From 4c96a544cdf7128f0959b9f31459d74cabb5e1e0 Mon Sep 17 00:00:00 2001 From: ys-li <56712176+Yshuo-Li@users.noreply.github.com> Date: Fri, 11 Feb 2022 11:59:04 +0800 Subject: [PATCH] [Fix] delete `__init__` in `TestVFIDataset` (#731) * [Doc] Add docs of Ref-SR demo and video frame interpolation demo * [Fix] delete '__init__' * back * Fix --- .../test_datasets/test_vfi_dataset.py | 18 ++++++++---------- .../test_restorers/test_basic_restorer.py | 18 +++++++++--------- .../test_basic_interpolator.py | 18 +++++++++--------- 3 files changed, 26 insertions(+), 28 deletions(-) diff --git a/tests/test_data/test_datasets/test_vfi_dataset.py b/tests/test_data/test_datasets/test_vfi_dataset.py index 8296d10fb0..fded405043 100644 --- a/tests/test_data/test_datasets/test_vfi_dataset.py +++ b/tests/test_data/test_datasets/test_vfi_dataset.py @@ -6,16 +6,14 @@ class TestVFIDataset: - def __init__(self): - self.pipeline = [ - dict( - type='LoadImageFromFileList', io_backend='disk', key='inputs'), - dict(type='LoadImageFromFile', io_backend='disk', key='target'), - dict(type='FramesToTensor', keys=['inputs']), - dict(type='ImageToTensor', keys=['target']), - ] - self.folder = 'tests/data/vimeo90k' - self.ann_file = 'tests/data/vimeo90k/vfi_ann.txt' + pipeline = [ + dict(type='LoadImageFromFileList', io_backend='disk', key='inputs'), + dict(type='LoadImageFromFile', io_backend='disk', key='target'), + dict(type='FramesToTensor', keys=['inputs']), + dict(type='ImageToTensor', keys=['target']), + ] + folder = 'tests/data/vimeo90k' + ann_file = 'tests/data/vimeo90k/vfi_ann.txt' def test_base_vfi_dataset(self): diff --git a/tests/test_models/test_restorers/test_basic_restorer.py b/tests/test_models/test_restorers/test_basic_restorer.py index f50bf41516..5ef1a5562c 100644 --- a/tests/test_models/test_restorers/test_basic_restorer.py +++ b/tests/test_models/test_restorers/test_basic_restorer.py @@ -35,8 +35,8 @@ def test_basic_restorer(): assert isinstance(restorer.pixel_loss, L1Loss) # prepare data - inputs = torch.rand(1, 3, 2, 2) - targets = torch.rand(1, 3, 8, 8) + inputs = torch.rand(1, 3, 20, 20) + targets = torch.rand(1, 3, 80, 80) data_batch = {'lq': inputs, 'gt': targets} # prepare optimizer @@ -56,20 +56,20 @@ def test_basic_restorer(): assert torch.equal(outputs['results']['lq'], data_batch['lq']) assert torch.equal(outputs['results']['gt'], data_batch['gt']) assert torch.is_tensor(outputs['results']['output']) - assert outputs['results']['output'].size() == (1, 3, 8, 8) + assert outputs['results']['output'].size() == (1, 3, 80, 80) # test forward_test with torch.no_grad(): outputs = restorer(**data_batch, test_mode=True) assert torch.equal(outputs['lq'], data_batch['lq']) assert torch.is_tensor(outputs['output']) - assert outputs['output'].size() == (1, 3, 8, 8) + assert outputs['output'].size() == (1, 3, 80, 80) # test forward_dummy with torch.no_grad(): output = restorer.forward_dummy(data_batch['lq']) assert torch.is_tensor(output) - assert output.size() == (1, 3, 8, 8) + assert output.size() == (1, 3, 80, 80) # test train_step outputs = restorer.train_step(data_batch, optimizer) @@ -80,7 +80,7 @@ def test_basic_restorer(): assert torch.equal(outputs['results']['lq'], data_batch['lq']) assert torch.equal(outputs['results']['gt'], data_batch['gt']) assert torch.is_tensor(outputs['results']['output']) - assert outputs['results']['output'].size() == (1, 3, 8, 8) + assert outputs['results']['output'].size() == (1, 3, 80, 80) # test train_step and forward_test (gpu) if torch.cuda.is_available(): @@ -99,14 +99,14 @@ def test_basic_restorer(): assert torch.equal(outputs['results']['lq'], data_batch['lq'].cpu()) assert torch.equal(outputs['results']['gt'], data_batch['gt'].cpu()) assert torch.is_tensor(outputs['results']['output']) - assert outputs['results']['output'].size() == (1, 3, 8, 8) + assert outputs['results']['output'].size() == (1, 3, 80, 80) # forward_test with torch.no_grad(): outputs = restorer(**data_batch, test_mode=True) assert torch.equal(outputs['lq'], data_batch['lq'].cpu()) assert torch.is_tensor(outputs['output']) - assert outputs['output'].size() == (1, 3, 8, 8) + assert outputs['output'].size() == (1, 3, 80, 80) # train_step outputs = restorer.train_step(data_batch, optimizer) @@ -117,7 +117,7 @@ def test_basic_restorer(): assert torch.equal(outputs['results']['lq'], data_batch['lq'].cpu()) assert torch.equal(outputs['results']['gt'], data_batch['gt'].cpu()) assert torch.is_tensor(outputs['results']['output']) - assert outputs['results']['output'].size() == (1, 3, 8, 8) + assert outputs['results']['output'].size() == (1, 3, 80, 80) # test with metric and save image test_cfg = dict(metrics=('PSNR', 'SSIM'), crop_border=0) diff --git a/tests/test_models/test_video_interpolator/test_basic_interpolator.py b/tests/test_models/test_video_interpolator/test_basic_interpolator.py index a4214a4aba..c8c6e14ede 100644 --- a/tests/test_models/test_video_interpolator/test_basic_interpolator.py +++ b/tests/test_models/test_video_interpolator/test_basic_interpolator.py @@ -62,8 +62,8 @@ def test_basic_interpolator(): assert isinstance(restorer.pixel_loss, L1Loss) # prepare data - inputs = torch.rand(1, 2, 3, 8, 8) - target = torch.rand(1, 3, 8, 8) + inputs = torch.rand(1, 2, 3, 20, 20) + target = torch.rand(1, 3, 20, 20) data_batch = {'inputs': inputs, 'target': target} # prepare optimizer @@ -83,7 +83,7 @@ def test_basic_interpolator(): assert torch.equal(outputs['results']['inputs'], data_batch['inputs']) assert torch.equal(outputs['results']['target'], data_batch['target']) assert torch.is_tensor(outputs['results']['output']) - assert outputs['results']['output'].size() == (1, 3, 8, 8) + assert outputs['results']['output'].size() == (1, 3, 20, 20) # test forward_test with torch.no_grad(): @@ -91,13 +91,13 @@ def test_basic_interpolator(): outputs = restorer(**data_batch, test_mode=True) assert torch.equal(outputs['inputs'], data_batch['inputs']) assert torch.is_tensor(outputs['output']) - assert outputs['output'].size() == (1, 3, 8, 8) + assert outputs['output'].size() == (1, 3, 20, 20) # test forward_dummy with torch.no_grad(): output = restorer.forward_dummy(data_batch['inputs']) assert torch.is_tensor(output) - assert output.size() == (1, 3, 8, 8) + assert output.size() == (1, 3, 20, 20) # test train_step outputs = restorer.train_step(data_batch, optimizer) @@ -108,7 +108,7 @@ def test_basic_interpolator(): assert torch.equal(outputs['results']['inputs'], data_batch['inputs']) assert torch.equal(outputs['results']['target'], data_batch['target']) assert torch.is_tensor(outputs['results']['output']) - assert outputs['results']['output'].size() == (1, 3, 8, 8) + assert outputs['results']['output'].size() == (1, 3, 20, 20) # test train_step and forward_test (gpu) if torch.cuda.is_available(): @@ -129,7 +129,7 @@ def test_basic_interpolator(): assert torch.equal(outputs['results']['target'], data_batch['target'].cpu()) assert torch.is_tensor(outputs['results']['output']) - assert outputs['results']['output'].size() == (1, 3, 8, 8) + assert outputs['results']['output'].size() == (1, 3, 20, 20) # forward_test with torch.no_grad(): @@ -137,7 +137,7 @@ def test_basic_interpolator(): outputs = restorer(**data_batch, test_mode=True) assert torch.equal(outputs['inputs'], data_batch['inputs'].cpu()) assert torch.is_tensor(outputs['output']) - assert outputs['output'].size() == (1, 3, 8, 8) + assert outputs['output'].size() == (1, 3, 20, 20) # train_step outputs = restorer.train_step(data_batch, optimizer) @@ -150,7 +150,7 @@ def test_basic_interpolator(): assert torch.equal(outputs['results']['target'], data_batch['target'].cpu()) assert torch.is_tensor(outputs['results']['output']) - assert outputs['results']['output'].size() == (1, 3, 8, 8) + assert outputs['results']['output'].size() == (1, 3, 20, 20) # test with metric and save image test_cfg = dict(metrics=('PSNR', 'SSIM'), crop_border=0)