mmdetection/tests/test_pipelines/test_transform.py

import copy
import os.path as osp

import mmcv
import numpy as np
import pytest
from mmcv.utils import build_from_cfg

from mmdet.datasets.builder import PIPELINES


def test_resize():
    # test assertion if img_scale is a list
    with pytest.raises(AssertionError):
        transform = dict(type='Resize', img_scale=[1333, 800], keep_ratio=True)
        build_from_cfg(transform, PIPELINES)

    # test assertion if len(img_scale) while ratio_range is not None
    with pytest.raises(AssertionError):
        transform = dict(
            type='Resize',
            img_scale=[(1333, 800), (1333, 600)],
            ratio_range=(0.9, 1.1),
            keep_ratio=True)
        build_from_cfg(transform, PIPELINES)

    # test assertion for invalid multiscale_mode
    with pytest.raises(AssertionError):
        transform = dict(
            type='Resize',
            img_scale=[(1333, 800), (1333, 600)],
            keep_ratio=True,
            multiscale_mode='2333')
        build_from_cfg(transform, PIPELINES)

    transform = dict(type='Resize', img_scale=(1333, 800), keep_ratio=True)
    resize_module = build_from_cfg(transform, PIPELINES)

    results = dict()
    img = mmcv.imread(
        osp.join(osp.dirname(__file__), '../data/color.jpg'), 'color')
    results['img'] = img
    results['img2'] = copy.deepcopy(img)
    results['img_shape'] = img.shape
    results['ori_shape'] = img.shape
    # Set initial values for default meta_keys
    results['pad_shape'] = img.shape
    results['scale_factor'] = 1.0
    results['img_fields'] = ['img', 'img2']

    results = resize_module(results)
    assert np.equal(results['img'], results['img2']).all()

    results.pop('scale')
    transform = dict(
        type='Resize',
        img_scale=(1280, 800),
        multiscale_mode='value',
        keep_ratio=False)
    resize_module = build_from_cfg(transform, PIPELINES)
    results = resize_module(results)
    assert np.equal(results['img'], results['img2']).all()
    assert results['img_shape'] == (800, 1280, 3)


def test_flip():
    # test assertion for invalid flip_ratio
    with pytest.raises(AssertionError):
        transform = dict(type='RandomFlip', flip_ratio=1.5)
        build_from_cfg(transform, PIPELINES)

    # test assertion for invalid direction
    with pytest.raises(AssertionError):
        transform = dict(
            type='RandomFlip', flip_ratio=1, direction='horizonta')
        build_from_cfg(transform, PIPELINES)

    transform = dict(type='RandomFlip', flip_ratio=1)
    flip_module = build_from_cfg(transform, PIPELINES)

    results = dict()
    img = mmcv.imread(
        osp.join(osp.dirname(__file__), '../data/color.jpg'), 'color')
    original_img = copy.deepcopy(img)
    results['img'] = img
    results['img2'] = copy.deepcopy(img)
    results['img_shape'] = img.shape
    results['ori_shape'] = img.shape
    # Set initial values for default meta_keys
    results['pad_shape'] = img.shape
    results['scale_factor'] = 1.0
    results['img_fields'] = ['img', 'img2']

    results = flip_module(results)
    assert np.equal(results['img'], results['img2']).all()

    flip_module = build_from_cfg(transform, PIPELINES)
    results = flip_module(results)
    assert np.equal(results['img'], results['img2']).all()
    assert np.equal(original_img, results['img']).all()


def test_pad():
    # test assertion if both size_divisor and size is None
    with pytest.raises(AssertionError):
        transform = dict(type='Pad')
        build_from_cfg(transform, PIPELINES)

    transform = dict(type='Pad', size_divisor=32)
    transform = build_from_cfg(transform, PIPELINES)
    results = dict()
    img = mmcv.imread(
        osp.join(osp.dirname(__file__), '../data/color.jpg'), 'color')
    original_img = copy.deepcopy(img)
    results['img'] = img
    results['img2'] = copy.deepcopy(img)
    results['img_shape'] = img.shape
    results['ori_shape'] = img.shape
    # Set initial values for default meta_keys
    results['pad_shape'] = img.shape
    results['scale_factor'] = 1.0
    results['img_fields'] = ['img', 'img2']

    results = transform(results)
    assert np.equal(results['img'], results['img2']).all()
    # original img already divisible by 32
    assert np.equal(results['img'], original_img).all()
    img_shape = results['img'].shape
    assert img_shape[0] % 32 == 0
    assert img_shape[1] % 32 == 0

    resize_transform = dict(
        type='Resize', img_scale=(1333, 800), keep_ratio=True)
    resize_module = build_from_cfg(resize_transform, PIPELINES)
    results = resize_module(results)
    results = transform(results)
    img_shape = results['img'].shape
    assert np.equal(results['img'], results['img2']).all()
    assert img_shape[0] % 32 == 0
    assert img_shape[1] % 32 == 0


def test_normalize():
    img_norm_cfg = dict(
        mean=[123.675, 116.28, 103.53],
        std=[58.395, 57.12, 57.375],
        to_rgb=True)
    transform = dict(type='Normalize', **img_norm_cfg)
    transform = build_from_cfg(transform, PIPELINES)
    results = dict()
    img = mmcv.imread(
        osp.join(osp.dirname(__file__), '../data/color.jpg'), 'color')
    original_img = copy.deepcopy(img)
    results['img'] = img
    results['img2'] = copy.deepcopy(img)
    results['img_shape'] = img.shape
    results['ori_shape'] = img.shape
    # Set initial values for default meta_keys
    results['pad_shape'] = img.shape
    results['scale_factor'] = 1.0
    results['img_fields'] = ['img', 'img2']

    results = transform(results)
    assert np.equal(results['img'], results['img2']).all()

    mean = np.array(img_norm_cfg['mean'])
    std = np.array(img_norm_cfg['std'])
    converted_img = (original_img[..., ::-1] - mean) / std
    assert np.allclose(results['img'], converted_img)