ValueError: You are trying to restore a checkpoint from a legacy Keras optimizer into a v2.11+ Optimizer, which can cause errors.

[Christopher Atkinson]

I get the following error code while using code in google collab:

ValueError: You are trying to restore a checkpoint from a legacy Keras optimizer into a v2.11+ Optimizer, which can cause errors. Please update the optimizer referenced in your code to be an instance of tf.keras.optimizers.legacy.Optimizer, e.g.: tf.keras.optimizers.legacy.Adam.

Tried both instances with no solution to the problem.

The code used is shown below:

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import cv2
from skimage import measure
from tensorflow.keras.optimizers.legacy import Adam
from tensorflow.keras.preprocessing.image import load_img
from importlib import reload
import segmenteverygrain as seg
from tqdm import trange

import tensorflow as tf
model = seg.Unet()
model.compile(optimizer= "Adam", loss=seg.weighted_crossentropy, metrics=["accuracy"])
model.load_weights('./checkpoints/seg_model')

The very last line "model.load_weights" is where the error is and not sure how to approach it.

[Keshav Singh]

I am facing same issue.

[farzona05]

I am also getting this error and do not know how to solve it. If you figured out, can you please share with solution?

[lonelywanderer8]

I am also getting this error and do not know how to solve it. If you figured out, can you please share with solution?

I guess this may be due to different versions of TensorFlow, but it seems that the author did not provide the TensorFlow version

[Zoltán Sylvester]

Hi all, sorry for the slow response on this. I have uploaded an environment file that works for me on both Mac and Windows machines.