我正在尝试转换 Keras DarkNet 代码的部分内容,以使代码运行得更快。这是我试图优化的代码:
model_image_size = (416, 416)
import cv2
from PIL import Image
frame = cv2.imread("test.png", cv2.IMREAD_COLOR)
im = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
im = Image.fromarray(im).crop((1625, 785, 1920, 1080)) # crop ROI
resized_image = im.resize(tuple(reversed(model_image_size)), Image.BICUBIC)
image_data = np.array(resized_image, dtype='float32')
image_data /= 255.
image_data = np.expand_dims(image_data, 0) # Add batch dimension.
return image_data
Run Code Online (Sandbox Code Playgroud)
这是我尝试在不使用中间 PIL 转换来减少时间的情况下实现相同的输出:
model_image_size = (416, 416)
import cv2
frame = cv2.imread("test.png", cv2.IMREAD_COLOR)
frame = frame[785:1080,1625:1920] # crop ROI
im = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
resized_image = cv2.resize(im, model_image_size, interpolation …Run Code Online (Sandbox Code Playgroud)