File size: 5,016 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 | #!/usr/bin/env python3
"""单图 axmodel 推理，输出原图+增强图拼接对比图。
依赖 axengine / cv2 / numpy，无 torch 相关操作。
所有参数写在文件顶部，运行时只需指定输入图片。
"""
import time
from pathlib import Path
import cv2
import numpy as np
import axengine as axe
# ───────────────────────── 默认参数 ─────────────────────────
AXMODEL_PATH = 'Retinexformer_224_224.axmodel'
MODEL_HEIGHT = 224
MODEL_WIDTH = 224
OUTPUT_DIR = './'
GAP = 8 # 拼接白缝宽度（像素）
# ────────────────────────────────────────────────────────────
IMAGE_SUFFIXES = {'.jpg', '.jpeg', '.png', '.bmp', '.tif', '.tiff', '.webp'}
def load_rgb_image(path):
"""读取图片，BGR → RGB。"""
bgr = cv2.imread(str(path), cv2.IMREAD_COLOR)
if bgr is None:
raise FileNotFoundError(f'无法读取图片: {path}')
return cv2.cvtColor(bgr, cv2.COLOR_BGR2RGB)
def preprocess(rgb):
"""RGB uint8 → NCHW uint8。"""
x = rgb.astype(np.uint8)
x = np.transpose(x, (2, 0, 1))[None, ...]
return np.ascontiguousarray(x, dtype=np.uint8)
def postprocess(output):
"""模型输出 NCHW float32 → RGB uint8。"""
if isinstance(output, (list, tuple)):
output = output[0]
output = np.asarray(output)
if output.ndim != 4 or output.shape[0] != 1:
raise ValueError(f'异常输出 shape: {output.shape}')
output = np.clip(output[0], 0.0, 1.0)
rgb = np.transpose(output, (1, 2, 0))
return (rgb * 255.0 + 0.5).astype(np.uint8)
def add_label(rgb, label):
"""在图像左上角添加黑色半透明标签。"""
canvas = rgb.copy()
bgr = cv2.cvtColor(canvas, cv2.COLOR_RGB2BGR)
cv2.rectangle(bgr, (0, 0), (190, 34), (0, 0, 0), thickness=-1)
cv2.putText(
bgr,
label,
(10, 24),
cv2.FONT_HERSHEY_SIMPLEX,
0.75,
(255, 255, 255),
2,
cv2.LINE_AA,
)
return cv2.cvtColor(bgr, cv2.COLOR_BGR2RGB)
def make_side_by_side(original_rgb, enhanced_rgb, gap):
"""左右拼接 Original | Enhanced，中间加白缝，同时标注标签。"""
if original_rgb.shape[:2] != enhanced_rgb.shape[:2]:
enhanced_rgb = cv2.resize(
enhanced_rgb,
(original_rgb.shape[1], original_rgb.shape[0]),
interpolation=cv2.INTER_AREA,
)
left = add_label(original_rgb, 'Original')
right = add_label(enhanced_rgb, 'Enhanced')
if gap <= 0:
return np.concatenate([left, right], axis=1)
spacer = np.full((left.shape[0], gap, 3), 255, dtype=np.uint8)
return np.concatenate([left, spacer, right], axis=1)
def save_rgb_image(path, rgb):
"""保存 RGB 图片为 PNG。"""
path = Path(path)
path.parent.mkdir(parents=True, exist_ok=True)
cv2.imwrite(str(path), cv2.cvtColor(rgb, cv2.COLOR_RGB2BGR))
def main():
import argparse
parser = argparse.ArgumentParser(description='单图 axmodel 推理 → 拼接图')
parser.add_argument('--input', default='1.png', help='输入图片路径')
args = parser.parse_args()
input_path = Path(args.input)
# 1. 读原图，记住原始尺寸
original_rgb = load_rgb_image(input_path)
orig_h, orig_w = original_rgb.shape[:2]
# 2. Resize 到模型输入尺寸
if (orig_h, orig_w) != (MODEL_HEIGHT, MODEL_WIDTH):
model_rgb = cv2.resize(original_rgb, (MODEL_WIDTH, MODEL_HEIGHT), interpolation=cv2.INTER_AREA)
else:
model_rgb = original_rgb
# 3. 预处理 → 推理
input_tensor = preprocess(model_rgb)
session = axe.InferenceSession(AXMODEL_PATH, providers=['AxEngineExecutionProvider'])
input_name = session.get_inputs()[0].name
output_names = [output.name for output in session.get_outputs()]
start = time.time()
axmodel_output = session.run(output_names, {input_name: input_tensor})[0]
elapsed = time.time() - start
# 4. 后处理 → 增强图（模型尺寸）
enhanced_model_size = postprocess(axmodel_output)
# 5. 将增强图还原到原始尺寸
if (orig_h, orig_w) != (MODEL_HEIGHT, MODEL_WIDTH):
enhanced_rgb = cv2.resize(enhanced_model_size, (orig_w, orig_h), interpolation=cv2.INTER_AREA)
else:
enhanced_rgb = enhanced_model_size
# 6. 拼接原图 + 增强图
comparison = make_side_by_side(original_rgb, enhanced_rgb, GAP)
# 7. 保存
output_path = Path(OUTPUT_DIR) / 'axmodel_res.png'
save_rgb_image(output_path, comparison)
print(f'输入: {input_path} ({orig_w}x{orig_h})')
print(f'模型: {AXMODEL_PATH} ({MODEL_WIDTH}x{MODEL_HEIGHT})')
print(f'输出: {output_path} ({comparison.shape[1]}x{comparison.shape[0]})')
print(f'耗时: {elapsed:.4f}s')
if __name__ == '__main__':
main()
|