import tensorflow as tf
from tensorflow.keras.applications import ResNet50
from tensorflow.keras.layers import LSTM, Dense, GlobalAveragePooling2D, Dropout
from tensorflow.keras.activations import relu

class Model(tf.keras.Model):
    def __init__(self, num_classes, latent_dim=2048, lstm_layers=1, hidden_dim=2048, bidirectional=False):
        super(Model, self).__init__()
        self.base_model = tf.keras.Sequential([
            ResNet50(include_top=False, weights=None, input_shape=(None, None, 3)),
        ], name='resnet50_base')
        self.base_model.layers[0].name = 'resnet50_base'  # Set a unique name for the ResNet50 model
        self.base_model.layers[0].trainable = False  # Ensure the ResNet50 model is not trainable
        self.lstm = LSTM(hidden_dim, return_sequences=True, return_state=True, name='lstm_layer')
        self.relu = relu
        self.dp = Dropout(0.4, name='dropout_layer')
        self.linear1 = Dense(num_classes, name='output_layer')
        self.avgpool = GlobalAveragePooling2D(name='global_avg_pooling')
        self.built = True  # Mark the model as built

    def call(self, inputs):
        batch_size, seq_length, h, w, c = inputs.shape.as_list()  # TensorFlow shape order is different
        inputs = tf.reshape(inputs, (batch_size * seq_length, h, w, c))
        fmap = self.base_model(inputs)
        x = self.avgpool(fmap)
        x = tf.reshape(x, (batch_size, seq_length, -1))
        x_lstm, _, _ = self.lstm(x)
        x = tf.reduce_mean(x_lstm, axis=1)
        x = self.dp(x)
        x = self.linear1(x)
        return fmap, x


model = Model(num_classes=2)  # Binary classification with 2 classes: 'real' and 'fake'`

after training and saving it as model.save(“vedio_model.keras”), when i try to load , the model ,
it gives error loaded_model = tf.keras.models.load_model(“vedio_model.keras”)

TypeError Traceback (most recent call last)
Cell In[34], line 1
—-> 1 loaded_model = tf.keras.models.load_model(“vedio_model.keras”)

File /usr/local/lib/python3.11/dist-packages/keras/src/saving/saving_api.py:176, in load_model(filepath, custom_objects, compile, safe_mode)
173 is_keras_zip = True
175 if is_keras_zip:
–> 176 return saving_lib.load_model(
177 filepath,
178 custom_objects=custom_objects,
179 compile=compile,
180 safe_mode=safe_mode,
181 )
182 if str(filepath).endswith((“.h5”, “.hdf5”)):
183 return legacy_h5_format.load_model_from_hdf5(filepath)

File /usr/local/lib/python3.11/dist-packages/keras/src/saving/saving_lib.py:155, in load_model(filepath, custom_objects, compile, safe_mode)
153 # Construct the model from the configuration file in the archive.
154 with ObjectSharingScope():
–> 155 model = deserialize_keras_object(
156 config_dict, custom_objects, safe_mode=safe_mode
157 )
159 all_filenames = zf.namelist()
160 if _VARS_FNAME + “.h5” in all_filenames:

File /usr/local/lib/python3.11/dist-packages/keras/src/saving/serialization_lib.py:687, in deserialize_keras_object(config, custom_objects, safe_mode, **kwargs)
684 if obj is not None:
685 return obj
–> 687 cls = _retrieve_class_or_fn(
688 class_name,
689 registered_name,
690 module,
691 obj_type=”class”,
692 full_config=config,
693 custom_objects=custom_objects,
694 )
696 if isinstance(cls, types.FunctionType):
697 return cls

File /usr/local/lib/python3.11/dist-packages/keras/src/saving/serialization_lib.py:805, in _retrieve_class_or_fn(name, registered_name, module, obj_type, full_config, custom_objects)
“ 802 if obj is not None:
803 return obj
–> 805 raise TypeError(
806 f”Could not locate {obj_type} ‘{name}’. ”
807 “Make sure custom classes are decorated with ”
808 “`@keras.saving.r

``

egister_keras_serializable()`. ”
809 f”Full object config: {full_config}”
810 )

TypeError: Could not locate class ‘Model’. Make sure custom classes are decorated with @keras.saving.register_keras_serializable(). Full object config: {‘module’: None, ‘class_name’: ‘Model’, ‘config’: {‘trainable’: True, ‘dtype’: ‘float32’}, ‘registered_name’: ‘Model’}

There was no error while , training and saving. but it is e=giving error while loading