import megengine.hub
model = megengine.hub.load('megengine/models', 'resnet18', pretrained=True)
# or any of these variants
# model = megengine.hub.load('megengine/models', 'resnet34', pretrained=True)
# model = megengine.hub.load('megengine/models', 'resnet50', pretrained=True)
# model = megengine.hub.load('megengine/models', 'resnet101', pretrained=True)
# model = megengine.hub.load('megengine/models', 'resnet152', pretrained=True)
# model = megengine.hub.load('megengine/models', 'resnext50_32x4d', pretrained=True)
model.eval()

所有预训练模型希望数据被正确预处理。 模型要求输入BGR的图片, 短边缩放到256, 并中心裁剪至(224 x 224)的大小，最后做归一化处理 (均值为: [103.530, 116.280, 123.675], 标准差为: [57.375, 57.120, 58.395])。

下面是一段处理一张图片的样例代码。

# Download an example image from the megengine data website
import urllib
url, filename = ("https://data.megengine.org.cn/images/cat.jpg", "cat.jpg")
try: urllib.URLopener().retrieve(url, filename)
except: urllib.request.urlretrieve(url, filename)

# Read and pre-process the image
import cv2
import numpy as np
import megengine.data.transform as T
import megengine.functional as F

image = cv2.imread("cat.jpg")
transform = T.Compose([
    T.Resize(256),
    T.CenterCrop(224),
    T.Normalize(mean=[103.530, 116.280, 123.675], std=[57.375, 57.120, 58.395]),  # BGR
    T.ToMode("CHW"),
])
processed_img = transform.apply(image)[np.newaxis, :]  # CHW -> 1CHW
logits = model(processed_img)
probs = F.softmax(logits)
print(probs)

模型描述

目前我们提供了以下几个预训练模型，分别是resnet18, resnet34, resnet50, resnet101，resnet152, resnext50_32x4d，它们在ImageNet验证集上的单crop性能如下表：

参考文献

• Deep Residual Learning for Image Recognition, Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770-778
• Aggregated Residual Transformation for Deep Neural Networks, Saining Xie, Ross Girshick, Piotr Dollar, Zhuowen Tu, Kaiming He; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 1492-1500