Ajay.paul@stud.hshl.de: Die Seite wurde neu angelegt: „= Convolutional Neural Network for Image Classification = A '''Convolutional Neural Network''' (CNN) is a class of deep neural networks, most commonly applied to analyzing visual imagery. This article describes a specific implementation of a CNN using the TensorFlow and Keras libraries to classify images from the '''CIFAR-10''' dataset. == Overview == The model described herein is designed to classify low-resolution color images ($32 \times 32$…“

2026-02-06T07:29:51Z

Die Seite wurde neu angelegt: „= Convolutional Neural Network for Image Classification = A '''Convolutional Neural Network''' (CNN) is a class of deep neural networks, most commonly applied to analyzing visual imagery. This article describes a specific implementation of a CNN using the TensorFlow and Keras libraries to classify images from the '''CIFAR-10''' dataset. == Overview == The model described herein is designed to classify low-resolution color images ($32 \times 32$…“

Neue Seite

= Convolutional Neural Network for Image Classification =

A '''Convolutional Neural Network''' (CNN) is a class of deep neural networks, most commonly applied to analyzing visual imagery. This article describes a specific implementation of a CNN using the [[TensorFlow]] and [[Keras]] libraries to classify images from the '''CIFAR-10''' dataset.

== Overview ==
The model described herein is designed to classify low-resolution color images ($32 \times 32$ pixels) into one of ten distinct classes (e.g., airplanes, automobiles, birds, cats). The implementation utilizes a sequential architecture consisting of a convolutional base for feature extraction followed by a dense network for classification.

== Dataset ==
The system is trained on the '''CIFAR-10''' dataset, which consists of 60,000 $32 \times 32$ color images in 10 classes, with 6,000 images per class.
* '''Training set:''' 50,000 images
* '''Test set:''' 10,000 images
* '''Preprocessing:''' Pixel values are normalized to the range [0, 1] by dividing by 255.0 to accelerate convergence during gradient descent.

[[File:Dataset_Example.png|thumb|center|Dataset example used for CNN image classification]]

== Network Architecture ==
The architecture follows a sequential pattern: <tt>Conv2D</tt> $\rightarrow$ <tt>MaxPooling</tt> $\rightarrow$ <tt>Dense</tt>. The specific layer configuration and parameter counts are detailed below:

'''Model: "sequential"'''
{| class="wikitable" style="text-align:center; width:60%;"
! style="text-align:left;" | Layer (type) !! Output Shape !! Param #
|-
| style="text-align:left;" | conv2d (Conv2D) || (None, 30, 30, 32) || 896
|-
| style="text-align:left;" | max_pooling2d (MaxPooling2D) || (None, 15, 15, 32) || 0
|-
| style="text-align:left;" | conv2d_1 (Conv2D) || (None, 13, 13, 64) || 18,496
|-
| style="text-align:left;" | max_pooling2d_1 (MaxPooling2D) || (None, 6, 6, 64) || 0
|-
| style="text-align:left;" | conv2d_2 (Conv2D) || (None, 4, 4, 64) || 36,928
|-
| style="text-align:left;" | flatten (Flatten) || (None, 1024) || 0
|-
| style="text-align:left;" | dense (Dense) || (None, 64) || 65,600
|-
| style="text-align:left;" | dense_1 (Dense) || (None, 10) || 650
|-
| style="font-weight:bold; background-color:#eaecf0; text-align:left;" colspan="3" | Total params: 122,570 (478.79 KB)
|-
| style="font-weight:bold; background-color:#eaecf0; text-align:left;" colspan="3" | Trainable params: 122,570 (478.79 KB)
|-
| style="font-weight:bold; background-color:#eaecf0; text-align:left;" colspan="3" | Non-trainable params: 0 (0.00 B)
|}

== Implementation Details ==

=== Training Configuration ===
The model is compiled with the following hyperparameters:
* '''Optimizer:''' Adam (Adaptive Moment Estimation).
* '''Loss Function:''' Sparse Categorical Crossentropy (<tt>from_logits=True</tt>).
* '''Metrics:''' Accuracy.
* '''Epochs:''' 10 iterations over the entire dataset.

=== Performance ===
Upon training for 10 epochs, the model typically achieves:
* '''Training Accuracy:''' High (variable based on initialization).
* '''Test Accuracy:''' Approximately 70% – 75%.
* '''Overfitting:''' A divergence between training accuracy and validation accuracy suggests the model may memorize training data. Techniques such as Dropout or Data Augmentation are recommended to mitigate this.

=== Result ===

{| style="border:none;"
|-
| [[Datei:Calssification.png|mini]]
| [[Datei:Classification new data.png|mini]]
|}

=== Inference on Custom Images ===
To test the model on high-quality external images, the input must be resized to match the network's input constraints ($32 \times 32$ pixels).
<source lang="python">
img = image.load_img(path, target_size=(32, 32))
img_array = image.img_to_array(img) / 255.0
predictions = model.predict(img_array)
</source>

PageName - Versionsgeschichte