By AnDenix, 2018-2019
Based on the dfaker model: https://github.com/dfaker
Acknowledgments:
kvrooman for numerous insights and invaluable aid
DeepHomage for lots of testing
"""
import logging
from lib.model.nn_blocks import (Conv2DOutput, Conv2DBlock, ResidualBlock,
UpscaleBlock, Upscale2xBlock)
from lib.utils import FaceswapError, get_backend
from ._base import ModelBase, KerasModel
if get_backend() == "amd":
from keras.layers import (AveragePooling2D, BatchNormalization,
Concatenate, Dense, Dropout, Flatten, Input,
Reshape, LeakyReLU, UpSampling2D)
else:
# Ignore linting errors from Tensorflow's thoroughly broken import system
from tensorflow.keras.layers import ( # pylint:disable=import-error,no-name-in-module
AveragePooling2D, BatchNormalization, Concatenate, Dense, Dropout,
Flatten, Input, Reshape, LeakyReLU, UpSampling2D)
logger = logging.getLogger(__name__) # pylint: disable=invalid-name
class Model(ModelBase):
""" DLight Autoencoder Model """
def __init__(self, *args, **kwargs):
#!/usr/bin/env python3
""" Sanity checks for Faceswap. """
import inspect
import pytest
import keras
from keras import backend as K
from lib.utils import get_backend
_BACKEND = get_backend()
@pytest.mark.parametrize('dummy', [None], ids=[get_backend().upper()])
def test_backend(dummy): # pylint:disable=unused-argument
""" Sanity check to ensure that Keras backend is returning the correct object type. """
test_var = K.variable((1, 1, 4, 4))
lib = inspect.getmodule(test_var).__name__.split(".")[0]
assert (_BACKEND == "cpu"
and lib == "tensorflow") or (_BACKEND == "amd"
and lib == "plaidml")
@pytest.mark.parametrize('dummy', [None], ids=[get_backend().upper()])
def test_keras(dummy): # pylint:disable=unused-argument
""" Sanity check to ensure that tensorflow keras is being used for CPU and standard
keras for AMD. """
assert ((_BACKEND == "cpu" and keras.__version__ == "2.4.0")
or (_BACKEND == "amd" and keras.__version__ == "2.2.4"))
#!/usr/bin/env python3
""" Tests for Faceswap Initializers.
Adapted from Keras tests.
"""
from keras import backend as K
from keras import initializers as k_initializers
import pytest
import numpy as np
from lib.model import initializers
from lib.utils import get_backend
CONV_SHAPE = (3, 3, 256, 2048)
CONV_ID = get_backend().upper()
def _runner(init,
shape,
target_mean=None,
target_std=None,
target_max=None,
target_min=None):
variable = K.variable(init(shape))
output = K.get_value(variable)
lim = 3e-2
if target_std is not None:
assert abs(output.std() - target_std) < lim
if target_mean is not None:
assert abs(output.mean() - target_mean) < lim
from itertools import product
import pytest
import numpy as np
from keras import Input, Model, backend as K
from numpy.testing import assert_allclose
from lib.model.nn_blocks import NNBlocks
from lib.utils import get_backend
_PARAMS = ["use_icnr_init", "use_convaware_init", "use_reflect_padding"]
_VALUES = list(product([True, False], repeat=len(_PARAMS)))
_IDS = [
"{}[{}]".format("|".join([_PARAMS[idx] for idx, b in enumerate(v) if b]),
get_backend().upper()) for v in _VALUES
]
def block_test(layer_func, kwargs={}, input_shape=None):
"""Test routine for faceswap neural network blocks.
Tests are simple and are to ensure that the blocks compile on both tensorflow
and plaidml backends
"""
# generate input data
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: