Untitled

from tensorflow.keras.applications.inception_v3 import InceptionV3, preprocess_input
from tensorflow.keras.preprocessing import image
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Dense, GlobalAveragePooling2D



import ssl

try:
    _create_unverified_https_context = ssl._create_unverified_context
except AttributeError:
    pass
else:
    ssl._create_default_https_context = _create_unverified_https_context

# Load the pre-trained InceptionV3 model without the top (fully connected) layers
base_model = InceptionV3(weights='imagenet', include_top=False)

# Add custom top layers for fine-tuning
x = base_model.output
x = GlobalAveragePooling2D()(x)
x = Dense(1024, activation='relu')(x)
# and a logistic layer — let's say we have 2 classes since we have 2 classes
predictions = Dense(2, activation='softmax')(x) ## Changes made here

# Combine the base model and custom top layers
model = Model(inputs=base_model.input, outputs=predictions)


for layer in base_model.layers:
    layer.trainable = False


model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'],run_eagerly=True)

from tensorflow.keras.preprocessing.image import ImageDataGenerator

train_datagen = ImageDataGenerator(
    rescale=1./255,
    shear_range=0.2,
    zoom_range=0.2,
    horizontal_flip=True
)

test_datagen = ImageDataGenerator(rescale=1./255)

batch_size = 20

# Define paths to your train and validation datasets
train_dataset_path = '/Analytics/venv/Jup/CAPE_Case_Management_PDF_Invoicing/Data/images/Train_dataset_images/'
validation_dataset_path = '/Analytics/venv/Jup/CAPE_Case_Management_PDF_Invoicing/Data/images/Validation_dataset_images/'

import pandas as pd
import os

# Create DataFrames with file paths and labels
train_invoice_df = pd.DataFrame({'filepath': [os.path.join(train_dataset_path, 'invoice', f) for f in os.listdir(os.path.join(train_dataset_path, 'invoice'))],
                                  'label': 'invoice'})

train_non_invoice_df = pd.DataFrame({'filepath': [os.path.join(train_dataset_path, 'non_invoice', f) for f in os.listdir(os.path.join(train_dataset_path, 'non_invoice'))],
                                      'label': 'non_invoice'})

validation_invoice_df = pd.DataFrame({'filepath': [os.path.join(validation_dataset_path, 'invoice', f) for f in os.listdir(os.path.join(validation_dataset_path, 'invoice'))],
                                       'label': 'invoice'})

validation_non_invoice_df = pd.DataFrame({'filepath': [os.path.join(validation_dataset_path, 'non_invoice', f) for f in os.listdir(os.path.join(validation_dataset_path, 'non_invoice'))],
                                           'label': 'non_invoice'})

# Concatenate the dataframes
train_df = pd.concat([train_invoice_df, train_non_invoice_df], ignore_index=True)
validation_df = pd.concat([validation_invoice_df, validation_non_invoice_df], ignore_index=True)

# Shuffle the dataframes
train_df = train_df.sample(frac=1).reset_index(drop=True)
validation_df = validation_df.sample(frac=1).reset_index(drop=True)

# Create data generators
train_generator = train_datagen.flow_from_dataframe(
    train_df,
    x_col='filepath',
    y_col='label',
    target_size=(299, 299),
    batch_size=batch_size,
    class_mode='binary'
)

validation_generator = test_datagen.flow_from_dataframe(
    validation_df,
    x_col='filepath',
    y_col='label',
    target_size=(299, 299),
    batch_size=batch_size,
    class_mode='binary'
)

epochs =8

print("Number of training samples:", len(train_generator))
print("Number of validation samples:", len(validation_generator))

print("Class indices for training:", train_generator.class_indices)
print("Class indices for validation:", validation_generator.class_indices)



model.fit(
    train_generator,
    steps_per_epoch=train_generator.samples // batch_size,
    epochs=epochs,
    validation_data=validation_generator,
    validation_steps=validation_generator.samples // batch_size
)

model.save('Fine_tuned_invoice_model_v2_dec5.h5')


And we have made changes in this line-

predictions = Dense(2, activation='softmax')(x) ## Changes made here

As no of classes we have = 2, but now we are getting error like this-

Epoch 1/8
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
Input In [1], in <cell line: 107>()
    102 print("Class indices for training:", train_generator.class_indices)
    103 print("Class indices for validation:", validation_generator.class_indices)
--> 107 model.fit(
    108     train_generator,
    109     steps_per_epoch=train_generator.samples // batch_size,
    110     epochs=epochs,
    111     validation_data=validation_generator,
    112     validation_steps=validation_generator.samples // batch_size
    113 )
    115 model.save('Fine_tuned_invoice_model_v2_dec5.h5')

File /Analytics/venv/CAPEANALYTICS/lib/python3.8/site-packages/keras/src/utils/traceback_utils.py:70, in filter_traceback.<locals>.error_handler(*args, **kwargs)
     67     filtered_tb = _process_traceback_frames(e.__traceback__)
     68     # To get the full stack trace, call:
     69     # `tf.debugging.disable_traceback_filtering()`
---> 70     raise e.with_traceback(filtered_tb) from None
     71 finally:
     72     del filtered_tb

File /Analytics/venv/CAPEANALYTICS/lib/python3.8/site-packages/keras/src/backend.py:5809, in binary_crossentropy(target, output, from_logits)
   5805 output, from_logits = _get_logits(
   5806     output, from_logits, "Sigmoid", "binary_crossentropy"
   5807 )
   5808 if from_logits:
-> 5809     return tf.nn.sigmoid_cross_entropy_with_logits(
   5810         labels=target, logits=output
   5811     )
   5813 epsilon_ = _constant_to_tensor(epsilon(), output.dtype.base_dtype)
   5814 output = tf.clip_by_value(output, epsilon_, 1.0 - epsilon_)

ValueError: `logits` and `labels` must have the same shape, received ((20, 2) vs (20, 1)).