How to use the mmcv.impad function in mmcv

img = np.random.randint(256, size=(10, 10, 3)).astype('uint8')
        padded_img = mmcv.impad(img, (15, 12, 3), [100, 110, 120])
        assert_array_equal(img, padded_img[:10, :10, :])
        assert_array_equal(
            np.array([100, 110, 120], dtype='uint8') * np.ones(
                (5, 12, 3), dtype='uint8'), padded_img[10:, :, :])
        assert_array_equal(
            np.array([100, 110, 120], dtype='uint8') * np.ones(
                (15, 2, 3), dtype='uint8'), padded_img[:, 10:, :])

        with pytest.raises(AssertionError):
            mmcv.impad(img, (15, ), 0)
        with pytest.raises(AssertionError):
            mmcv.impad(img, (5, 5), 0)
        with pytest.raises(AssertionError):
            mmcv.impad(img, (5, 5), [0, 1])

def test_impad(self):
        img = np.random.rand(10, 10, 3).astype(np.float32)
        padded_img = mmcv.impad(img, (15, 12), 0)
        assert_array_equal(img, padded_img[:10, :10, :])
        assert_array_equal(
            np.zeros((5, 12, 3), dtype='float32'), padded_img[10:, :, :])
        assert_array_equal(
            np.zeros((15, 2, 3), dtype='float32'), padded_img[:, 10:, :])

        img = np.random.randint(256, size=(10, 10, 3)).astype('uint8')
        padded_img = mmcv.impad(img, (15, 12, 3), [100, 110, 120])
        assert_array_equal(img, padded_img[:10, :10, :])
        assert_array_equal(
            np.array([100, 110, 120], dtype='uint8') * np.ones(
                (5, 12, 3), dtype='uint8'), padded_img[10:, :, :])
        assert_array_equal(
            np.array([100, 110, 120], dtype='uint8') * np.ones(
                (15, 2, 3), dtype='uint8'), padded_img[:, 10:, :])

np.zeros((15, 2, 3), dtype='float32'), padded_img[:, 10:, :])

        img = np.random.randint(256, size=(10, 10, 3)).astype('uint8')
        padded_img = mmcv.impad(img, (15, 12, 3), [100, 110, 120])
        assert_array_equal(img, padded_img[:10, :10, :])
        assert_array_equal(
            np.array([100, 110, 120], dtype='uint8') * np.ones(
                (5, 12, 3), dtype='uint8'), padded_img[10:, :, :])
        assert_array_equal(
            np.array([100, 110, 120], dtype='uint8') * np.ones(
                (15, 2, 3), dtype='uint8'), padded_img[:, 10:, :])

        with pytest.raises(AssertionError):
            mmcv.impad(img, (15, ), 0)
        with pytest.raises(AssertionError):
            mmcv.impad(img, (5, 5), 0)
        with pytest.raises(AssertionError):
            mmcv.impad(img, (5, 5), [0, 1])

def __call__(self, masks, pad_shape, scale_factor, flip=False):
        masks = [
            mmcv.imrescale(mask, scale_factor, interpolation='nearest')
            for mask in masks
        ]
        if flip:
            masks = [mask[:, ::-1] for mask in masks]
        padded_masks = [
            mmcv.impad(mask, pad_shape[:2], pad_val=0) for mask in masks
        ]
        padded_masks = np.stack(padded_masks, axis=0)
        return padded_masks

def __call__(self, results):
        if results['keep_ratio']:
            gt_seg = mmcv.imrescale(
                results['gt_semantic_seg'],
                results['scale'],
                interpolation='nearest')
        else:
            gt_seg = mmcv.imresize(
                results['gt_semantic_seg'],
                results['scale'],
                interpolation='nearest')
        if results['flip']:
            gt_seg = mmcv.imflip(gt_seg)
        if gt_seg.shape != results['pad_shape']:
            gt_seg = mmcv.impad(gt_seg, results['pad_shape'][:2])
        if self.scale_factor != 1:
            gt_seg = mmcv.imrescale(
                gt_seg, self.scale_factor, interpolation='nearest')
        results['gt_semantic_seg'] = gt_seg
        return results

def _pad_img(self, results):
        if self.size is not None:
            padded_img = mmcv.impad(results['img'], self.size, self.pad_val)
        elif self.size_divisor is not None:
            padded_img = mmcv.impad_to_multiple(
                results['img'], self.size_divisor, pad_val=self.pad_val)
        results['img'] = padded_img
        results['pad_shape'] = padded_img.shape
        results['pad_fixed_size'] = self.size
        results['pad_size_divisor'] = self.size_divisor

def _pad_seg(self, results):
        for key in results.get('seg_fields', []):
            results[key] = mmcv.impad(results[key], results['pad_shape'][:2])

# aspect ratio changed
        else:
            w_ratio, h_ratio = scale_factor[:2]
            if masks:
                h, w = masks[0].shape[:2]
                new_h = int(np.round(h * h_ratio))
                new_w = int(np.round(w * w_ratio))
                new_size = (new_w, new_h)
                masks = [
                    mmcv.imresize(mask, new_size, interpolation='nearest')
                    for mask in masks
                ]
        if flip:
            masks = [mask[:, ::-1] for mask in masks]
        padded_masks = [
            mmcv.impad(mask, pad_shape[:2], pad_val=0) for mask in masks
        ]
        padded_masks = np.stack(padded_masks, axis=0)
        return padded_masks

def __call__(self, masks, pad_shape, scale_factor, flip=False):
        masks = [
            mmcv.imrescale(mask, scale_factor, interpolation='nearest')
            for mask in masks
        ]
        if flip:
            masks = [mask[:, ::-1] for mask in masks]
        padded_masks = [
            mmcv.impad(mask, pad_shape[:2], pad_val=0) for mask in masks
        ]
        padded_masks = np.stack(padded_masks, axis=0)
        return padded_masks