mirror of
https://github.com/open-mmlab/mmclassification.git
synced 2025-06-03 21:53:55 +08:00
08dc8c75d3
* remove basehead * add moco series * add byol simclr simsiam * add ut * update configs * add simsiam hook * add and refactor beit * update ut * add cae * update extract_feat * refactor cae * add mae * refactor data preprocessor * update heads * add maskfeat * add milan * add simmim * add mixmim * fix lint * fix ut * fix lint * add eva * add densecl * add barlowtwins * add swav * fix lint * update readtherdocs rst * update docs * update * Decrease UT memory usage * Fix docstring * update DALLEEncoder * Update model docs * refactor dalle encoder * update docstring * fix ut * fix config error * add val_cfg and test_cfg * refactor clip generator * fix lint * pass check * fix ut * add lars * update type of BEiT in configs * Use MMEngine style momentum in EMA. * apply mmpretrain solarize --------- Co-authored-by: mzr1996 <mzr1996@163.com>
69 lines
2.1 KiB
Python
69 lines
2.1 KiB
Python
# Copyright (c) OpenMMLab. All rights reserved.
|
|
import platform
|
|
|
|
import pytest
|
|
import torch
|
|
from mmengine.utils import digit_version
|
|
|
|
from mmpretrain.models import MaskFeat, MaskFeatViT
|
|
from mmpretrain.structures import DataSample
|
|
|
|
|
|
@pytest.mark.skipif(platform.system() == 'Windows', reason='Windows mem limit')
|
|
def test_maskfeat_vit():
|
|
maskfeat_backbone = MaskFeatViT()
|
|
maskfeat_backbone.init_weights()
|
|
fake_inputs = torch.randn((2, 3, 224, 224))
|
|
fake_mask = torch.randn((2, 14, 14)).flatten(1).bool()
|
|
|
|
# test with mask
|
|
fake_outputs = maskfeat_backbone(fake_inputs, fake_mask)
|
|
assert list(fake_outputs.shape) == [2, 197, 768]
|
|
|
|
# test without mask
|
|
fake_outputs = maskfeat_backbone(fake_inputs, None)
|
|
assert len(fake_outputs[0]) == 2
|
|
assert fake_outputs[0][0].shape == torch.Size([2, 768, 14, 14])
|
|
assert fake_outputs[0][1].shape == torch.Size([2, 768])
|
|
|
|
|
|
@pytest.mark.skipif(
|
|
digit_version(torch.__version__) < digit_version('1.7.0'),
|
|
reason='torch version')
|
|
@pytest.mark.skipif(platform.system() == 'Windows', reason='Windows mem limit')
|
|
def test_maskfeat():
|
|
data_preprocessor = {
|
|
'mean': [0.5, 0.5, 0.5],
|
|
'std': [0.5, 0.5, 0.5],
|
|
'to_rgb': True
|
|
}
|
|
|
|
backbone = dict(type='MaskFeatViT', arch='b', patch_size=16)
|
|
neck = dict(
|
|
type='LinearNeck', in_channels=768, out_channels=108, gap_dim=0)
|
|
head = dict(
|
|
type='MIMHead',
|
|
loss=dict(type='PixelReconstructionLoss', criterion='L2'))
|
|
target_generator = dict(
|
|
type='HOGGenerator', nbins=9, pool=8, gaussian_window=16)
|
|
|
|
alg = MaskFeat(
|
|
backbone=backbone,
|
|
neck=neck,
|
|
head=head,
|
|
target_generator=target_generator,
|
|
data_preprocessor=data_preprocessor)
|
|
|
|
# test forward_train
|
|
fake_data_sample = DataSample()
|
|
fake_mask = torch.rand((14, 14)).bool()
|
|
fake_data_sample.set_mask(fake_mask)
|
|
fake_data = {
|
|
'inputs': torch.randn((1, 3, 224, 224)),
|
|
'data_samples': [fake_data_sample]
|
|
}
|
|
|
|
fake_input = alg.data_preprocessor(fake_data)
|
|
fake_outputs = alg(**fake_input, mode='loss')
|
|
assert isinstance(fake_outputs['loss'].item(), float)
|