activation": "relu",
    "batch_norm": false,
    "filter_num": [
        16,
        32,
        64,
        128,
        128
    ],
    "kernel_reg": "l2",
    "n_labels": 3,
    "output_activation": null
}

{
    "alpha": 0.0001,
    "batch": 16,
    "epochs": 50,
    "epsilon": 0.03,
    "input": "(256, 256)",
    "losses": {
        "FEAT_ArcFace": {
            "d": "cosine_similarity",
            "f": "ArcFace",
            "name": "FEAT_ArcFace",
            "reduction": "sum_over_batch_size",
            "threshold": 0.68,
            "weight": 0.1
        },
        "TopIQ": {
            "full_ref": true,
            "lower_better": false,
            "name": "TopIQ",
            "reduction": "sum_over_batch_size",
            "score_range": "~0, ~1",
            "weight": 0.9
        },
        "mean_squared_error": {
            "name": "mean_squared_error",
            "reduction": "sum_over_batch_size",
            "weight": 0.1
        }
    },
    "mixed_precision": false,
    "optimizer": {
        "amsgrad": false,
        "beta_1": 0.9,
        "beta_2": 0.999,
        "clipnorm": 1,
        "clipvalue": null,
        "ema_momentum": 0.99,
        "ema_overwrite_frequency": null,
        "epsilon": 1e-07,
        "global_clipnorm": null,
        "gradient_accumulation_steps": null,
        "learning_rate": 9.999999747378752e-05,
        "loss_scale_factor": null,
        "name": "adam",
        "use_ema": false,
        "weight_decay": null
    },
    "seed": "LKUHKVHVALZF",
    "testing": 0.1,
    "training": 0.9
}

Model Architecture Plot