face_landmark icon indicating copy to clipboard operation
face_landmark copied to clipboard

预训练权重

Open Yakuho opened this issue 3 years ago • 0 comments

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

Yakuho avatar Apr 12 '21 11:04 Yakuho