最近在用tensorflow 2.2 的环境训练有关centernet的模型，此前已经跑通了centernet_resnet50_v2，训练效果还可以，这两天想试下centernet_hourglass104_512*512的预训练模型，但是总是遇到一个错误也不知到哪里出了问题，训练的时候指定4个gpu,配置文件使用centernet_hourglass104_512x512_coco17_tpu-8.config,按照要求更改，报错代码如下
A checkpoint was restored (e.g. tf.train.Checkpoint.restore or tf.keras.Model.load_weights) but not all checkpointed values were used. See above for specific issues. Use expect_partial() on the load status object, e.g. tf.train.Checkpoint.restore(…).expect_partial(), to silence these warnings, or use assert_consumed() to make the check explicit.
1 Like