Why the even epochs are not giving appropriate results in binary classification problem

Question

I wanted to do image classification using CNN and now I am getting abnormal results cause the even no of epochs are not working as expected even if i change the no of epochs

import os
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import tensorflow as tf
import kagglehub

data_dir = kagglehub.dataset_download("ryanholbrook/car-or-truck")


from tensorflow.keras.preprocessing.image import ImageDataGenerator


tf.random.set_seed(42)

train_datagen = ImageDataGenerator(rescale=1./255)
valid_datagen = ImageDataGenerator(rescale=1./255)


train_dir = "/root/.cache/kagglehub/datasets/ryanholbrook/car-or-truck/versions/1/train/"
test_dir = "/root/.cache/kagglehub/datasets/ryanholbrook/car-or-truck/versions/1/valid/"


train_data = train_datagen.flow_from_directory(directory = train_dir, batch_size=32, target_size=(224,224), class_mode="binary", seed=42, shuffle =True)
valid_data = valid_datagen.flow_from_directory(directory = test_dir, batch_size=32, target_size=(224,224), class_mode="binary", seed=42, shuffle =True)

model_1 = tf.keras.models.Sequential([
    tf.keras.layers.Conv2D(filters=10, kernel_size=3, input_shape=(224,224,3), activation="relu"),
    tf.keras.layers.Conv2D(10,3, activation="relu"),
    tf.keras.layers.MaxPool2D(pool_size=2, padding="valid"),
    tf.keras.layers.Conv2D(10,3, activation="relu"),
    tf.keras.layers.Conv2D(10,3, activation="relu"),
    tf.keras.layers.MaxPool2D(pool_size=2, padding="valid"),
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(1, activation="sigmoid")
])

# Compile our CNN
model_1.compile(loss="binary_crossentropy", optimizer=tf.keras.optimizers.Adam(), metrics=["accuracy"])

# Fit the CNN to the data
history_1 = model_1.fit(train_data, epochs=25, steps_per_epoch=len(train_data), validation_data=valid_data, validation_steps=len(valid_data))

Getting this type of result:

Found 5117 images belonging to 2 classes.
Found 5051 images belonging to 2 classes.
Epoch 1/25
/usr/local/lib/python3.10/dist-packages/keras/src/layers/convolutional/base_conv.py:107: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.
  super().__init__(activity_regularizer=activity_regularizer, **kwargs)
/usr/local/lib/python3.10/dist-packages/keras/src/trainers/data_adapters/py_dataset_adapter.py:122: UserWarning: Your `PyDataset` class should call `super().__init__(**kwargs)` in its constructor. `**kwargs` can include `workers`, `use_multiprocessing`, `max_queue_size`. Do not pass these arguments to `fit()`, as they will be ignored.
  self._warn_if_super_not_called()
160/160 ━━━━━━━━━━━━━━━━━━━━ 18s 93ms/step - accuracy: 0.6169 - loss: 0.6532 - val_accuracy: 0.6391 - val_loss: 0.6453

Epoch 2/25
160/160 ━━━━━━━━━━━━━━━━━━━━ 0s 109us/step - accuracy: 0.0000e+00 - loss: 0.0000e+00

Epoch 3/25
/usr/lib/python3.10/contextlib.py:153: UserWarning: Your input ran out of data; interrupting training. Make sure that your dataset or generator can generate at least `steps_per_epoch * epochs` batches. You may need to use the `.repeat()` function when building your dataset.
  self.gen.throw(typ, value, traceback)
160/160 ━━━━━━━━━━━━━━━━━━━━ 17s 80ms/step - accuracy: 0.6780 - loss: 0.5921 - val_accuracy: 0.7020 - val_loss: 0.5711

Epoch 4/25
160/160 ━━━━━━━━━━━━━━━━━━━━ 4s 26ms/step - accuracy: 0.0000e+00 - loss: 0.0000e+00

Epoch 5/25
160/160 ━━━━━━━━━━━━━━━━━━━━ 13s 81ms/step - accuracy: 0.7679 - loss: 0.4824 - val_accuracy: 0.7193 - val_loss: 0.5556

Epoch 6/25
160/160 ━━━━━━━━━━━━━━━━━━━━ 4s 25ms/step - accuracy: 0.0000e+00 - loss: 0.0000e+00

Epoch 7/25
160/160 ━━━━━━━━━━━━━━━━━━━━ 18s 88ms/step - accuracy: 0.8320 - loss: 0.3964 - val_accuracy: 0.7242 - val_loss: 0.5764

Epoch 8/25
160/160 ━━━━━━━━━━━━━━━━━━━━ 4s 25ms/step - accuracy: 0.0000e+00 - loss: 0.0000e+00

Epoch 9/25
160/160 ━━━━━━━━━━━━━━━━━━━━ 15s 78ms/step - accuracy: 0.8764 - loss: 0.3101 - val_accuracy: 0.6995 - val_loss: 0.6768

Epoch 10/25
160/160 ━━━━━━━━━━━━━━━━━━━━ 0s 93us/step - accuracy: 0.0000e+00 - loss: 0.0000e+00

Epoch 11/25
160/160 ━━━━━━━━━━━━━━━━━━━━ 13s 80ms/step - accuracy: 0.9233 - loss: 0.2111 - val_accuracy: 0.7145 - val_loss: 0.7014

Epoch 12/25
160/160 ━━━━━━━━━━━━━━━━━━━━ 0s 97us/step - accuracy: 0.0000e+00 - loss: 0.0000e+00

Epoch 13/25
160/160 ━━━━━━━━━━━━━━━━━━━━ 13s 77ms/step - accuracy: 0.9491 - loss: 0.1485 - val_accuracy: 0.7123 - val_loss: 0.8927

Epoch 14/25
160/160 ━━━━━━━━━━━━━━━━━━━━ 5s 31ms/step - accuracy: 0.0000e+00 - loss: 0.0000e+00

Epoch 15/25
160/160 ━━━━━━━━━━━━━━━━━━━━ 16s 82ms/step - accuracy: 0.9814 - loss: 0.0733 - val_accuracy: 0.7104 - val_loss: 1.1305

Epoch 16/25
160/160 ━━━━━━━━━━━━━━━━━━━━ 0s 71us/step - accuracy: 0.0000e+00 - loss: 0.0000e+00

Epoch 17/25
160/160 ━━━━━━━━━━━━━━━━━━━━ 20s 80ms/step - accuracy: 0.9903 - loss: 0.0431 - val_accuracy: 0.7143 - val_loss: 1.3878

Epoch 18/25
160/160 ━━━━━━━━━━━━━━━━━━━━ 0s 98us/step - accuracy: 0.0000e+00 - loss: 0.0000e+00

Epoch 19/25
160/160 ━━━━━━━━━━━━━━━━━━━━ 20s 80ms/step - accuracy: 0.9915 - loss: 0.0323 - val_accuracy: 0.7165 - val_loss: 1.5466

Epoch 20/25
160/160 ━━━━━━━━━━━━━━━━━━━━ 4s 26ms/step - accuracy: 0.0000e+00 - loss: 0.0000e+00

Epoch 21/25
160/160 ━━━━━━━━━━━━━━━━━━━━ 15s 75ms/step - accuracy: 0.9967 - loss: 0.0177 - val_accuracy: 0.7058 - val_loss: 1.6167

Epoch 22/25
160/160 ━━━━━━━━━━━━━━━━━━━━ 0s 144us/step - accuracy: 0.0000e+00 - loss: 0.0000e+00

Epoch 23/25
160/160 ━━━━━━━━━━━━━━━━━━━━ 21s 79ms/step - accuracy: 0.9939 - loss: 0.0196 - val_accuracy: 0.7111 - val_loss: 1.7555

Epoch 24/25
160/160 ━━━━━━━━━━━━━━━━━━━━ 0s 97us/step - accuracy: 0.0000e+00 - loss: 0.0000e+00

Epoch 25/25
160/160 ━━━━━━━━━━━━━━━━━━━━ 15s 90ms/step - accuracy: 0.9942 - loss: 0.0211 - val_accuracy: 0.7076 - val_loss: 1.9112

You should fix your warnings, especially this one:" Make sure that your dataset or generator can generate at least steps_per_epoch * epochs batches." You have a batch size of 32, 25 epochs and len(train_data) as steps per epoch. That means you are immideatly running out of data. Fix this and see if this helps. Also maybe take a look here stackoverflow.com/questions/38340311/… . — Frede
– Frede, Commented Jan 13 at 12:14

desertnaut · Accepted Answer · 2025-03-10 12:47:40Z

1

The issue is about steps_per_epoch and validation_steps. When I deleted them the problem was solved.

history = model.fit(
    train_generator,
    epochs=32,
    validation_data=val_generator,
    callbacks=callbacks,
    # steps_per_epoch=train_steps,
    # validation_steps=val_steps
)

This is what it looks like. When I did this, I realized that my formula had calculated 272 but the model took it as 273 and that was the problem. I don't know why this is a problem but it worked. The formula was that:

train_steps = train_generator.samples // train_generator.batch_size
val_steps = val_generator.samples // val_generator.batch_size

edited Mar 10 at 12:47

desertnaut

60.8k32 gold badges155 silver badges183 bronze badges

answered Mar 9 at 19:38

Lawliet

111 bronze badge

Sign up to request clarification or add additional context in comments.

Comments

BEANB00ZLED · Accepted Answer · 2025-01-13 13:33:40Z

0

Since the model is actually changing between the odd epochs I it is more likely to be a hyperparameter issue than an architecture issue. I would try adjusting the learning rate and batch size and see if that that helps.

answered Jan 13 at 13:33

BEANB00ZLED

33 bronze badges

1 Comment

Frede Jan 14 at 10:19

With steps_per_epochs=len(train_data) the only batch size that would work is 1. As long as this issue is not fixed there is no reason to believe that the learning rate is a problem.

Collectives™ on Stack Overflow

Why the even epochs are not giving appropriate results in binary classification problem

2 Answers 2

Comments

1 Comment

Your Answer

Linked

Hot Network Questions

Collectives™ on Stack Overflow

2 Answers 2

Comments

1 Comment

Your Answer

Sign up or log in

Post as a guest

Linked

Related