I'm trying to use Imagenet V2 with transfer-learning for multiclass classification (6 classes), but getting the following error. Can anyone please help?

ValueError: `logits` and `labels` must have the same shape, received ((None, 6) vs (None, 1)).

I borrowed this code from Andrew Ng's CNN course I took a while back but the original code was for binary classification. I tried to modify it for multiclass classification but got this error. Here's my code:

import matplotlib.pyplot as plt
import numpy as np
import os
import tensorflow as tf
import tensorflow.keras.layers as tfl
import datetime

from tensorflow.keras.preprocessing import image_dataset_from_directory
from tensorflow.keras.layers.experimental.preprocessing import RandomFlip, RandomRotation

BATCH_SIZE = 16
IMG_SIZE = (160, 160)
training_directory = "/content/drive/MyDrive/Microscopy Data/04112028_multiclass_maiden/Training/Actin"
validation_directory = "/content/drive/MyDrive/Microscopy Data/04112028_multiclass_maiden/Validation/Actin"
train_dataset = image_dataset_from_directory(training_directory,
                                             shuffle=True,
                                             batch_size=BATCH_SIZE,
                                             image_size=IMG_SIZE,
                                             seed=42)
validation_dataset = image_dataset_from_directory(validation_directory,
                                             shuffle=True,
                                             batch_size=BATCH_SIZE,
                                             image_size=IMG_SIZE,
                                             seed=42)

Output: Found 600 files belonging to 6 classes. Found 600 files belonging to 6 classes. Code Continued...

class_names = train_dataset.class_names

AUTOTUNE = tf.data.experimental.AUTOTUNE
train_dataset = train_dataset.prefetch(buffer_size=AUTOTUNE)

preprocess_input = tf.keras.applications.mobilenet_v2.preprocess_input

IMG_SHAPE = IMG_SIZE   (3,)
base_model = tf.keras.applications.MobileNetV2(input_shape=IMG_SHAPE,
                                               include_top=True,
                                               weights='imagenet')

def huvec_model (image_shape=IMG_SIZE, data_augmentation=data_augmenter()):
    ''' Define a tf.keras model for binary classification out of the MobileNetV2 model
    Arguments:
        image_shape -- Image width and height
        data_augmentation -- data augmentation function
    Returns:
    Returns:
        tf.keras.model
    '''
    
    
    input_shape = image_shape   (3,)
    
    # Freeze the base model by making it non trainable
    # base_model.trainable = None 

    # create the input layer (Same as the imageNetv2 input size)
    # inputs = tf.keras.Input(shape=None) 
    
    # apply data augmentation to the inputs
    # x = None
    
    # data preprocessing using the same weights the model was trained on
    # x = preprocess_input(None) 
    
    # set training to False to avoid keeping track of statistics in the batch norm layer
    # x = base_model(None, training=None) 
    
    # Add the new Binary classification layers
    # use global avg pooling to summarize the info in each channel
    # x = None()(x) 
    #include dropout with probability of 0.2 to avoid overfitting
    # x = None(None)(x)
        
    # create a prediction layer with one neuron (as a classifier only needs one)
    # prediction_layer = None
    
    base_model = tf.keras.applications.MobileNetV2(input_shape=IMG_SHAPE,
                                               include_top=False,
                                               weights='imagenet')
    base_model.trainable = False
    inputs = tf.keras.Input(shape=input_shape)
    x = data_augmentation(inputs)
    x = preprocess_input(x)
    x = base_model(x, training=False)
    x = tf.keras.layers.GlobalAveragePooling2D()(x)
    x = tfl.Dropout(.2)(x)
    prediction_layer = tf.keras.layers.Dense(units = len(class_names), activation='softmax')
    # YOUR CODE ENDS HERE
    
    outputs = prediction_layer(x) 
    model = tf.keras.Model(inputs, outputs)
    
    return model

model2 = huvec_model(IMG_SIZE)

base_model.trainable = True
# Let's take a look to see how many layers are in the base model
print("Number of layers in the base model: ", len(base_model.layers))

# Fine-tune from this layer onwards
fine_tune_at = 120

# Freeze all the layers before the `fine_tune_at` layer
# for layer in base_model.layers[:fine_tune_at]:
#    layer.trainable = None
    
# Define a BinaryCrossentropy loss function. Use from_logits=True
# loss_function=None
# Define an Adam optimizer with a learning rate of 0.1 * base_learning_rate
# optimizer = None
# Use accuracy as evaluation metric
# metrics=None
base_learning_rate = 0.01
# YOUR CODE STARTS HERE
for layer in base_model.layers[:fine_tune_at]:
    layer.trainable = False
loss_function=tf.keras.losses.BinaryCrossentropy(from_logits=True)
optimizer= tf.keras.optimizers.Adam(learning_rate=0.1*base_learning_rate)
metrics=['accuracy']

# YOUR CODE ENDS HERE
model2.compile(loss=loss_function,
              optimizer = optimizer,
              metrics=metrics)

initial_epochs = 5
history = model2.fit(train_dataset, validation_data=validation_dataset, epochs=initial_epochs)

CodePudding user response：

Looks like you yet have to one-hot-encode your labels, i.e. instead of having number i (between 0 and 5, inclusive) for a label of an image that belongs to the i-th class, which is of shape (None, 1), provide an array of all 0's except a 1 at index i, which is of shape (None, 6). Then labels has the same shape as logits.

CodePudding user response：