"ValueError: Layer 'dense' expected 1 input(s). Received 2 instead" on tf.keras.models.load_model about tensorflow HOT 18 OPEN

input_shape = (224, 224, 3)
model = tf.keras.models.load_model('model.keras', compile=False, custom_objects={'input_shape': input_shape})

base_model = keras.applications.MobileNetV2(input_shape=(224,224,3),include_top=False,weights="imagenet")
model = keras.Sequential([
    base_model,
    keras.layers.GlobalAveragePooling2D(),
    keras.layers.Dropout(rate=0.5),
    keras.layers.Dense(8,activation='softmax'),
])

model.compile(...)
model.fit(...)

model.summary() #OK

model.save("test_mobilenetv2_save.keras")

model_2 = keras.saving.load_model("test_mobilenetv2_save.keras") #Error
model_2 = keras.saving.load_model("test_mobilenetv2_save.keras",compile=False, custom_objects={'input_shape': input_shape}) #Error

model_2.summary() 

base_model2 = keras.applications.MobileNetV2(input_shape=(224,224,3),include_top=False,weights="imagenet")

base_model2.trainable = True

model2 = keras.Sequential([
    base_model2,
    keras.layers.GlobalAveragePooling2D(),
    keras.layers.Dropout(rate=0.5),
    keras.layers.Dense(8,activation='softmax'),
])

model2.compile(
    loss=loss,
    # optimizer=keras.optimizers.SGD(learning_rate=0.01),
    optimizer = optimizer,
    metrics=[
        metrics.CategoricalAccuracy(),
        metrics.TopKCategoricalAccuracy(k=3),
    ]
)

model2.summary()

model2.predict(np.ones((32,224,224,3))) #must build model first or you not able to load weights

model2.load_weights("mobilenetv2_weights_only.weights.h5", skip_mismatch=False)

>>> tf.keras.models.load_model('model.keras', compile=False, custom_objects={'input_shape': (48, 48, 3)})
...
ValueError: Layer 'dense' expected 1 input(s). Received 2 instead.

model = build_model()
model.build(input_shape=(None, *INPUT_SHAPE))
model.load_weights('model.weights.h5')

import pathlib
import pickle
import tensorflow as tf
import matplotlib.pyplot as plt
import numpy as np
from keras.preprocessing.image import ImageDataGenerator

'''
import os
for dirname, _, filenames in os.walk('/kaggle/input'):
    for filename in filenames:
        print(os.path.join(dirname, filename))
'''
format_1 = '/kaggle/input/flower-dataset/train'
format_2 = '/kaggle/input/flower-dataset/valid'
train_dir = pathlib.Path(format_1)
valid_dir = pathlib.Path(format_2)
train_count = len(list(train_dir.glob('*/*.jpg')))
valid_count = len(list(valid_dir.glob('*/*.jpg')))

print(train_count)
print(valid_count)

CLASS_NAMES = np.array([item.name for item in train_dir.glob('*') if item.is_dir()])

image_generator = tf.keras.preprocessing.image.ImageDataGenerator(rescale=1. / 255)
BATCH_SIZE = 32
IMG_HEIGHT = 224
IMG_WIDTH = 224
train_data_gen = image_generator.flow_from_directory(directory=str(train_dir),
                                                     batch_size=BATCH_SIZE,
                                                     target_size=(IMG_HEIGHT, IMG_WIDTH),
                                                     shuffle=True,
                                                     classes=list(CLASS_NAMES))
valid_data_gen = image_generator.flow_from_directory(directory=str(valid_dir),
                                                     batch_size=BATCH_SIZE,
                                                     target_size=(IMG_HEIGHT, IMG_WIDTH),
                                                     shuffle=True,
                                                     classes=list(CLASS_NAMES))
print(CLASS_NAMES)
ResNet50 = tf.keras.applications.resnet_v2.ResNet50V2(include_top=False, weights='imagenet', input_shape=(224, 224, 3))
ResNet50.trainable = True
my_net = tf.keras.models.Sequential()
my_net.add(ResNet50)
my_net.add(tf.keras.layers.GlobalAveragePooling2D())
my_net.add(tf.keras.layers.Dense(100, activation='softmax'))
my_net.summary()
my_net.compile(optimizer=tf.keras.optimizers.Adamax(0.001),
            loss='categorical_crossentropy',
            metrics=['accuracy'])
epoch_steps = train_count // BATCH_SIZE
val_steps = valid_count // BATCH_SIZE
my_net.fit_generator(
    train_data_gen,
    steps_per_epoch=epoch_steps,
    epochs=5,
    validation_data=valid_data_gen,
    validation_steps=val_steps
)
my_net.save('flower.h5')

Traceback (most recent call last):
  File "/root/keras-flask-deploy-webapp/app.py", line 42, in <module>
    model = tf.keras.models.load_model(MODEL_PATH, compile=False, custom_objects={'input_shape': input_shape})
  File "/usr/local/lib/python3.10/dist-packages/keras/src/saving/saving_api.py", line 183, in load_model
    return legacy_h5_format.load_model_from_hdf5(filepath)
  File "/usr/local/lib/python3.10/dist-packages/keras/src/legacy/saving/legacy_h5_format.py", line 133, in load_model_from_hdf5
    model = saving_utils.model_from_config(
  File "/usr/local/lib/python3.10/dist-packages/keras/src/legacy/saving/saving_utils.py", line 85, in model_from_config
    return serialization.deserialize_keras_object(
  File "/usr/local/lib/python3.10/dist-packages/keras/src/legacy/saving/serialization.py", line 495, in deserialize_keras_object
    deserialized_obj = cls.from_config(
  File "/usr/local/lib/python3.10/dist-packages/keras/src/models/sequential.py", line 335, in from_config
    model.add(layer)
  File "/usr/local/lib/python3.10/dist-packages/keras/src/models/sequential.py", line 116, in add
    self._maybe_rebuild()
  File "/usr/local/lib/python3.10/dist-packages/keras/src/models/sequential.py", line 135, in _maybe_rebuild
    self.build(input_shape)
  File "/usr/local/lib/python3.10/dist-packages/keras/src/layers/layer.py", line 223, in build_wrapper
    original_build_method(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/keras/src/models/sequential.py", line 176, in build
    x = layer(x)
  File "/usr/local/lib/python3.10/dist-packages/keras/src/utils/traceback_utils.py", line 122, in error_handler
    raise e.with_traceback(filtered_tb) from None
  File "/usr/local/lib/python3.10/dist-packages/keras/src/layers/input_spec.py", line 156, in assert_input_compatibility
    raise ValueError(
ValueError: Layer 'dense' expected 1 input(s). Received 2 instead.

import tensorflow as tf
from tensorflow.keras.applications import EfficientNetV2S

V2S_model = EfficientNetV2S(weights='imagenet',
                        include_top=False,
                        input_shape=(224, 224, 3))

for layer in V2S_model.layers:
  layer.trainable = False
from tensorflow.keras import layers

image_preprocess = tf.keras.Sequential([
    tf.keras.Input((None,None,3)),
    layers.Resizing(224,224, crop_to_aspect_ratio = True),
    layers.RandomFlip("horizontal_and_vertical"),
    layers.RandomRotation(0.2)
], name = "image_aug")

transfer_model = tf.keras.Sequential([
    tf.keras.Input((None,None,3)),
    image_preprocess,
    V2S_model,
    layers.GlobalAveragePooling2D(),
    layers.Dense(512, activation='relu'),
    layers.Dropout(0.2),
    layers.Dense(1, activation = 'sigmoid')
])

transfer_model.summary()

metrics = [tf.keras.metrics.BinaryAccuracy(threshold=0.5, name='accuracy'),
           tf.keras.metrics.AUC(),
           tf.keras.metrics.TruePositives(),
           tf.keras.metrics.TrueNegatives(),
           tf.keras.metrics.FalsePositives(),
           tf.keras.metrics.FalseNegatives()
          ]

transfer_model.compile(loss=tf.keras.losses.BinaryCrossentropy(),
                       optimizer=tf.keras.optimizers.Adam(learning_rate=0.001),
                       metrics=metrics)

BATCH_SIZE = 16
IMAGE_SIZE = (224,224)
SEED = 42

# This sets up a training and validation set from our ../data/ directory
train_dataset = tf.keras.utils.image_dataset_from_directory(
    '../data/',
    class_names = ['not_niblet','niblet'],
    color_mode='rgb',
    batch_size=BATCH_SIZE,
    image_size=IMAGE_SIZE,
    shuffle=True,
    validation_split=0.2,
    subset='training',
    seed=SEED)

# This is the validation set. Notice `shuffle = FALSE` and `subset = validation`
val_dataset = tf.keras.utils.image_dataset_from_directory(
    '../data/',
    class_names = ['not_niblet','niblet'],
    color_mode='rgb',
    batch_size=BATCH_SIZE,
    image_size=IMAGE_SIZE,
    shuffle=True,
    validation_split=0.2,
    subset='validation',
    seed=SEED)

from tensorflow.keras.callbacks import EarlyStopping

es = EarlyStopping(patience=15, monitor='val_loss')

history = transfer_model.fit(train_dataset, epochs=100,
                             validation_data=val_dataset,
                             callbacks=[es])

transfer_model.save('../models/transfer_model_gt_2024_04_23.keras')

transfer_model_loaded = tf.keras.models.load_model('../models/transfer_model_gt_2024_04_23.keras')

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
Cell In[16], line 2
      1 input_shape = (None,None,3)
----> 2 transfer_model_loaded = tf.keras.models.load_model('../models/transfer_model_gt_2024_04_23.keras', compile=False, custom_objects={'input_shape': input_shape})

File [~\anaconda3\envs\CS380_final\Lib\site-packages\keras\src\saving\saving_api.py:176](http://localhost:8888/lab/tree/Documents/GitHub/CSC380/scripts/~/anaconda3/envs/CS380_final/Lib/site-packages/keras/src/saving/saving_api.py#line=175), 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 [~\anaconda3\envs\CS380_final\Lib\site-packages\keras\src\saving\saving_lib.py:152](http://localhost:8888/lab/tree/Documents/GitHub/CSC380/scripts/~/anaconda3/envs/CS380_final/Lib/site-packages/keras/src/saving/saving_lib.py#line=151), in load_model(filepath, custom_objects, compile, safe_mode)
    147     raise ValueError(
    148         "Invalid filename: expected a `.keras` extension. "
    149         f"Received: filepath={filepath}"
    150     )
    151 with open(filepath, "rb") as f:
--> 152     return _load_model_from_fileobj(
    153         f, custom_objects, compile, safe_mode
    154     )

File [~\anaconda3\envs\CS380_final\Lib\site-packages\keras\src\saving\saving_lib.py:170](http://localhost:8888/lab/tree/Documents/GitHub/CSC380/scripts/~/anaconda3/envs/CS380_final/Lib/site-packages/keras/src/saving/saving_lib.py#line=169), in _load_model_from_fileobj(fileobj, custom_objects, compile, safe_mode)
    168 # Construct the model from the configuration file in the archive.
    169 with ObjectSharingScope():
--> 170     model = deserialize_keras_object(
    171         config_dict, custom_objects, safe_mode=safe_mode
    172     )
    174 all_filenames = zf.namelist()
    175 if _VARS_FNAME + ".h5" in all_filenames:

File [~\anaconda3\envs\CS380_final\Lib\site-packages\keras\src\saving\serialization_lib.py:711](http://localhost:8888/lab/tree/Documents/GitHub/CSC380/scripts/~/anaconda3/envs/CS380_final/Lib/site-packages/keras/src/saving/serialization_lib.py#line=710), in deserialize_keras_object(config, custom_objects, safe_mode, **kwargs)
    709 with custom_obj_scope, safe_mode_scope:
    710     try:
--> 711         instance = cls.from_config(inner_config)
    712     except TypeError as e:
    713         raise TypeError(
    714             f"{cls} could not be deserialized properly. Please"
    715             " ensure that components that are Python object"
   (...)
    719             f"\n\nconfig={config}[.\n\nException](http://localhost:8888/lab/tree/Documents/GitHub/CSC380/scripts/n/nException) encountered: {e}"
    720         )

File [~\anaconda3\envs\CS380_final\Lib\site-packages\keras\src\models\sequential.py:339](http://localhost:8888/lab/tree/Documents/GitHub/CSC380/scripts/~/anaconda3/envs/CS380_final/Lib/site-packages/keras/src/models/sequential.py#line=338), in Sequential.from_config(cls, config, custom_objects)
    334     else:
    335         layer = serialization_lib.deserialize_keras_object(
    336             layer_config,
    337             custom_objects=custom_objects,
    338         )
--> 339     model.add(layer)
    340 if (
    341     not model._functional
    342     and build_input_shape
    343     and isinstance(build_input_shape, (tuple, list))
    344 ):
    345     model.build(build_input_shape)

File [~\anaconda3\envs\CS380_final\Lib\site-packages\keras\src\models\sequential.py:120](http://localhost:8888/lab/tree/Documents/GitHub/CSC380/scripts/~/anaconda3/envs/CS380_final/Lib/site-packages/keras/src/models/sequential.py#line=119), in Sequential.add(self, layer, rebuild)
    118 self._layers.append(layer)
    119 if rebuild:
--> 120     self._maybe_rebuild()
    121 else:
    122     self.built = False

File [~\anaconda3\envs\CS380_final\Lib\site-packages\keras\src\models\sequential.py:139](http://localhost:8888/lab/tree/Documents/GitHub/CSC380/scripts/~/anaconda3/envs/CS380_final/Lib/site-packages/keras/src/models/sequential.py#line=138), in Sequential._maybe_rebuild(self)
    137 if isinstance(self._layers[0], InputLayer) and len(self._layers) > 1:
    138     input_shape = self._layers[0].batch_shape
--> 139     self.build(input_shape)

File [~\anaconda3\envs\CS380_final\Lib\site-packages\keras\src\layers\layer.py:222](http://localhost:8888/lab/tree/Documents/GitHub/CSC380/scripts/~/anaconda3/envs/CS380_final/Lib/site-packages/keras/src/layers/layer.py#line=221), in Layer.__new__.<locals>.build_wrapper(*args, **kwargs)
    219 @wraps(original_build_method)
    220 def build_wrapper(*args, **kwargs):
    221     with obj._open_name_scope():
--> 222         original_build_method(*args, **kwargs)
    223     # Record build config.
    224     signature = inspect.signature(original_build_method)

File [~\anaconda3\envs\CS380_final\Lib\site-packages\keras\src\models\sequential.py:180](http://localhost:8888/lab/tree/Documents/GitHub/CSC380/scripts/~/anaconda3/envs/CS380_final/Lib/site-packages/keras/src/models/sequential.py#line=179), in Sequential.build(self, input_shape)
    178 for layer in self._layers[1:]:
    179     try:
--> 180         x = layer(x)
    181     except NotImplementedError:
    182         # Can happen if shape inference is not implemented.
    183         # TODO: consider reverting inbound nodes on layers processed.
    184         return

File [~\anaconda3\envs\CS380_final\Lib\site-packages\keras\src\utils\traceback_utils.py:122](http://localhost:8888/lab/tree/Documents/GitHub/CSC380/scripts/~/anaconda3/envs/CS380_final/Lib/site-packages/keras/src/utils/traceback_utils.py#line=121), in filter_traceback.<locals>.error_handler(*args, **kwargs)
    119     filtered_tb = _process_traceback_frames(e.__traceback__)
    120     # To get the full stack trace, call:
    121     # `keras.config.disable_traceback_filtering()`
--> 122     raise e.with_traceback(filtered_tb) from None
    123 finally:
    124     del filtered_tb

File [~\anaconda3\envs\CS380_final\Lib\site-packages\keras\src\layers\input_spec.py:156](http://localhost:8888/lab/tree/Documents/GitHub/CSC380/scripts/~/anaconda3/envs/CS380_final/Lib/site-packages/keras/src/layers/input_spec.py#line=155), in assert_input_compatibility(input_spec, inputs, layer_name)
    154 inputs = tree.flatten(inputs)
    155 if len(input_spec) != len(inputs):
--> 156     raise ValueError(
    157         f"Layer '{layer_name}' expected {len(input_spec)} input(s). "
    158         f"Received {len(inputs)} instead."
    159     )
    160 for x in inputs:
    161     # Having a shape/dtype is the only commonality of the various
    162     # tensor-like objects that may be passed. The most common kind of
    163     # invalid type we are guarding for is a Layer instance (Functional API),
    164     # which does not have a `shape` attribute.
    165     if not hasattr(x, "shape"):

ValueError: Layer 'dense' expected 1 input(s). Received 2 instead.