Upload butterfly_classification_with_cnn.py

butterfly_classification_with_cnn.py

@@ -0,0 +1,202 @@
+# -*- coding: utf-8 -*-
+"""Butterfly classification with CNN.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/18Jo5pBel2xJCse_nNq61zkDnPN_zzg_u
+
+# Import Libraries and Load Data
+"""
+
+## Remove Warnings ##
+import warnings
+warnings.filterwarnings("ignore")
+
+## Data ##
+import numpy as np
+import pandas as pd
+import os
+
+## Visualization ##
+import matplotlib.pyplot as plt
+import plotly.express as px
+import seaborn as sns
+import plotly.graph_objects as go
+
+## Image ##
+import cv2
+from tensorflow.keras.preprocessing.image import ImageDataGenerator
+
+## Tensorflow ##
+from tensorflow.keras.models import Sequential, Model
+from tensorflow.keras.layers import Input, Dense , Conv2D , Dropout , Flatten , Activation, MaxPooling2D , GlobalAveragePooling2D
+from tensorflow.keras.optimizers import Adam , RMSprop
+from tensorflow.keras.layers import BatchNormalization
+from tensorflow.keras.callbacks import ReduceLROnPlateau , EarlyStopping , ModelCheckpoint , LearningRateScheduler
+from tensorflow.keras.applications import ResNet50V2
+
+df = pd.read_csv('C:/Users/kamel/Documents/Image Classification/butterfly-dataset/butterflies and moths.csv')
+IMAGE_DIR = 'C:/Users/kamel/Documents/Image Classification/butterfly-dataset'
+df['filepaths'] = IMAGE_DIR + '/' + df['filepaths']
+df.head()
+
+train_df = df.loc[df['data set'] == 'train']
+val_df = df.loc[df['data set'] == 'valid']
+test_df = df.loc[df['data set'] == 'test']
+
+"""# Exploratory Data Analysis"""
+
+label_counts = df['labels'].value_counts()[:10]
+
+fig = px.bar(x=label_counts.index,
+             y=label_counts.values,
+             color=label_counts.values,
+             text=label_counts.values,
+             color_continuous_scale='Blues')
+
+fig.update_layout(
+    title_text='Labels Distribution',
+    template='plotly_white',
+    xaxis=dict(
+        title='Label',
+    ),
+    yaxis=dict(
+        title='Count',
+    )
+)
+
+fig.update_traces(marker_line_color='black',
+                  marker_line_width=1.5,
+                  opacity=0.8)
+
+fig.show()
+
+"""# Generate Image using ImageDataGenerator"""
+
+# only train data needs to be augmented
+train_gen = ImageDataGenerator(horizontal_flip=True, vertical_flip=True, rescale=1/255.)
+val_gen = ImageDataGenerator(rescale=1/255.)
+
+train_dir = 'C:/Users/kamel/Documents/Image Classification/butterfly-dataset/train'
+val_dir = 'C:/Users/kamel/Documents/Image Classification/butterfly-dataset/valid'
+
+BATCH_SIZE = 16
+SEED = 56
+IMAGE_SIZE = (244, 244)
+
+train_flow_gen = train_gen.flow_from_directory(directory=train_dir,
+                                              class_mode='sparse',
+                                              batch_size=BATCH_SIZE,
+                                              target_size=IMAGE_SIZE,
+                                              seed=SEED)
+
+val_flow_gen = val_gen.flow_from_directory(directory=val_dir,
+                                            class_mode='sparse',
+                                            batch_size=BATCH_SIZE,
+                                            target_size=IMAGE_SIZE,
+                                            seed=SEED)
+
+"""# Create Model"""
+
+verbose=False
+
+input_tensor = Input(shape=(224, 224, 3))
+
+base_model = ResNet50V2(input_tensor=input_tensor, include_top=False, weights='imagenet')
+
+bm_output = base_model.output
+
+x = GlobalAveragePooling2D()(bm_output)
+x = Dense(1024, activation='relu')(x)
+x = Dropout(rate=0.5)(x)
+output = Dense(100, activation='softmax')(x)
+model = Model(inputs=input_tensor, outputs=output)
+
+if verbose:
+    model.summary()
+
+"""# ResNet Modelling"""
+
+model.compile(optimizer=Adam(lr=0.001), loss='sparse_categorical_crossentropy', metrics=['accuracy'])
+
+rlr_cb = ReduceLROnPlateau(monitor='val_loss', factor=0.2, patience=3, mode='min', verbose=0)
+early_cb = EarlyStopping(monitor='val_loss', patience=5, mode='min', verbose=0)
+
+model.fit(train_flow_gen, epochs=5,
+         steps_per_epoch=int(np.ceil(train_df.shape[0]/BATCH_SIZE)),
+         validation_data=val_flow_gen,
+         validation_steps=int(np.ceil(val_df.shape[0]/BATCH_SIZE)),
+         callbacks=[rlr_cb, early_cb])
+
+test_dir = 'C:/Users/kamel/Documents/Image Classification/butterfly-dataset/test'
+test_gen = ImageDataGenerator(rescale=1/255.)
+test_flow_gen = test_gen.flow_from_directory(directory=test_dir,
+                                             class_mode='sparse',
+                                             batch_size=BATCH_SIZE,
+                                             target_size=IMAGE_SIZE,
+                                             seed=SEED)
+
+print('ResNet Test Data Accuracy: {0}'.format(model.evaluate(test_flow_gen)[1:][0]))
+
+# Save the current weights manually
+model.save('C:/Users/kamel/Documents/Image Classification/model_checkpoint_manual_effnet.h5')
+
+"""# Deployment"""
+
+import gradio as gr
+import tensorflow as tf
+from tensorflow.keras.models import load_model
+import numpy as np
+import cv2
+
+# Load the trained model
+model_path = 'C:/Users/kamel/Documents/Image Classification/model_checkpoint_manual_effnet.h5'
+model = load_model(model_path)
+
+class_names = ['ADONIS', 'AFRICAN GIANT SWALLOWTAIL', 'AMERICAN SNOOT', 'AN 88', 'APPOLLO', 'ARCIGERA FLOWER MOTH', 'ATALA', 'ATLAS MOTH', 'BANDED ORANGE HELICONIAN', 'BANDED PEACOCK']
+
+# Define a function to preprocess the input image
+def preprocess_image(img):
+    # Check if img is a file path or an image object
+    if isinstance(img, str):
+        # Load and preprocess the image
+        img = cv2.imread(img)
+        img = cv2.resize(img, (224, 224))
+        img = img / 255.0  # Normalize pixel values
+        img = np.expand_dims(img, axis=0)  # Add batch dimension
+    elif isinstance(img, np.ndarray):
+        # If img is already an image array, resize it
+        img = cv2.resize(img, (224, 224))
+        img = img / 255.0  # Normalize pixel values
+        img = np.expand_dims(img, axis=0)  # Add batch dimension
+    else:
+        raise ValueError("Unsupported input type. Please provide a file path or a NumPy array.")
+
+    return img
+
+# Define the classification function
+def classify_image(img):
+    # Preprocess the image
+    img = preprocess_image(img)
+
+    # Make predictions
+    predictions = model.predict(img)
+
+    # Get the predicted class label
+    predicted_class = np.argmax(predictions)
+
+    # Get the predicted class name
+    predicted_class_name = class_names[predicted_class]
+
+    return f"Predicted Class: {predicted_class_name}"
+
+# Create a Gradio interface
+iface = gr.Interface(fn=classify_image,
+                     inputs="image",
+                     outputs="text",
+                     live=True)
+
+# Launch the Gradio app
+iface.launch()
+