Load Model from Checkpoints After Pre-training for Fine-Tuning Issue

[fatmacelebi]

After I run the simclr on custom dataset, I got checkpoints and I tried to load checkpoints to resnet model like below ;
import tensorflow as tf
from tensorflow.keras.models import *
checkpoint_path = '/tmp/model.ckpt-13079'

model =tf.keras.applications.ResNet101(
include_top=True, weights=None, input_shape=(224, 224, 3))
model.load_weights(checkpoint_path)
and I was not able to lead weights from checkpoints path and I got below error;
AssertionError Traceback (most recent call last)
~\AppData\Local\Temp/ipykernel_15012/3954170122.py in
----> 1 model.load_weights(checkpoint_path)

~\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\keras\engine\training.py in load_weights(self, filepath, by_name, skip_mismatch, options)
2306 # streaming restore for any variables created in the future.
2307 trackable_utils.streaming_restore(status=status, session=session)
-> 2308 status.assert_nontrivial_match()
2309 return status
2310 if h5py is None:

~\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\training\tracking\util.py in assert_nontrivial_match(self)
1023 # assert_nontrivial_match and assert_consumed (and both are less
1024 # useful since we don't touch Python objects or Python state).
-> 1025 return self.assert_consumed()
1026
1027 def _gather_saveable_objects(self):

~\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\training\tracking\util.py in assert_consumed(self)
1000 raise AssertionError(
1001 "Some objects had attributes which were not restored:{}".format(
-> 1002 "".join(unused_attribute_strings)))
1003 for trackable in self._graph_view.list_objects():
1004 # pylint: disable=protected-access

AssertionError: Some objects had attributes which were not restored:
<tf.Variable 'conv1_conv/kernel:0' shape=(7, 7, 3, 64) dtype=float32, numpy

Can you help please?
Thanks in Advance.