mirror of
https://github.com/deepfakes/faceswap.git
synced 2026-10-21 09:01:52 +08:00
torzdf
837bc2d51d
* FaceSwap 3 (#1515) * Update extract pipeline * Update requirements + setup for nvidia * Remove allow-growth option * tf.keras to keras updates * lib.model.losses - Port + fix all loss functions for Keras3 * lib.model - port initializers, layers. normalization to Keras3 * lib.model.autoclip to Keras 3 * Update mixed precision layer storage * model file to .keras format * Restructure nn_blocks to initialize layers in __init__ * Tensorboard - Trainer: Add Torch compatible Tensorboard callbacks - GUI event reader remove TF dependency * Loss logging - Flush TB logs on save - Replace TB live iterator for GUI * Backup models on total loss drop rather than per side * Update all models to Keras3 Compat * Remove lib.model.session * Update clip ViT to Keras 3 * plugins.extract.mask.unet-dfl - Fix for Keras3/Torch backend * Port AdaBelief to Keras 3 * setup.py: - Add --dev flag for dev tool install * Fix Keras 3 syntax * Fix LR Finder for Keras 3 * Fix mixed precision switching for Keras 3 * Add more optimizers + open up config setting * train: Remove updating FS1 weights to FS2 models * Alignments: Remove support for legacy .json files * tools.model: - Remove TF Saved Format saving - Fix Backup/Restore + Nan-Scan * Fix inference model creation for Keras 3 * Preview tool: Fix for Keras3 * setup.py: Configure keras backend * train: Migration of FS2 models to FS3 * Training: Default coverage to 100% * Remove DirectML backend * Update setup for MacOS * GUI: Force line reading to UTF-8 * Remove redundant Tensorflow references * Remove redundant code * Legacy model loading: Fix TFLamdaOp scalar ops and DepthwiseConv2D * Add vertical offset option for training * Github actions: Add more python versions * Add python version to workflow names * Github workflow: Exclude Python 3.12 for macOS * Implement custom training loop * Fs3 - Add RTX5xxx and ROCm 6.1-6.4 support (#1511) * setup.py: Add Cuda/ROCm version select options * bump minimum python version to 3.11 * Switch from setup.cgf to pyproject.toml * Documentation: Update all docs to use automodapi * Allow sysinfo to run with missing packages + correctly install tk under Linux * Bugfix: dot naming convention in clip models * lib.config: Centralise globally rather than passing as object - Add torch DataParallel for multi-gpu training - GUI: Group switches together when generating cli args - CLI: Remove deprecated multi-character argparse args - Refactor: - Centralise tensorboard reading/writing + unit tests - Create trainer plugin interfaces + add original + distributed * Update installers
86 lines
3.1 KiB
Python
86 lines
3.1 KiB
Python
#!/usr/bin/env python3
|
|
""" Tests for Faceswap Custom Layers.
|
|
|
|
Adapted from Keras tests.
|
|
"""
|
|
|
|
from itertools import product
|
|
|
|
import pytest
|
|
import numpy as np
|
|
|
|
from numpy.testing import assert_allclose
|
|
|
|
from keras import device, Input, Model, backend as K
|
|
|
|
from lib.model import nn_blocks
|
|
from lib.utils import get_backend
|
|
from plugins.train import train_config as cfg
|
|
# pylint:disable=unused-import
|
|
from tests.lib.config.helpers import patch_config # noqa:[F401]
|
|
|
|
|
|
def block_test(layer_func, # pylint:disable=dangerous-default-value,too-many-locals
|
|
kwargs={},
|
|
input_shape=None):
|
|
"""Test routine for faceswap neural network blocks. """
|
|
# generate input data
|
|
# pylint:disable=duplicate-code
|
|
assert input_shape
|
|
input_dtype = K.floatx()
|
|
input_data_shape = list(input_shape)
|
|
for i, var_e in enumerate(input_data_shape):
|
|
if var_e is None:
|
|
input_data_shape[i] = np.random.randint(1, 4)
|
|
input_data = 10 * np.random.random(input_data_shape)
|
|
input_data = input_data.astype(input_dtype)
|
|
expected_output_dtype = input_dtype
|
|
|
|
# test in functional API
|
|
inp = Input(shape=input_shape[1:], dtype=input_dtype)
|
|
outp = layer_func(inp, **kwargs)
|
|
assert outp.dtype == expected_output_dtype
|
|
|
|
# check with the functional API
|
|
model = Model(inp, outp)
|
|
|
|
actual_output = model.predict(input_data, verbose=0) # type:ignore
|
|
|
|
# test serialization, weight setting at model level
|
|
model_config = model.get_config()
|
|
recovered_model = model.__class__.from_config(model_config)
|
|
if model.weights:
|
|
weights = model.get_weights()
|
|
recovered_model.set_weights(weights)
|
|
_output = recovered_model.predict(input_data, verbose=0) # type:ignore
|
|
assert_allclose(_output, actual_output, rtol=1e-3)
|
|
|
|
# for further checks in the caller function
|
|
return actual_output
|
|
|
|
|
|
_PARAMS = ["use_icnr_init", "use_convaware_init", "use_reflect_padding"]
|
|
_VALUES = list(product([True, False], repeat=len(_PARAMS)))
|
|
_IDS = [f"{'|'.join([_PARAMS[idx] for idx, b in enumerate(v) if b])}[{get_backend().upper()}]"
|
|
for v in _VALUES]
|
|
|
|
|
|
@pytest.mark.parametrize(_PARAMS, _VALUES, ids=_IDS)
|
|
def test_blocks(use_icnr_init,
|
|
use_convaware_init,
|
|
use_reflect_padding,
|
|
patch_config): # pylint:disable=redefined-outer-name # noqa:[F811]
|
|
""" Test for all blocks contained within the NNBlocks Class """
|
|
config = {"icnr_init": use_icnr_init,
|
|
"conv_aware_init": use_convaware_init,
|
|
"reflect_padding": use_reflect_padding}
|
|
patch_config(cfg, config)
|
|
with device("cpu"):
|
|
block_test(nn_blocks.Conv2DOutput(64, 3), input_shape=(2, 8, 8, 32))
|
|
block_test(nn_blocks.Conv2DBlock(64), input_shape=(2, 8, 8, 32))
|
|
block_test(nn_blocks.SeparableConv2DBlock(64), input_shape=(2, 8, 8, 32))
|
|
block_test(nn_blocks.UpscaleBlock(64), input_shape=(2, 4, 4, 128))
|
|
block_test(nn_blocks.Upscale2xBlock(64, fast=True), input_shape=(2, 4, 4, 128))
|
|
block_test(nn_blocks.Upscale2xBlock(64, fast=False), input_shape=(2, 4, 4, 128))
|
|
block_test(nn_blocks.ResidualBlock(64), input_shape=(2, 4, 4, 64))
|