{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"provenance":[],"mount_file_id":"1qg53Uym1zwQuc17Nkotcii-KNsUdRif1","authorship_tag":"ABX9TyNw1xp3OYDjq+c+KjX9CcjR"},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"}},"cells":[{"cell_type":"markdown","source":["
"],"metadata":{"id":"kEjJNenswUwQ"}},{"cell_type":"markdown","source":["# CNN Classification"],"metadata":{"id":"88JR0IcwwNlC"}},{"cell_type":"markdown","source":["### Introduction"],"metadata":{"id":"xK8Huis_yQBG"}},{"cell_type":"markdown","source":["In this project, I developed a deep Convolutional Neural Network (CNN) to classify grapevine leaf images into four categories: Black Rot, Esca, Leaf Blight, and Healthy. The dataset (12,000 images, 3,000 per class) was obtained from Kaggle and enhanced using data augmentation techniques to improve generalization. All images are provided in PNG format. The data was split into 80% training and 20% validation, with a separate test set of 1,805 images.\n","\n","The goal of this model is to support early detection of grapevine diseases using image-based classification. The CNN was implemented using TensorFlow/Keras and trained without transfer learning. To evaluate the performance, I used accuracy, precision, and recall as metrics."],"metadata":{"id":"fAX8RJ1fwMpY"}},{"cell_type":"markdown","source":["!pip install tensorflow\n","from google.colab import drive\n","drive.mount('/content/drive')"],"metadata":{"id":"WBbuffJZeMbC"}},{"cell_type":"markdown","source":["!pip install kaggle\n","from google.colab import files\n","files.upload() # kaggle.json Schlüssel hier hochladen\n","!mkdir ~/.kaggle\n","!cp kaggle.json ~/.kaggle/\n","!chmod 600 ~/.kaggle/kaggle.json\n","!kaggle datasets download -d pushpalama/grape-disease\n","!unzip grape-disease.zip"],"metadata":{"id":"LPaBYfeCg3Xv"}},{"cell_type":"markdown","source":["!mkdir -p ~/.kaggle\n","!cp kaggle.json ~/.kaggle/\n","!chmod 600 ~/.kaggle/kaggle.json\n","\n","# Download\n","!kaggle datasets download -d pushpalama/grape-disease -p /content\n","\n","# ZIP\n","!unzip -q /content/grape-disease.zip -d /content"],"metadata":{"id":"blnKezrkhRNM"}},{"cell_type":"markdown","source":["from google.colab import drive\n","drive.mount('/content/drive')\n","\n","!cp -r \"/content/grape_dataset\" \"/content/drive/MyDrive/\""],"metadata":{"id":"J4K-PoPJoPy4"}},{"cell_type":"code","source":["from google.colab import drive\n","drive.mount('/content/drive')\n","\n","base_path = \"/content/drive/MyDrive/grape_dataset\"\n","train_dir = base_path + \"/train\"\n","test_dir = base_path + \"/test\""],"metadata":{"id":"-K8cGcEU_rzf"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["import os\n","\n","base_path = \"/content/drive/MyDrive/grape_dataset\"\n","train_dir = base_path + \"/train\"\n","test_dir = base_path + \"/test\""],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"KEy_11ntAvQr","executionInfo":{"status":"ok","timestamp":1763591296503,"user_tz":-60,"elapsed":1825,"user":{"displayName":"Enes Yamac","userId":"16727765546892709191"}},"outputId":"d6c1d9b0-97ec-4708-f905-5386d6ade398"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Train sucessfull: True\n","Test sucessfull: True\n","Classes: ['Grape___Black_rot', 'Grape___Esca_(Black_Measles)', 'Grape___Leaf_blight_(Isariopsis_Leaf_Spot)', 'Grape___healthy']\n"]}]},{"cell_type":"code","source":["from tensorflow.keras.preprocessing.image import ImageDataGenerator\n","from tensorflow.keras.models import Sequential\n","from tensorflow.keras.layers import Conv2D, MaxPooling2D, GlobalAveragePooling2D, Flatten, Dense, Dropout, BatchNormalization\n","from tensorflow.keras.callbacks import EarlyStopping, ModelCheckpoint\n","from tensorflow.keras.applications.resnet50 import preprocess_input\n","from tensorflow.keras.models import Model\n","from tensorflow.keras.optimizers import Adam\n","from tensorflow.keras.metrics import Precision, Recall\n","from sklearn.metrics import confusion_matrix, classification_report\n","from tensorflow.keras.applications import ResNet50\n","import numpy as np\n","import matplotlib.pyplot as plt\n","import seaborn as sns"],"metadata":{"id":"KOpTMHBNBDnu","executionInfo":{"status":"ok","timestamp":1763852985198,"user_tz":-60,"elapsed":5735,"user":{"displayName":"Enes Yamac","userId":"16727765546892709191"}}},"execution_count":2,"outputs":[]},{"cell_type":"code","source":["IMG_SIZE = (224, 224)\n","BATCH_SIZE = 32\n","\n","train_datagen = ImageDataGenerator(\n"," rescale=1./255,\n"," rotation_range=25,\n"," width_shift_range=0.1,\n"," height_shift_range=0.1,\n"," zoom_range=0.2,\n"," shear_range=0.2,\n"," brightness_range=[0.8, 1.2],\n"," horizontal_flip=True,\n"," vertical_flip=True,\n"," validation_split=0.2\n",")\n","\n","train_generator = train_datagen.flow_from_directory(\n"," train_dir,\n"," target_size=IMG_SIZE,\n"," batch_size=BATCH_SIZE,\n"," class_mode=\"categorical\",\n"," subset=\"training\"\n",")\n","\n","val_generator = train_datagen.flow_from_directory(\n"," train_dir,\n"," target_size=IMG_SIZE,\n"," batch_size=BATCH_SIZE,\n"," class_mode=\"categorical\",\n"," subset=\"validation\"\n",")"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"GE2kXqe2D40q","executionInfo":{"status":"ok","timestamp":1763591304509,"user_tz":-60,"elapsed":4634,"user":{"displayName":"Enes Yamac","userId":"16727765546892709191"}},"outputId":"5b8e43bd-6734-4e90-833b-1db80d178763"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Found 5779 images belonging to 4 classes.\n","Found 1443 images belonging to 4 classes.\n"]}]},{"cell_type":"code","source":["num_classes = train_generator.num_classes\n","\n","model = Sequential([\n"," Conv2D(32, (3,3), activation='relu', padding='same', input_shape=IMG_SIZE + (3,)),\n"," BatchNormalization(),\n"," MaxPooling2D((2,2)),\n"," Conv2D(64, (3,3), activation='relu', padding='same'),\n"," BatchNormalization(),\n"," MaxPooling2D((2,2)),\n"," Conv2D(128, (3,3), activation='relu', padding='same'),\n"," BatchNormalization(),\n"," Conv2D(128, (3,3), activation='relu', padding='same'),\n"," BatchNormalization(),\n"," MaxPooling2D((2,2)),\n"," Conv2D(256, (3,3), activation='relu', padding='same'),\n"," BatchNormalization(),\n"," Flatten(),\n"," Dense(256, activation='relu'),\n"," Dropout(0.5),\n"," Dense(num_classes, activation='softmax')])\n","\n","model.summary()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":808},"id":"lh4UXv9jFon3","executionInfo":{"status":"ok","timestamp":1763521975989,"user_tz":-60,"elapsed":1959,"user":{"displayName":"Enes Yamac","userId":"16727765546892709191"}},"outputId":"04c44a3d-2b3a-431a-cc40-0f7dd668eb95"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.12/dist-packages/keras/src/layers/convolutional/base_conv.py:113: 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.\n"," super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"]},{"output_type":"display_data","data":{"text/plain":["\u001b[1mModel: \"sequential\"\u001b[0m\n"],"text/html":["
Model: \"sequential\"\n","\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n","┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ conv2d (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m224\u001b[0m, \u001b[38;5;34m224\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m896\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ batch_normalization │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m224\u001b[0m, \u001b[38;5;34m224\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m128\u001b[0m │\n","│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ max_pooling2d (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m112\u001b[0m, \u001b[38;5;34m112\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ conv2d_1 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m112\u001b[0m, \u001b[38;5;34m112\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m18,496\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ batch_normalization_1 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m112\u001b[0m, \u001b[38;5;34m112\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m256\u001b[0m │\n","│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ max_pooling2d_1 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m56\u001b[0m, \u001b[38;5;34m56\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ conv2d_2 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m56\u001b[0m, \u001b[38;5;34m56\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m73,856\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ batch_normalization_2 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m56\u001b[0m, \u001b[38;5;34m56\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m512\u001b[0m │\n","│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ conv2d_3 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m56\u001b[0m, \u001b[38;5;34m56\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m147,584\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ batch_normalization_3 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m56\u001b[0m, \u001b[38;5;34m56\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m512\u001b[0m │\n","│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ max_pooling2d_2 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m28\u001b[0m, \u001b[38;5;34m28\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ conv2d_4 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m28\u001b[0m, \u001b[38;5;34m28\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m295,168\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ batch_normalization_4 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m28\u001b[0m, \u001b[38;5;34m28\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m1,024\u001b[0m │\n","│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ flatten (\u001b[38;5;33mFlatten\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m200704\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m51,380,480\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dropout (\u001b[38;5;33mDropout\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_1 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m) │ \u001b[38;5;34m1,028\u001b[0m │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n"],"text/html":["┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n","┃ Layer (type) ┃ Output Shape ┃ Param # ┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ conv2d (Conv2D) │ (None, 224, 224, 32) │ 896 │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ batch_normalization │ (None, 224, 224, 32) │ 128 │\n","│ (BatchNormalization) │ │ │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ max_pooling2d (MaxPooling2D) │ (None, 112, 112, 32) │ 0 │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ conv2d_1 (Conv2D) │ (None, 112, 112, 64) │ 18,496 │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ batch_normalization_1 │ (None, 112, 112, 64) │ 256 │\n","│ (BatchNormalization) │ │ │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ max_pooling2d_1 (MaxPooling2D) │ (None, 56, 56, 64) │ 0 │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ conv2d_2 (Conv2D) │ (None, 56, 56, 128) │ 73,856 │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ batch_normalization_2 │ (None, 56, 56, 128) │ 512 │\n","│ (BatchNormalization) │ │ │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ conv2d_3 (Conv2D) │ (None, 56, 56, 128) │ 147,584 │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ batch_normalization_3 │ (None, 56, 56, 128) │ 512 │\n","│ (BatchNormalization) │ │ │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ max_pooling2d_2 (MaxPooling2D) │ (None, 28, 28, 128) │ 0 │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ conv2d_4 (Conv2D) │ (None, 28, 28, 256) │ 295,168 │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ batch_normalization_4 │ (None, 28, 28, 256) │ 1,024 │\n","│ (BatchNormalization) │ │ │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ flatten (Flatten) │ (None, 200704) │ 0 │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense (Dense) │ (None, 256) │ 51,380,480 │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dropout (Dropout) │ (None, 256) │ 0 │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_1 (Dense) │ (None, 4) │ 1,028 │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n","\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Total params: \u001b[0m\u001b[38;5;34m51,919,940\u001b[0m (198.06 MB)\n"],"text/html":["
Total params: 51,919,940 (198.06 MB)\n","\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m51,918,724\u001b[0m (198.05 MB)\n"],"text/html":["
Trainable params: 51,918,724 (198.05 MB)\n","\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m1,216\u001b[0m (4.75 KB)\n"],"text/html":["
Non-trainable params: 1,216 (4.75 KB)\n","\n"]},"metadata":{}}]},{"cell_type":"code","source":["model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=1e-4),loss='categorical_crossentropy',metrics=['accuracy',tf.keras.metrics.Precision(name='precision'),tf.keras.metrics.Recall(name='recall')])"],"metadata":{"id":"LRcBG_IvGc3z"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["checkpoint_path = \"/content/drive/MyDrive/best_grape_cnn_optionA.h5\"\n","\n","checkpoint = ModelCheckpoint(checkpoint_path,monitor='val_accuracy',save_best_only=True,mode='max',verbose=1)\n","early_stop = EarlyStopping(monitor='val_loss',patience=5,restore_best_weights=True,verbose=1)"],"metadata":{"id":"GxtuwZH0HbzW"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["history = model.fit(train_generator,validation_data=val_generator,epochs=80,callbacks=[checkpoint, early_stop])"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"GcmEGum2H-KW","executionInfo":{"status":"ok","timestamp":1763524587636,"user_tz":-60,"elapsed":1963250,"user":{"displayName":"Enes Yamac","userId":"16727765546892709191"}},"outputId":"b16e68f9-37f9-4338-ad67-d309fa0d104b"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.12/dist-packages/keras/src/trainers/data_adapters/py_dataset_adapter.py:121: 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.\n"," self._warn_if_super_not_called()\n"]},{"output_type":"stream","name":"stdout","text":["Epoch 1/80\n","\u001b[1m181/181\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 557ms/step - accuracy: 0.7391 - loss: 1.2786 - precision: 0.7473 - recall: 0.7298\n","Epoch 1: val_accuracy improved from -inf to 0.27512, saving model to /content/drive/MyDrive/best_grape_cnn_optionA.h5\n"]},{"output_type":"stream","name":"stderr","text":["WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"]},{"output_type":"stream","name":"stdout","text":["\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r\u001b[1m181/181\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m151s\u001b[0m 749ms/step - accuracy: 0.7394 - loss: 1.2757 - precision: 0.7476 - recall: 0.7301 - val_accuracy: 0.2751 - val_loss: 19.5084 - val_precision: 0.2751 - val_recall: 0.2751\n","Epoch 2/80\n","\u001b[1m181/181\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 532ms/step - accuracy: 0.8419 - loss: 0.4330 - precision: 0.8534 - recall: 0.8279\n","Epoch 2: val_accuracy improved from 0.27512 to 0.34511, saving model to /content/drive/MyDrive/best_grape_cnn_optionA.h5\n"]},{"output_type":"stream","name":"stderr","text":["WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"]},{"output_type":"stream","name":"stdout","text":["\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r\u001b[1m181/181\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m128s\u001b[0m 710ms/step - accuracy: 0.8420 - loss: 0.4327 - precision: 0.8535 - recall: 0.8280 - val_accuracy: 0.3451 - val_loss: 20.0653 - val_precision: 0.3451 - val_recall: 0.3451\n","Epoch 3/80\n","\u001b[1m181/181\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 634ms/step - accuracy: 0.8932 - loss: 0.3124 - precision: 0.9018 - recall: 0.8838\n","Epoch 3: val_accuracy improved from 0.34511 to 0.44144, saving model to /content/drive/MyDrive/best_grape_cnn_optionA.h5\n"]},{"output_type":"stream","name":"stderr","text":["WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"]},{"output_type":"stream","name":"stdout","text":["\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r\u001b[1m181/181\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m143s\u001b[0m 789ms/step - accuracy: 0.8932 - loss: 0.3123 - precision: 0.9018 - recall: 0.8839 - val_accuracy: 0.4414 - val_loss: 9.7117 - val_precision: 0.4411 - val_recall: 0.4387\n","Epoch 4/80\n","\u001b[1m181/181\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 621ms/step - accuracy: 0.9081 - loss: 0.2580 - precision: 0.9149 - recall: 0.8998\n","Epoch 4: val_accuracy improved from 0.44144 to 0.78863, saving model to /content/drive/MyDrive/best_grape_cnn_optionA.h5\n"]},{"output_type":"stream","name":"stderr","text":["WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"]},{"output_type":"stream","name":"stdout","text":["\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r\u001b[1m181/181\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m143s\u001b[0m 793ms/step - accuracy: 0.9081 - loss: 0.2580 - precision: 0.9149 - recall: 0.8998 - val_accuracy: 0.7886 - val_loss: 0.6252 - val_precision: 0.8045 - val_recall: 0.7755\n","Epoch 5/80\n","\u001b[1m181/181\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 619ms/step - accuracy: 0.9335 - loss: 0.2024 - precision: 0.9405 - recall: 0.9287\n","Epoch 5: val_accuracy improved from 0.78863 to 0.96466, saving model to /content/drive/MyDrive/best_grape_cnn_optionA.h5\n"]},{"output_type":"stream","name":"stderr","text":["WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"]},{"output_type":"stream","name":"stdout","text":["\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r\u001b[1m181/181\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m142s\u001b[0m 785ms/step - accuracy: 0.9335 - loss: 0.2025 - precision: 0.9405 - recall: 0.9287 - val_accuracy: 0.9647 - val_loss: 0.1246 - val_precision: 0.9666 - val_recall: 0.9640\n","Epoch 6/80\n","\u001b[1m181/181\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 615ms/step - accuracy: 0.9363 - loss: 0.2017 - precision: 0.9404 - recall: 0.9328\n","Epoch 6: val_accuracy improved from 0.96466 to 0.97089, saving model to /content/drive/MyDrive/best_grape_cnn_optionA.h5\n"]},{"output_type":"stream","name":"stderr","text":["WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"]},{"output_type":"stream","name":"stdout","text":["\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r\u001b[1m181/181\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m145s\u001b[0m 800ms/step - accuracy: 0.9364 - loss: 0.2015 - precision: 0.9405 - recall: 0.9329 - val_accuracy: 0.9709 - val_loss: 0.0816 - val_precision: 0.9716 - val_recall: 0.9709\n","Epoch 7/80\n","\u001b[1m181/181\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 630ms/step - accuracy: 0.9436 - loss: 0.1885 - precision: 0.9463 - recall: 0.9411\n","Epoch 7: val_accuracy did not improve from 0.97089\n","\u001b[1m181/181\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m137s\u001b[0m 756ms/step - accuracy: 0.9436 - loss: 0.1885 - precision: 0.9463 - recall: 0.9411 - val_accuracy: 0.9446 - val_loss: 0.1689 - val_precision: 0.9445 - val_recall: 0.9432\n","Epoch 8/80\n","\u001b[1m181/181\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 525ms/step - accuracy: 0.9513 - loss: 0.1519 - precision: 0.9529 - recall: 0.9487\n","Epoch 8: val_accuracy did not improve from 0.97089\n","\u001b[1m181/181\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m118s\u001b[0m 651ms/step - accuracy: 0.9513 - loss: 0.1520 - precision: 0.9529 - recall: 0.9487 - val_accuracy: 0.9314 - val_loss: 0.2251 - val_precision: 0.9326 - val_recall: 0.9300\n","Epoch 9/80\n","\u001b[1m181/181\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 523ms/step - accuracy: 0.9416 - loss: 0.1721 - precision: 0.9444 - recall: 0.9351\n","Epoch 9: val_accuracy did not improve from 0.97089\n","\u001b[1m181/181\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m118s\u001b[0m 650ms/step - accuracy: 0.9417 - loss: 0.1719 - precision: 0.9445 - recall: 0.9352 - val_accuracy: 0.9529 - val_loss: 0.1631 - val_precision: 0.9542 - val_recall: 0.9522\n","Epoch 10/80\n","\u001b[1m181/181\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 522ms/step - accuracy: 0.9645 - loss: 0.1164 - precision: 0.9671 - recall: 0.9617\n","Epoch 10: val_accuracy improved from 0.97089 to 0.97228, saving model to /content/drive/MyDrive/best_grape_cnn_optionA.h5\n"]},{"output_type":"stream","name":"stderr","text":["WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"]},{"output_type":"stream","name":"stdout","text":["\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r\u001b[1m181/181\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m131s\u001b[0m 727ms/step - accuracy: 0.9645 - loss: 0.1164 - precision: 0.9671 - recall: 0.9617 - val_accuracy: 0.9723 - val_loss: 0.0719 - val_precision: 0.9723 - val_recall: 0.9723\n","Epoch 11/80\n","\u001b[1m181/181\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 623ms/step - accuracy: 0.9632 - loss: 0.1201 - precision: 0.9661 - recall: 0.9618\n","Epoch 11: val_accuracy did not improve from 0.97228\n","\u001b[1m181/181\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m135s\u001b[0m 745ms/step - accuracy: 0.9632 - loss: 0.1201 - precision: 0.9661 - recall: 0.9618 - val_accuracy: 0.9515 - val_loss: 0.1452 - val_precision: 0.9535 - val_recall: 0.9515\n","Epoch 12/80\n","\u001b[1m181/181\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 528ms/step - accuracy: 0.9679 - loss: 0.0994 - precision: 0.9691 - recall: 0.9672\n","Epoch 12: val_accuracy did not improve from 0.97228\n","\u001b[1m181/181\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m118s\u001b[0m 652ms/step - accuracy: 0.9679 - loss: 0.0997 - precision: 0.9691 - recall: 0.9671 - val_accuracy: 0.9653 - val_loss: 0.1226 - val_precision: 0.9673 - val_recall: 0.9640\n","Epoch 13/80\n","\u001b[1m181/181\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 519ms/step - accuracy: 0.9660 - loss: 0.1173 - precision: 0.9693 - recall: 0.9613\n","Epoch 13: val_accuracy did not improve from 0.97228\n","\u001b[1m181/181\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m117s\u001b[0m 647ms/step - accuracy: 0.9660 - loss: 0.1172 - precision: 0.9693 - recall: 0.9613 - val_accuracy: 0.9695 - val_loss: 0.1004 - val_precision: 0.9709 - val_recall: 0.9695\n","Epoch 14/80\n","\u001b[1m181/181\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 519ms/step - accuracy: 0.9654 - loss: 0.1086 - precision: 0.9686 - recall: 0.9636\n","Epoch 14: val_accuracy did not improve from 0.97228\n","\u001b[1m181/181\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m117s\u001b[0m 647ms/step - accuracy: 0.9654 - loss: 0.1087 - precision: 0.9686 - recall: 0.9635 - val_accuracy: 0.9411 - val_loss: 0.3379 - val_precision: 0.9416 - val_recall: 0.9390\n","Epoch 15/80\n","\u001b[1m181/181\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 520ms/step - accuracy: 0.9671 - loss: 0.1023 - precision: 0.9692 - recall: 0.9659\n","Epoch 15: val_accuracy did not improve from 0.97228\n","\u001b[1m181/181\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m117s\u001b[0m 647ms/step - accuracy: 0.9671 - loss: 0.1023 - precision: 0.9692 - recall: 0.9659 - val_accuracy: 0.9674 - val_loss: 0.0943 - val_precision: 0.9681 - val_recall: 0.9667\n","Epoch 15: early stopping\n","Restoring model weights from the end of the best epoch: 10.\n"]}]},{"cell_type":"code","source":["final_train_acc = history['accuracy'][-1]\n","final_val_acc = history['val_accuracy'][-1]\n","final_train_loss = history['loss'][-1]\n","final_val_loss = history['val_loss'][-1]\n","\n","print(f\"🔹 Final Train Accuracy: {final_train_acc:.4f}\")\n","print(f\"🔹 Final Val Accuracy: {final_val_acc:.4f}\")\n","print(f\"🔹 Final Train Loss: {final_train_loss:.4f}\")\n","print(f\"🔹 Final Val Loss: {final_val_loss:.4f}\")"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"fB3CSaBPO8QO","executionInfo":{"status":"ok","timestamp":1763591346350,"user_tz":-60,"elapsed":22,"user":{"displayName":"Enes Yamac","userId":"16727765546892709191"}},"outputId":"f6a8e518-03a4-4cd9-b8f0-f5c2478eb820"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["🔹 Final Train Accuracy: 0.9675\n","🔹 Final Val Accuracy: 0.9674\n","🔹 Final Train Loss: 0.1018\n","🔹 Final Val Loss: 0.0943\n"]}]},{"cell_type":"code","source":["import matplotlib.pyplot as plt\n","\n","# Accuracy Plot\n","plt.plot(history['accuracy'], label='Train Accuracy')\n","plt.plot(history['val_accuracy'], label='Validation Accuracy')\n","plt.title('Accuracy Progress')\n","plt.xlabel('Epochs')\n","plt.ylabel('Accuracy')\n","plt.legend()\n","plt.show()\n","\n","# Loss Plot\n","plt.plot(history['loss'], label='Train Loss')\n","plt.plot(history['val_loss'], label='Validation Loss')\n","plt.title('Loss Progress')\n","plt.xlabel('Epochs')\n","plt.ylabel('Loss')\n","plt.legend()\n","plt.show()\n","\n","plt.plot(history['precision'], label='Train Precision')\n","plt.plot(history['val_precision'], label='Val Precision')\n","plt.legend()\n","plt.show()\n","\n","plt.plot(history['recall'], label='Train Recall')\n","plt.plot(history['val_recall'], label='Val Recall')\n","plt.legend()\n","plt.show()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":1000},"id":"rHGqmnqfRqIT","executionInfo":{"status":"ok","timestamp":1763591353380,"user_tz":-60,"elapsed":643,"user":{"displayName":"Enes Yamac","userId":"16727765546892709191"}},"outputId":"acdf3c74-7944-40c8-c3cb-e6f473a753ab"},"execution_count":null,"outputs":[{"output_type":"display_data","data":{"text/plain":["