commit 535558f12801d935aa8d3d3e6a4637286ea04852
Author: r0r-5chach <r0r-5chach.xyz@proton.me>
Date:   Sat May 18 16:22:07 2024 +0100

    transfer_learning

diff --git a/brief.pdf b/brief.pdf
new file mode 100644
index 0000000..a420106
Binary files /dev/null and b/brief.pdf differ
diff --git a/crop-classifier-callbacks.keras b/crop-classifier-callbacks.keras
new file mode 100644
index 0000000..55f0b9b
Binary files /dev/null and b/crop-classifier-callbacks.keras differ
diff --git a/main.py b/main.py
new file mode 100644
index 0000000..67cb787
--- /dev/null
+++ b/main.py
@@ -0,0 +1,147 @@
+import numpy as np
+import matplotlib.pyplot as plt
+import tensorflow as tf 
+import os 
+
+
+#Import Data
+PATH = os.path.join(os.getcwd(), "crop-data")
+
+training_data = os.path.join(PATH, "train")
+validation_data = os.path.join(PATH, "valid")
+test_data = os.path.join(PATH, "test")
+
+BATCH_SIZE = 64
+IMG_SIZE = (160,160)
+
+training_data = tf.keras.utils.image_dataset_from_directory(training_data,
+                                                            shuffle=True,
+                                                            batch_size=BATCH_SIZE,
+                                                            image_size=IMG_SIZE)
+validation_data = tf.keras.utils.image_dataset_from_directory(validation_data,
+                                                            shuffle=True,
+                                                            batch_size=BATCH_SIZE,
+                                                            image_size=IMG_SIZE)
+
+test_data = tf.keras.utils.image_dataset_from_directory(test_data,
+                                                            shuffle=True,
+                                                            batch_size=BATCH_SIZE,
+                                                            image_size=IMG_SIZE)
+
+class_names = training_data.class_names
+
+#View Data
+plt.figure(figsize=(10,10))
+for images, labels in training_data.take(1):
+    for i in range(9):
+        ax = plt.subplot(3, 3, i+1)
+        plt.imshow(images[i].numpy().astype("uint8"))
+        plt.title(class_names[labels[i]])
+        plt.axis("off")
+plt.show()
+
+
+#Init Prefetching
+AUTOTUNE = tf.data.AUTOTUNE
+training_data = training_data.prefetch(buffer_size=AUTOTUNE)
+validation_data = validation_data.prefetch(buffer_size=AUTOTUNE)
+test_data = test_data.prefetch(buffer_size=AUTOTUNE)
+
+
+#Data Augmentation
+data_augmentation = tf.keras.Sequential([
+    tf.keras.layers.RandomFlip('horisontal'),
+    tf.keras.layers.RandomRotation(0.2)
+    ])
+
+#Rescale Pixel Values
+preprocess_input = tf.keras.applications.mobilenet_v3.preprocess_input
+
+rescale = tf.keras.layers.Rescaling(1./127.5, offset=-1)
+
+#Create Base Model From MobileNetV3
+IMG_SHAPE = IMG_SIZE + (3,)
+base_model = tf.keras.applications.MobileNetV3Large(
+        input_shape=IMG_SHAPE,
+        include_top=False,
+        weights="imagenet"
+        )
+
+image_batch, label_batch = next(iter(training_data))
+feature_batch = base_model(image_batch)
+
+base_model.trainable = False
+
+
+#View Base Model
+base_model.summary()
+
+#Add Classification Header
+
+
+global_avg_layer = tf.keras.layers.GlobalAveragePooling2D()
+feature_batch_avg = global_avg_layer(feature_batch)
+
+prediction_layer = tf.keras.layers.Dense(38, activation="softmax")
+predication_batch = prediction_layer(feature_batch_avg)
+
+inputs = tf.keras.Input(shape=(160,160,3))
+x = data_augmentation(inputs)
+x = preprocess_input(x)
+x = base_model(x, training=False)
+x = global_avg_layer(x)
+x = tf.keras.layers.Dropout(0.2)(x)
+outputs = prediction_layer(x)
+
+model = tf.keras.Model(inputs, outputs)
+
+#View Model with Classification Head
+model.summary()
+
+
+#Compile the Model
+base_learning_rate = 0.0001
+
+training_data = training_data.map(lambda x,y: (x, tf.one_hot(y,38)))
+validation_data = validation_data.map(lambda x,y: (x, tf.one_hot(y,38)))
+
+
+
+optimizer = tf.keras.optimizers.Adam(learning_rate=base_learning_rate)
+loss = tf.keras.losses.CategoricalCrossentropy()
+metrics = [tf.keras.metrics.CategoricalAccuracy()]
+
+
+phy_dev = tf.config.list_physical_devices("GPU")
+for gpu in phy_dev:
+    tf.config.experimental.set_memory_growth(gpu, True)
+
+model.compile(optimizer=optimizer, loss=loss, metrics=metrics)
+
+#Train the Model
+initial_epochs = 50
+
+loss0, accuracy0 = model.evaluate(validation_data)
+
+print(f"initial loss: {loss0}")
+print(f"initial accuracy: {accuracy0}")
+
+lr_schedule = tf.keras.callbacks.ReduceLROnPlateau(
+        monitor="val_loss",
+        factor=0.1,
+        patience=5,
+        min_lr=1e-6
+        )
+
+earky_stopping = tf.keras.callbacks.EarlyStopping(
+        monitor="val_loss",
+        patience=10,
+        restore_best_weights=True
+        )
+
+history = model.fit(training_data,
+                    epochs=initial_epochs,
+                    validation_data=validation_data,
+                    callbacks=[lr_schedule])
+
+model.save("crop-classifier-callbacks.keras")
diff --git a/report.odt b/report.odt
new file mode 100644
index 0000000..b620efc
Binary files /dev/null and b/report.odt differ