ValueError: The passed save_path is not a valid checkpoint: model/model.ckpt-43000

[JianfengNing]

How to fix this problem?

raceback (most recent call last): File "D:/Desktop/Codes/deeponet-master/deeponet-master/src/deeponet_pde.py", line 285, in main() File "D:/Desktop/Codes/deeponet-master/deeponet-master/src/deeponet_pde.py", line 281, in main run(problem, system, space, T, m, nn, net, lr, epochs, num_train, num_test) File "D:/Desktop/Codes/deeponet-master/deeponet-master/src/deeponet_pde.py", line 176, in run model.restore("model/model.ckpt-" + str(train_state.best_step), verbose=1) File "D:\Users\FIVE\miniconda3\lib\site-packages\deepxde\model.py", line 666, in restore self.saver.restore(self.sess, save_path) File "D:\Users\FIVE\miniconda3\lib\site-packages\tensorflow\python\training\saver.py", line 1290, in restore raise ValueError("The passed save_path is not a valid checkpoint: " + ValueError: The passed save_path is not a valid checkpoint: model/model.ckpt-43000

[lululxvi]

What is your backend?

[JianfengNing]

font{
    line-height: 1.6;
}
ul,ol{
    padding-left: 20px;
    list-style-position: inside;
}

tf2.x

On 12/7/2021 09:20，Lu ***@***.***> wrote： 

What is your backend?

—You are receiving this because you authored the thread.Reply to this email directly, view it on GitHub, or unsubscribe.Triage notifications on the go with GitHub Mobile for iOS or Android.

[MinZhu123]

You could replace the error line with model.restore(f"model/model-{train_state.best_step}.ckpt", verbose=1)

[cfd-ai]

@minzhu-penn - May I know which version of TensorFlow you use and which backend?
I had to do this: model.restore("model/model.ckpt-" + str(train_state.best_step) + ".ckpt", verbose=1) Because model files are like: model.ckpt-500.ckpt.meta model.ckpt-500.ckpt.index model.ckpt-500.ckpt.data-00000-of-00001

Backend: tensorflow.compat.v1 TensorFlow version: 2.6.2

[DaJiang7]

@JianfengNing I have the same problem as you. You can check the running memory of the computer.

[anshumansinha16]

I am getting this error as well! My backend is : Using backend: tensorflow.compat.v1'

code:

# Restore the best test loss model
    model.restore( save_dir +save_str+"/model.ckpt-" + str(np.argmin(model.losshistory.loss_test)*100), verbose=0)

Error:

Traceback (most recent call last):
  File "/Users/anshumansinha/Desktop/ML_project/./main.py", line 311, in <module>
    NN_MSEs_test, NN_MSEs_train = DeepONet(samples, split, y/np.max(np.abs(y)) , I, inds, neurons, epochs, b_layers)
  File "/Users/anshumansinha/Desktop/ML_project/./main.py", line 289, in DeepONet
    model.restore( save_dir +save_str+"/model.ckpt-" + str(np.argmin(model.losshistory.loss_test)*100), verbose=0)
  File "/Users/anshumansinha/venv/lib/python3.10/site-packages/deepxde/model.py", line 914, in restore
    self.saver.restore(self.sess, save_path)
  File "/Users/anshumansinha/venv/lib/python3.10/site-packages/tensorflow/python/training/saver.py", line 1409, in restore
    raise ValueError("The passed save_path is not a valid checkpoint: " +
ValueError: The passed save_path is not a valid checkpoint: /Users/anshumansinha/Desktop/ML_project/model/Levin1_Seed_1_Samples_100_X_4_5_epochs_10_blayers_3_neurons_125/model.ckpt-100

[anshumansinha16]

What is your backend?

I am using, `Using backend: tensorflow.compat.v1' and getting similar error : link

[lululxvi]

See FAQ Q: More details about DeepXDE source code, and want to modify DeepXDE at https://deepxde.readthedocs.io/en/latest/user/faq.html