mirror of
https://github.com/facefusion/facefusion-labs.git
synced 2026-06-25 07:59:55 +02:00
Henry Ruhs
2e6394565a
* add sync batchnorm * replace random.choice with hash * fifty percent reduction * fix discriminator input * restore dataset.py * Remove duplicates * add discriminator_ratio to config * fix onnx export bug: replace round() with int() * Fix embedding naming * Introduce ModelWithConfigCheckpoint callback (#86) * Fix dist ini * Style: Refactor typing and improve code clarity in training.py (#88) * Add type casting for trainer params * Add type casting for trainer params * Add type casting for trainer params * Remove inplace activations for torch.compile compatibility (#89) * Fix README * improvise with norm layers & weighted average * add skip layer * use gelu instead of leaky_relu * cleanup * cleanup * Update dependencies * Different defaults and enable validation * Different defaults and enable validation * Revert to higher batch size * Just use copy over copy2 --------- Co-authored-by: harisreedhar <h4harisreedhar.s.s@gmail.com> Co-authored-by: NeuroDonu <112660822+NeuroDonu@users.noreply.github.com> Co-authored-by: Harisreedhar <46858047+harisreedhar@users.noreply.github.com>
57 lines
1.4 KiB
Python
57 lines
1.4 KiB
Python
from configparser import ConfigParser
|
|
|
|
import pytest
|
|
import torch
|
|
|
|
from hyperswap.src.networks.aad import AAD
|
|
from hyperswap.src.networks.masknet import MaskNet
|
|
from hyperswap.src.networks.unet import UNet
|
|
|
|
|
|
@pytest.mark.parametrize('output_size', [ 128, 256, 512 ])
|
|
def test_aad_with_unet(output_size : int) -> None:
|
|
config_parser = ConfigParser()
|
|
config_parser.read_dict(
|
|
{
|
|
'training.model.generator':
|
|
{
|
|
'source_channels': '512',
|
|
'output_size': str(output_size),
|
|
'num_blocks': '2'
|
|
}
|
|
})
|
|
|
|
encoder = UNet(config_parser).eval()
|
|
generator = AAD(config_parser).eval()
|
|
|
|
source_tensor = torch.randn(1, 512)
|
|
target_tensor = torch.randn(1, 3, output_size, output_size)
|
|
|
|
target_features = encoder(target_tensor)
|
|
output_tensor = generator(source_tensor, target_features)
|
|
|
|
assert output_tensor.shape == (1, 3, output_size, output_size)
|
|
|
|
|
|
@pytest.mark.parametrize('output_size', [ 128, 256, 512 ])
|
|
def test_mask_net(output_size : int) -> None:
|
|
config_parser = ConfigParser()
|
|
config_parser.read_dict(
|
|
{
|
|
'training.model.masker':
|
|
{
|
|
'input_channels': '67',
|
|
'output_channels': '1',
|
|
'num_filters': '16'
|
|
}
|
|
})
|
|
|
|
masker = MaskNet(config_parser).eval()
|
|
|
|
target_tensor = torch.randn(1, 3, output_size, output_size)
|
|
target_feature = torch.randn(1, 64, output_size, output_size)
|
|
|
|
output_mask = masker(target_tensor, target_feature)
|
|
|
|
assert output_mask.shape == (1, 1, output_size, output_size)
|