610265158 / face_landmark

A simple method for face alignment based on wingloss and mutitask learning :)
Apache License 2.0
251 stars 80 forks source link

预训练权重 #51

Open Yakuho opened 3 years ago

Yakuho commented 3 years ago

作者你好,感谢你的开源!! 我在使用您的shufflenetv2_0.75预训练权重,想做迁移学习的时候发现,我导入的权重值貌似不匹配,你用的网络结构与是哪个呢?

from lib.core.model.shufflenet.simpleface import SimpleFace as SimpleFace_shufflenet
import numpy as np

pretrained_model = "./model/keypoints/variables/variables"
model = SimpleFace_shufflenet()
image = np.zeros(shape=(1, 160, 160, 3), dtype=np.float32)
model(image)
model.load_weights(pretrained_model)
    raise ValueError("Shapes %s and %s are incompatible" % (self, other))
ValueError: Shapes (3, 3, 48, 1) and (3, 3, 58, 1) are incompatible