Error on custom dataset dimensions feeding transfer model in TensorFLow - tensorflow

Question

Can someone explain this TensorFlow error for me, I'm having trouble understanding what I am doing wrong.
I have a dataset in Tensorflow constructed with a generator. When I test the output of the generator, output dimensions look correct (224 x 224 x 1). But when I try to train the model, I get an error:
WARNING:tensorflow:Model was constructed with shape (None, 224, 224, 1) for input
KerasTensor(type_spec=TensorSpec(shape=(None, 224, 224, 1), dtype=tf.float32,
name='input_2'), name='input_2', description="created by layer 'input_2'"),
but it was called on an input with incompatible shape (224, 224, 1, 1).
I'm unsure why the dimension of this output has an extra 1 at the end.
Here is the code to create the generator and model. df is a dataframe with file-paths to data and labels. The data are 2D matrices of variable dimensions. I'm using cv2.resize to make them 224x224 and then np.reshape to transform dimensions to (224x224x1). Then I yield the result.
def datagen_row():
# ======================== #
# Import data
# ======================== #
df = get_data()
rowsize = 224
colsize = 224
# ======================== #
#
# ======================== #
for row in range(len(df)):
data = get_data_from_filepath(df.iloc[row].file_path)
data = cv2.resize(data, dsize=(rowsize, colsize), interpolation=cv2.INTER_CUBIC)
labels = df.iloc[row].label
data = data.reshape( 224, 224, 1)
yield data, labels
dataset = tf.data.Dataset.from_generator(
datagen_row,
output_signature=(
tf.TensorSpec(shape = (int(os.getenv('rowsize')), int(os.getenv('colsize')), 1), dtype=tf.float32, name=None),
tf.TensorSpec(shape=(), dtype=tf.int64, name=None)
)
)
Testing the following I get what I expected:
iterator = iter(dataset.batch(8))
x = iterator.get_next()
x[0].shape # TensorShape([8, 224, 224, 1])
x[1].shape # TensorShape([8])
x[0] # <tf.Tensor: shape=(8, 224, 224, 1), dtype=float32, numpy=array(...
x[1] # <tf.Tensor: shape=(8,), dtype=int64, numpy=array([1, 1, 1, 1, 1, 1, 1, 1], dtype=int64)>
I'm trying to plug this into InceptionV3 model to do a classification
from tensorflow.keras.applications.inception_v3 import InceptionV3
from tensorflow.keras.layers import Input
from tensorflow.keras import layers
origModel = InceptionV3(weights = 'imagenet', include_top = False)
inputs = layers.Input(shape = (224, 224, 1))
modified_inputs = layers.Conv2D(3, 3, padding = 'same', activation='relu')(inputs)
x = origModel(modified_inputs)
x = layers.GlobalAveragePooling2D()(x)
x = layers.Dense(1024, activation = 'relu')(x)
x = layers.Dense(512, activation = 'relu')(x)
x = layers.Dense(256, activation = 'relu')(x)
x = layers.Dense(128, activation = 'relu')(x)
x = layers.Dense(64, activation = 'relu')(x)
x = layers.Dense(32, activation = 'relu')(x)
outputs = layers.Dense(2)(x)
model = tf.keras.Model(inputs, outputs)
model.summary() # 24.6 M trainable params
for layer in origModel.layers:
layer.trainable = False
model.summary() # now shows 2.8 M trainable params
model.compile(
optimizer = 'adam',
loss = tf.keras.losses.SparseCategoricalCrossentropy(from_logits = True),
metrics = ['accuracy']
)
model.fit(dataset, epochs = 1, verbose = True, batch_size = 32)
Here is the output of model.summary
model.summary()
Model: "model"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_2 (InputLayer) [(None, 224, 224, 1)] 0
conv2d_94 (Conv2D) (None, 224, 224, 3) 30
inception_v3 (Functional) (None, None, None, 2048) 21802784
global_average_pooling2d (G (None, 2048) 0
lobalAveragePooling2D)
dense (Dense) (None, 1024) 2098176
dense_1 (Dense) (None, 512) 524800
dense_2 (Dense) (None, 256) 131328
dense_3 (Dense) (None, 128) 32896
dense_4 (Dense) (None, 64) 8256
dense_5 (Dense) (None, 32) 2080
dense_6 (Dense) (None, 2) 66
=================================================================
Total params: 24,600,416
Trainable params: 2,797,632
Non-trainable params: 21,802,784
_________________________________________________________________

Answer 1

This code worked after changing
model.fit(dataset, epochs = 1, verbose = True, batch_size = 32)
to
model.fit(dataset.batch(2), epochs = 1, verbose = True, batch_size = 32)
So... I will have to look into using dataset.batch versus batch_size in model.fit