XIAO

训练完后运行predict.py时在load_weights()时出错

15

训练自己的数据，完后进行预测时在load_weights()时shape不对，ValueError: Layer #32 (named "conv4_3_norm_mbox_conf"), weight has shape (3, 3, 512, 8), but the saved weight has shape (4, 512, 3, 3)，我的keras是2.3.1，K.image_data_format的问题我在训练前就改过来了，请问是什么原因呢？

clip

1

from clip import clip well，where is the clip, just from the https://github.com/openai/CLIP/clip ?