TensorFlow从指定checkpoint恢复

1. 打开保存checkpoint文件的路径。
2. 打开其中的checkpoint文件。
3. 如下：
4. all_model_checkpoint_paths: “model.ckpt-0”
   all_model_checkpoint_paths: “model.ckpt-100”
   all_model_checkpoint_paths: “model.ckpt-200”
   all_model_checkpoint_paths: “model.ckpt-300”
   all_model_checkpoint_paths: “model.ckpt-400”
   all_model_checkpoint_paths: “model.ckpt-500”
   all_model_checkpoint_paths: “model.ckpt-600”
   all_model_checkpoint_paths: “model.ckpt-700”
   all_model_checkpoint_paths: “model.ckpt-800”
   all_model_checkpoint_paths: “model.ckpt-900”
   all_model_checkpoint_paths: “model.ckpt-1000”
   all_model_checkpoint_paths: “model.ckpt-1100”
   all_model_checkpoint_paths: “model.ckpt-1200”
   all_model_checkpoint_paths: “model.ckpt-1300”
   假设你想从1300恢复。
   则把文件中的
   all_model_checkpoint_paths: “model.ckpt-1400”
   all_model_checkpoint_paths: “model.ckpt-1500”
   all_model_checkpoint_paths: “model.ckpt-1600”
   all_model_checkpoint_paths: “model.ckpt-1700”
   all_model_checkpoint_paths: “model.ckpt-1800”
   all_model_checkpoint_paths: “model.ckpt-1900”
   all_model_checkpoint_paths: “model.ckpt-2000”
   删除即可。