File size: 4,864 Bytes
525e655
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
import argparse
import os
import time

import axengine as axe
import numpy as np
from PIL import Image, ImageDraw


def get_tensor_dtype(tensor_info):
    dtype = getattr(tensor_info, 'dtype', None)
    if dtype is None:
        dtype = getattr(tensor_info, 'type', None)
    return str(dtype).lower() if dtype is not None else ''


def format_tensor_stats(name, tensor):
    tensor_np = np.asarray(tensor)
    return '{}: dtype={}, shape={}, min={:.6f}, max={:.6f}'.format(
        name,
        tensor_np.dtype,
        tensor_np.shape,
        float(tensor_np.min()),
        float(tensor_np.max()),
    )


def preprocess(image_path, height, width, resize, input_dtype):
    original_image = Image.open(image_path).convert('RGB')
    original_size = original_image.size
    if resize:
        model_image = original_image.resize((width, height), Image.BILINEAR)
    else:
        if original_image.size[0] < width or original_image.size[1] < height:
            raise ValueError('Image is smaller than axmodel input size: {}'.format(image_path))
        model_image = original_image.crop((0, 0, width, height))

    image_np = np.asarray(model_image)
    if 'float' in input_dtype:
        image_np = image_np.astype(np.float32) / 255.0
    else:
        image_np = image_np.astype(np.uint8)
    image_np = image_np.transpose(2, 0, 1)[None, :, :, :]
    return original_image, original_size, image_np


def postprocess(enhanced_np, original_size):
    enhanced_np = enhanced_np[0].transpose(1, 2, 0)
    max_value = float(enhanced_np.max())
    min_value = float(enhanced_np.min())
    if max_value <= 1.5 and min_value >= -0.5:
        enhanced_np = np.clip(enhanced_np, 0.0, 1.0) * 255.0
    else:
        enhanced_np = np.clip(enhanced_np, 0.0, 255.0)
    enhanced_np = enhanced_np.round().astype(np.uint8)
    enhanced_image = Image.fromarray(enhanced_np)
    return enhanced_image.resize(original_size, Image.BILINEAR)


def add_label(image, text):
    label_height = 32
    canvas = Image.new('RGB', (image.width, image.height + label_height), color=(0, 0, 0))
    canvas.paste(image, (0, label_height))
    draw = ImageDraw.Draw(canvas)
    draw.text((10, 8), text, fill=(255, 255, 255))
    return canvas


def save_compare(original_image, enhanced_image, result_path):
    original_labeled = add_label(original_image, 'Original')
    enhanced_labeled = add_label(enhanced_image, 'Result')
    compare_image = Image.new('RGB', (original_labeled.width + enhanced_labeled.width, original_labeled.height))
    compare_image.paste(original_labeled, (0, 0))
    compare_image.paste(enhanced_labeled, (original_labeled.width, 0))
    result_dir = os.path.dirname(result_path)
    if result_dir and not os.path.exists(result_dir):
        os.makedirs(result_dir)
    compare_image.save(result_path)


def build_axmodel_session(axmodel_path):
    return axe.InferenceSession(axmodel_path, providers=['AxEngineExecutionProvider'])


def infer(config):
    if not os.path.isfile(config.input):
        raise ValueError('Input image does not exist: {}'.format(config.input))

    session = build_axmodel_session(config.axmodel)
    input_info = session.get_inputs()[0]
    output_info = session.get_outputs()[0]
    input_name = input_info.name
    input_shape = input_info.shape
    input_dtype = get_tensor_dtype(input_info)
    output_dtype = get_tensor_dtype(output_info)
    height = int(input_shape[2]) if config.height <= 0 else config.height
    width = int(input_shape[3]) if config.width <= 0 else config.width

    original_image, original_size, input_np = preprocess(
        config.input,
        height,
        width,
        bool(config.resize),
        input_dtype,
    )
    start = time.time()
    axmodel_outputs = session.run(None, {input_name: input_np})
    axmodel_enhanced = axmodel_outputs[0]
    elapsed = time.time() - start

    enhanced_image = postprocess(axmodel_enhanced, original_size)
    save_compare(original_image, enhanced_image, config.output)

    print('Input image:', config.input)
    print('Output image:', config.output)
    print('Model input dtype:', input_dtype or 'unknown')
    print('Model output dtype:', output_dtype or 'unknown')
    print(format_tensor_stats('Prepared input', input_np))
    print(format_tensor_stats('Model output', axmodel_enhanced))
    print('axmodel time:', elapsed)


if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('--axmodel', type=str, default='zerodcepp_512_sf8.axmodel')
    parser.add_argument('--input', type=str, default='101_3_.png')
    parser.add_argument('--output', type=str, default='axmodel_res.png')
    parser.add_argument('--height', type=int, default=512)
    parser.add_argument('--width', type=int, default=512)
    parser.add_argument('--resize', type=int, default=1)
    config = parser.parse_args()

    infer(config)