1788 lines
68 KiB
Plaintext
1788 lines
68 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Zadanie 8 - Alexnet + Dropout & BatchRegularization\n",
|
|
"### Aleksandra Jonas, Aleksandra Gronowska, Iwona Christop"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Przygotowanie danych"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from IPython.display import Image, display"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"id": "2fe63b50",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import sys\n",
|
|
"import subprocess\n",
|
|
"import pkg_resources\n",
|
|
"import numpy as np\n",
|
|
"\n",
|
|
"required = { 'scikit-image'}\n",
|
|
"installed = {pkg.key for pkg in pkg_resources.working_set}\n",
|
|
"missing = required - installed\n",
|
|
"# Alexnet requires images to be of dim = (227, 227, 3)\n",
|
|
"newSize = (227,227)\n",
|
|
"\n",
|
|
"if missing: \n",
|
|
" python = sys.executable\n",
|
|
" subprocess.check_call([python, '-m', 'pip', 'install', *missing], stdout=subprocess.DEVNULL)\n",
|
|
"\n",
|
|
"def load_train_data(input_dir):\n",
|
|
" import numpy as np\n",
|
|
" import pandas as pd\n",
|
|
" import os\n",
|
|
" from skimage.io import imread\n",
|
|
" import cv2 as cv\n",
|
|
" from pathlib import Path\n",
|
|
" import random\n",
|
|
" from shutil import copyfile, rmtree\n",
|
|
" import json\n",
|
|
"\n",
|
|
" import seaborn as sns\n",
|
|
" import matplotlib.pyplot as plt\n",
|
|
"\n",
|
|
" import matplotlib\n",
|
|
" \n",
|
|
" image_dir = Path(input_dir)\n",
|
|
" categories_name = []\n",
|
|
" for file in os.listdir(image_dir):\n",
|
|
" d = os.path.join(image_dir, file)\n",
|
|
" if os.path.isdir(d):\n",
|
|
" categories_name.append(file)\n",
|
|
"\n",
|
|
" folders = [directory for directory in image_dir.iterdir() if directory.is_dir()]\n",
|
|
"\n",
|
|
" train_img = []\n",
|
|
" categories_count=[]\n",
|
|
" labels=[]\n",
|
|
" for i, direc in enumerate(folders):\n",
|
|
" count = 0\n",
|
|
" for obj in direc.iterdir():\n",
|
|
" if os.path.isfile(obj) and os.path.basename(os.path.normpath(obj)) != 'desktop.ini':\n",
|
|
" labels.append(os.path.basename(os.path.normpath(direc)))\n",
|
|
" count += 1\n",
|
|
" img = imread(obj)#zwraca ndarry postaci xSize x ySize x colorDepth\n",
|
|
" img = img[:, :, :3]\n",
|
|
" img = cv.resize(img, newSize, interpolation=cv.INTER_AREA)# zwraca ndarray\n",
|
|
" img = img / 255 #normalizacja\n",
|
|
" train_img.append(img)\n",
|
|
" categories_count.append(count)\n",
|
|
" X={}\n",
|
|
" X[\"values\"] = np.array(train_img)\n",
|
|
" X[\"categories_name\"] = categories_name\n",
|
|
" X[\"categories_count\"] = categories_count\n",
|
|
" X[\"labels\"]=labels\n",
|
|
" return X\n",
|
|
"\n",
|
|
"def load_test_data(input_dir):\n",
|
|
" import numpy as np\n",
|
|
" import pandas as pd\n",
|
|
" import os\n",
|
|
" from skimage.io import imread\n",
|
|
" import cv2 as cv\n",
|
|
" from pathlib import Path\n",
|
|
" import random\n",
|
|
" from shutil import copyfile, rmtree\n",
|
|
" import json\n",
|
|
"\n",
|
|
" import seaborn as sns\n",
|
|
" import matplotlib.pyplot as plt\n",
|
|
"\n",
|
|
" import matplotlib\n",
|
|
"\n",
|
|
" image_path = Path(input_dir)\n",
|
|
"\n",
|
|
" labels_path = image_path.parents[0] / 'test_labels.json'\n",
|
|
"\n",
|
|
" jsonString = labels_path.read_text()\n",
|
|
" objects = json.loads(jsonString)\n",
|
|
"\n",
|
|
" categories_name = []\n",
|
|
" categories_count=[]\n",
|
|
" count = 0\n",
|
|
" c = objects[0]['value']\n",
|
|
" for e in objects:\n",
|
|
" if e['value'] != c:\n",
|
|
" categories_count.append(count)\n",
|
|
" c = e['value']\n",
|
|
" count = 1\n",
|
|
" else:\n",
|
|
" count += 1\n",
|
|
" if not e['value'] in categories_name:\n",
|
|
" categories_name.append(e['value'])\n",
|
|
"\n",
|
|
" categories_count.append(count)\n",
|
|
" \n",
|
|
" test_img = []\n",
|
|
"\n",
|
|
" labels=[]\n",
|
|
" for e in objects:\n",
|
|
" p = image_path / e['filename']\n",
|
|
" img = imread(p)#zwraca ndarry postaci xSize x ySize x colorDepth\n",
|
|
" img = img[:, :, :3]\n",
|
|
" img = cv.resize(img, newSize, interpolation=cv.INTER_AREA)# zwraca ndarray\n",
|
|
" img = img / 255#normalizacja\n",
|
|
" test_img.append(img)\n",
|
|
" labels.append(e['value'])\n",
|
|
"\n",
|
|
" X={}\n",
|
|
" X[\"values\"] = np.array(test_img)\n",
|
|
" X[\"categories_name\"] = categories_name\n",
|
|
" X[\"categories_count\"] = categories_count\n",
|
|
" X[\"labels\"]=labels\n",
|
|
" return X"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"id": "cc941c5a",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Data load\n",
|
|
"data_train = load_train_data(\"./train_test_sw/train_sw\")\n",
|
|
"values_train = data_train['values']\n",
|
|
"labels_train = data_train['labels']\n",
|
|
"\n",
|
|
"data_test = load_test_data(\"./train_test_sw/test_sw\")\n",
|
|
"X_test = data_test['values']\n",
|
|
"y_test = data_test['labels']"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"id": "25040ac9",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from sklearn.model_selection import train_test_split"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"id": "18d44949",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"X_train, X_validate, y_train, y_validate = train_test_split(values_train, labels_train, test_size=0.2, random_state=42)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 6,
|
|
"id": "a1fe47e6",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from sklearn.preprocessing import LabelEncoder\n",
|
|
"class_le = LabelEncoder()\n",
|
|
"y_train_enc = class_le.fit_transform(y_train)\n",
|
|
"y_validate_enc = class_le.fit_transform(y_validate)\n",
|
|
"y_test_enc = class_le.fit_transform(y_test)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 7,
|
|
"id": "d90af799",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"class_le = LabelEncoder()\n",
|
|
"y_train_enc = class_le.fit_transform(y_train)\n",
|
|
"y_validate_enc = class_le.fit_transform(y_validate)\n",
|
|
"y_test_enc = class_le.fit_transform(y_test)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 8,
|
|
"id": "c2323985",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import tensorflow as tf"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 9,
|
|
"id": "dfe674dc",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"train_ds = tf.data.Dataset.from_tensor_slices((X_train, y_train_enc))\n",
|
|
"validation_ds = tf.data.Dataset.from_tensor_slices((X_validate, y_validate_enc))\n",
|
|
"test_ds = tf.data.Dataset.from_tensor_slices((X_test, y_test_enc))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 10,
|
|
"id": "076c8ac9",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Training data size: 820\n",
|
|
"Test data size: 259\n",
|
|
"Validation data size: 206\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"train_ds_size = tf.data.experimental.cardinality(train_ds).numpy()\n",
|
|
"test_ds_size = tf.data.experimental.cardinality(test_ds).numpy()\n",
|
|
"validation_ds_size = tf.data.experimental.cardinality(validation_ds).numpy()\n",
|
|
"print(\"Training data size:\", train_ds_size)\n",
|
|
"print(\"Test data size:\", test_ds_size)\n",
|
|
"print(\"Validation data size:\", validation_ds_size)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 11,
|
|
"id": "07ebcd4a",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"train_ds = (train_ds\n",
|
|
" .shuffle(buffer_size=train_ds_size)\n",
|
|
" .batch(batch_size=32, drop_remainder=True))\n",
|
|
"test_ds = (test_ds\n",
|
|
" .shuffle(buffer_size=train_ds_size)\n",
|
|
" .batch(batch_size=32, drop_remainder=True))\n",
|
|
"validation_ds = (validation_ds\n",
|
|
" .shuffle(buffer_size=train_ds_size)\n",
|
|
" .batch(batch_size=32, drop_remainder=True))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 12,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from tensorflow import keras"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Dropout"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"### Do warstw spłaszczonych"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 13,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"model_flat_drop = keras.models.Sequential([\n",
|
|
" keras.layers.Conv2D(filters=96, kernel_size=(11,11), strides=(4,4), activation='relu', input_shape=(227,227,3)),\n",
|
|
" keras.layers.MaxPool2D(pool_size=(3,3), strides=(2,2)),\n",
|
|
" keras.layers.Conv2D(filters=256, kernel_size=(5,5), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.MaxPool2D(pool_size=(3,3), strides=(2,2)),\n",
|
|
" keras.layers.Conv2D(filters=384, kernel_size=(3,3), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.Conv2D(filters=384, kernel_size=(3,3), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.Conv2D(filters=256, kernel_size=(3,3), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.MaxPool2D(pool_size=(3,3), strides=(2,2)),\n",
|
|
" keras.layers.Flatten(),\n",
|
|
" keras.layers.Dense(4096, activation='relu'),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.Dense(4096, activation='relu'),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.Dense(10, activation='softmax')\n",
|
|
"])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 14,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"WARNING:absl:`lr` is deprecated, please use `learning_rate` instead, or use the legacy optimizer, e.g.,tf.keras.optimizers.legacy.SGD.\n"
|
|
]
|
|
},
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Model: \"sequential\"\n",
|
|
"_________________________________________________________________\n",
|
|
" Layer (type) Output Shape Param # \n",
|
|
"=================================================================\n",
|
|
" conv2d (Conv2D) (None, 55, 55, 96) 34944 \n",
|
|
" \n",
|
|
" max_pooling2d (MaxPooling2D (None, 27, 27, 96) 0 \n",
|
|
" ) \n",
|
|
" \n",
|
|
" conv2d_1 (Conv2D) (None, 27, 27, 256) 614656 \n",
|
|
" \n",
|
|
" max_pooling2d_1 (MaxPooling (None, 13, 13, 256) 0 \n",
|
|
" 2D) \n",
|
|
" \n",
|
|
" conv2d_2 (Conv2D) (None, 13, 13, 384) 885120 \n",
|
|
" \n",
|
|
" conv2d_3 (Conv2D) (None, 13, 13, 384) 1327488 \n",
|
|
" \n",
|
|
" conv2d_4 (Conv2D) (None, 13, 13, 256) 884992 \n",
|
|
" \n",
|
|
" max_pooling2d_2 (MaxPooling (None, 6, 6, 256) 0 \n",
|
|
" 2D) \n",
|
|
" \n",
|
|
" flatten (Flatten) (None, 9216) 0 \n",
|
|
" \n",
|
|
" dense (Dense) (None, 4096) 37752832 \n",
|
|
" \n",
|
|
" dropout (Dropout) (None, 4096) 0 \n",
|
|
" \n",
|
|
" dense_1 (Dense) (None, 4096) 16781312 \n",
|
|
" \n",
|
|
" dropout_1 (Dropout) (None, 4096) 0 \n",
|
|
" \n",
|
|
" dense_2 (Dense) (None, 10) 40970 \n",
|
|
" \n",
|
|
"=================================================================\n",
|
|
"Total params: 58,322,314\n",
|
|
"Trainable params: 58,322,314\n",
|
|
"Non-trainable params: 0\n",
|
|
"_________________________________________________________________\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"model_flat_drop.compile(loss='sparse_categorical_crossentropy', optimizer=tf.optimizers.SGD(lr=.001), metrics=['accuracy'])\n",
|
|
"model_flat_drop.summary()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 15,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"WARNING:tensorflow:`period` argument is deprecated. Please use `save_freq` to specify the frequency in number of batches seen.\n"
|
|
]
|
|
},
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"WARNING:tensorflow:`period` argument is deprecated. Please use `save_freq` to specify the frequency in number of batches seen.\n",
|
|
"/var/folders/6b/j4d60ym516x2s6wymzj707rh0000gn/T/ipykernel_13671/1946638494.py:6: UserWarning: `Model.fit_generator` is deprecated and will be removed in a future version. Please use `Model.fit`, which supports generators.\n",
|
|
" alex1 = model_flat_drop.fit_generator(\n"
|
|
]
|
|
},
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Epoch 1/25\n"
|
|
]
|
|
},
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"2023-01-06 21:33:12.260921: W tensorflow/tsl/platform/profile_utils/cpu_utils.cc:128] Failed to get CPU frequency: 0 Hz\n"
|
|
]
|
|
},
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"25/25 [==============================] - ETA: 0s - loss: 2.2671 - accuracy: 0.1963\n",
|
|
"Epoch 1: val_accuracy improved from -inf to 0.20312, saving model to alex_1.h5\n",
|
|
"25/25 [==============================] - 24s 939ms/step - loss: 2.2671 - accuracy: 0.1963 - val_loss: 2.2120 - val_accuracy: 0.2031\n",
|
|
"Epoch 2/25\n",
|
|
"25/25 [==============================] - ETA: 0s - loss: 2.0757 - accuracy: 0.1875\n",
|
|
"Epoch 2: val_accuracy improved from 0.20312 to 0.28125, saving model to alex_1.h5\n",
|
|
"25/25 [==============================] - 22s 899ms/step - loss: 2.0757 - accuracy: 0.1875 - val_loss: 1.7334 - val_accuracy: 0.2812\n",
|
|
"Epoch 3/25\n",
|
|
"25/25 [==============================] - ETA: 0s - loss: 1.7064 - accuracy: 0.2100\n",
|
|
"Epoch 3: val_accuracy did not improve from 0.28125\n",
|
|
"25/25 [==============================] - 23s 940ms/step - loss: 1.7064 - accuracy: 0.2100 - val_loss: 1.6128 - val_accuracy: 0.2656\n",
|
|
"Epoch 4/25\n",
|
|
"25/25 [==============================] - ETA: 0s - loss: 1.6449 - accuracy: 0.2537\n",
|
|
"Epoch 4: val_accuracy improved from 0.28125 to 0.34896, saving model to alex_1.h5\n",
|
|
"25/25 [==============================] - 23s 918ms/step - loss: 1.6449 - accuracy: 0.2537 - val_loss: 1.5930 - val_accuracy: 0.3490\n",
|
|
"Epoch 5/25\n",
|
|
"25/25 [==============================] - ETA: 0s - loss: 1.6596 - accuracy: 0.2275\n",
|
|
"Epoch 5: val_accuracy did not improve from 0.34896\n",
|
|
"25/25 [==============================] - 23s 928ms/step - loss: 1.6596 - accuracy: 0.2275 - val_loss: 1.5650 - val_accuracy: 0.2865\n",
|
|
"Epoch 6/25\n",
|
|
"25/25 [==============================] - ETA: 0s - loss: 1.6292 - accuracy: 0.2625\n",
|
|
"Epoch 6: val_accuracy did not improve from 0.34896\n",
|
|
"25/25 [==============================] - 23s 935ms/step - loss: 1.6292 - accuracy: 0.2625 - val_loss: 1.5573 - val_accuracy: 0.3021\n",
|
|
"Epoch 7/25\n",
|
|
"25/25 [==============================] - ETA: 0s - loss: 1.6197 - accuracy: 0.2562\n",
|
|
"Epoch 7: val_accuracy did not improve from 0.34896\n",
|
|
"25/25 [==============================] - 23s 929ms/step - loss: 1.6197 - accuracy: 0.2562 - val_loss: 1.5328 - val_accuracy: 0.3125\n",
|
|
"Epoch 8/25\n",
|
|
"25/25 [==============================] - ETA: 0s - loss: 1.5907 - accuracy: 0.2975\n",
|
|
"Epoch 8: val_accuracy improved from 0.34896 to 0.36458, saving model to alex_1.h5\n",
|
|
"25/25 [==============================] - 24s 943ms/step - loss: 1.5907 - accuracy: 0.2975 - val_loss: 1.4958 - val_accuracy: 0.3646\n",
|
|
"Epoch 9/25\n",
|
|
"25/25 [==============================] - ETA: 0s - loss: 1.5715 - accuracy: 0.2962\n",
|
|
"Epoch 9: val_accuracy improved from 0.36458 to 0.40104, saving model to alex_1.h5\n",
|
|
"25/25 [==============================] - 24s 944ms/step - loss: 1.5715 - accuracy: 0.2962 - val_loss: 1.4821 - val_accuracy: 0.4010\n",
|
|
"Epoch 10/25\n",
|
|
"25/25 [==============================] - ETA: 0s - loss: 1.5357 - accuracy: 0.3162\n",
|
|
"Epoch 10: val_accuracy did not improve from 0.40104\n",
|
|
"25/25 [==============================] - 23s 937ms/step - loss: 1.5357 - accuracy: 0.3162 - val_loss: 1.4562 - val_accuracy: 0.3958\n",
|
|
"Epoch 11/25\n",
|
|
"25/25 [==============================] - ETA: 0s - loss: 1.5030 - accuracy: 0.3262\n",
|
|
"Epoch 11: val_accuracy improved from 0.40104 to 0.45833, saving model to alex_1.h5\n",
|
|
"25/25 [==============================] - 24s 970ms/step - loss: 1.5030 - accuracy: 0.3262 - val_loss: 1.4106 - val_accuracy: 0.4583\n",
|
|
"Epoch 12/25\n",
|
|
"25/25 [==============================] - ETA: 0s - loss: 1.4862 - accuracy: 0.3613\n",
|
|
"Epoch 12: val_accuracy improved from 0.45833 to 0.53125, saving model to alex_1.h5\n",
|
|
"25/25 [==============================] - 25s 1s/step - loss: 1.4862 - accuracy: 0.3613 - val_loss: 1.3597 - val_accuracy: 0.5312\n",
|
|
"Epoch 13/25\n",
|
|
"25/25 [==============================] - ETA: 0s - loss: 1.4194 - accuracy: 0.4162\n",
|
|
"Epoch 13: val_accuracy did not improve from 0.53125\n",
|
|
"25/25 [==============================] - 24s 974ms/step - loss: 1.4194 - accuracy: 0.4162 - val_loss: 1.3095 - val_accuracy: 0.4583\n",
|
|
"Epoch 14/25\n",
|
|
"25/25 [==============================] - ETA: 0s - loss: 1.3418 - accuracy: 0.4437\n",
|
|
"Epoch 14: val_accuracy did not improve from 0.53125\n",
|
|
"25/25 [==============================] - 24s 959ms/step - loss: 1.3418 - accuracy: 0.4437 - val_loss: 1.2787 - val_accuracy: 0.4792\n",
|
|
"Epoch 15/25\n",
|
|
"25/25 [==============================] - ETA: 0s - loss: 1.3059 - accuracy: 0.4675\n",
|
|
"Epoch 15: val_accuracy did not improve from 0.53125\n",
|
|
"25/25 [==============================] - 24s 951ms/step - loss: 1.3059 - accuracy: 0.4675 - val_loss: 1.2374 - val_accuracy: 0.4635\n",
|
|
"Epoch 16/25\n",
|
|
"25/25 [==============================] - ETA: 0s - loss: 1.2688 - accuracy: 0.4725\n",
|
|
"Epoch 16: val_accuracy did not improve from 0.53125\n",
|
|
"25/25 [==============================] - 24s 955ms/step - loss: 1.2688 - accuracy: 0.4725 - val_loss: 1.2178 - val_accuracy: 0.4583\n",
|
|
"Epoch 17/25\n",
|
|
"25/25 [==============================] - ETA: 0s - loss: 1.2209 - accuracy: 0.4875\n",
|
|
"Epoch 17: val_accuracy did not improve from 0.53125\n",
|
|
"25/25 [==============================] - 24s 958ms/step - loss: 1.2209 - accuracy: 0.4875 - val_loss: 1.2793 - val_accuracy: 0.3958\n",
|
|
"Epoch 18/25\n",
|
|
"25/25 [==============================] - ETA: 0s - loss: 1.1457 - accuracy: 0.5150\n",
|
|
"Epoch 18: val_accuracy improved from 0.53125 to 0.55729, saving model to alex_1.h5\n",
|
|
"25/25 [==============================] - 24s 980ms/step - loss: 1.1457 - accuracy: 0.5150 - val_loss: 1.0978 - val_accuracy: 0.5573\n",
|
|
"Epoch 19/25\n",
|
|
"25/25 [==============================] - ETA: 0s - loss: 1.1318 - accuracy: 0.5063\n",
|
|
"Epoch 19: val_accuracy did not improve from 0.55729\n",
|
|
"25/25 [==============================] - 27s 1s/step - loss: 1.1318 - accuracy: 0.5063 - val_loss: 1.0764 - val_accuracy: 0.5104\n",
|
|
"Epoch 20/25\n",
|
|
"25/25 [==============================] - ETA: 0s - loss: 1.1289 - accuracy: 0.5125\n",
|
|
"Epoch 20: val_accuracy improved from 0.55729 to 0.56771, saving model to alex_1.h5\n",
|
|
"25/25 [==============================] - 25s 1s/step - loss: 1.1289 - accuracy: 0.5125 - val_loss: 1.0067 - val_accuracy: 0.5677\n",
|
|
"Epoch 21/25\n",
|
|
"25/25 [==============================] - ETA: 0s - loss: 1.0175 - accuracy: 0.5638\n",
|
|
"Epoch 21: val_accuracy did not improve from 0.56771\n",
|
|
"25/25 [==============================] - 26s 1s/step - loss: 1.0175 - accuracy: 0.5638 - val_loss: 1.0095 - val_accuracy: 0.5625\n",
|
|
"Epoch 22/25\n",
|
|
"25/25 [==============================] - ETA: 0s - loss: 1.0559 - accuracy: 0.5288\n",
|
|
"Epoch 22: val_accuracy did not improve from 0.56771\n",
|
|
"25/25 [==============================] - 26s 1s/step - loss: 1.0559 - accuracy: 0.5288 - val_loss: 1.0557 - val_accuracy: 0.5208\n",
|
|
"Epoch 23/25\n",
|
|
"25/25 [==============================] - ETA: 0s - loss: 1.1151 - accuracy: 0.5412\n",
|
|
"Epoch 23: val_accuracy did not improve from 0.56771\n",
|
|
"25/25 [==============================] - 26s 1s/step - loss: 1.1151 - accuracy: 0.5412 - val_loss: 1.0837 - val_accuracy: 0.5052\n",
|
|
"Epoch 24/25\n",
|
|
"25/25 [==============================] - ETA: 0s - loss: 1.0158 - accuracy: 0.5625\n",
|
|
"Epoch 24: val_accuracy improved from 0.56771 to 0.58333, saving model to alex_1.h5\n",
|
|
"25/25 [==============================] - 28s 1s/step - loss: 1.0158 - accuracy: 0.5625 - val_loss: 0.9605 - val_accuracy: 0.5833\n",
|
|
"Epoch 25/25\n",
|
|
" 6/25 [======>.......................] - ETA: 20s - loss: 0.9373 - accuracy: 0.5781"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"from keras.callbacks import ModelCheckpoint, EarlyStopping\n",
|
|
"\n",
|
|
"checkpoint = ModelCheckpoint(\"alex_1.h5\", monitor='val_accuracy', verbose=1, save_best_only=True, save_weights_only=False, mode='auto', period=1)\n",
|
|
"early = EarlyStopping(monitor='val_accuracy', min_delta=0, patience=20, verbose=1, mode='auto')\n",
|
|
"\n",
|
|
"alex1 = model_flat_drop.fit_generator(\n",
|
|
" steps_per_epoch=len(train_ds), \n",
|
|
" generator=train_ds, \n",
|
|
" validation_data= validation_ds, \n",
|
|
" validation_steps=len(validation_ds), \n",
|
|
" epochs=25, \n",
|
|
" callbacks=[checkpoint,early])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"import matplotlib.pyplot as plt\n",
|
|
"plt.plot(alex1.history[\"accuracy\"])\n",
|
|
"plt.plot(alex1.history['val_accuracy'])\n",
|
|
"plt.plot(alex1.history['loss'])\n",
|
|
"plt.plot(alex1.history['val_loss'])\n",
|
|
"plt.title(\"Model accuracy\")\n",
|
|
"plt.ylabel(\"Value\")\n",
|
|
"plt.xlabel(\"Epoch\")\n",
|
|
"plt.legend([\"Accuracy\",\"Validation Accuracy\",\"Loss\",\"Validation Loss\"])\n",
|
|
"plt.show()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"alex1.evaluate(test_ds)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"### Do warstw maxpooling"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"model_pool_drop = keras.models.Sequential([\n",
|
|
" keras.layers.Conv2D(filters=96, kernel_size=(11,11), strides=(4,4), activation='relu', input_shape=(227,227,3)),\n",
|
|
" keras.layers.MaxPool2D(pool_size=(3,3), strides=(2,2)),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.Conv2D(filters=256, kernel_size=(5,5), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.MaxPool2D(pool_size=(3,3), strides=(2,2)),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.Conv2D(filters=384, kernel_size=(3,3), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.Conv2D(filters=384, kernel_size=(3,3), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.Conv2D(filters=256, kernel_size=(3,3), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.MaxPool2D(pool_size=(3,3), strides=(2,2)),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.Flatten(),\n",
|
|
" keras.layers.Dense(4096, activation='relu'),\n",
|
|
" keras.layers.Dense(4096, activation='relu'),\n",
|
|
" keras.layers.Dense(10, activation='softmax')\n",
|
|
"])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"model_pool_drop.compile(loss='sparse_categorical_crossentropy', optimizer=tf.optimizers.SGD(lr=.001), metrics=['accuracy'])\n",
|
|
"model_pool_drop.summary()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"checkpoint = ModelCheckpoint(\"alex_2.h5\", monitor='val_accuracy', verbose=1, save_best_only=True, save_weights_only=False, mode='auto', period=1)\n",
|
|
"early = EarlyStopping(monitor='val_accuracy', min_delta=0, patience=20, verbose=1, mode='auto')\n",
|
|
"\n",
|
|
"alex2 = model_pool_drop.fit_generator(\n",
|
|
" steps_per_epoch=len(train_ds), \n",
|
|
" generator=train_ds, \n",
|
|
" validation_data= validation_ds, \n",
|
|
" validation_steps=len(validation_ds), \n",
|
|
" epochs=25, \n",
|
|
" callbacks=[checkpoint,early])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"plt.plot(alex2.history[\"accuracy\"])\n",
|
|
"plt.plot(alex2.history['val_accuracy'])\n",
|
|
"plt.plot(alex2.history['loss'])\n",
|
|
"plt.plot(alex2.history['val_loss'])\n",
|
|
"plt.title(\"Model accuracy\")\n",
|
|
"plt.ylabel(\"Value\")\n",
|
|
"plt.xlabel(\"Epoch\")\n",
|
|
"plt.legend([\"Accuracy\",\"Validation Accuracy\",\"Loss\",\"Validation Loss\"])\n",
|
|
"plt.show()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"alex2.evaluate(test_ds)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"### Do warstw splotowych"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"model_conv_drop = keras.models.Sequential([\n",
|
|
" keras.layers.Conv2D(filters=96, kernel_size=(11,11), strides=(4,4), activation='relu', input_shape=(227,227,3)),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.MaxPool2D(pool_size=(3,3), strides=(2,2)),\n",
|
|
" keras.layers.Conv2D(filters=256, kernel_size=(5,5), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.MaxPool2D(pool_size=(3,3), strides=(2,2)),\n",
|
|
" keras.layers.Conv2D(filters=384, kernel_size=(3,3), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.Conv2D(filters=384, kernel_size=(3,3), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.Conv2D(filters=256, kernel_size=(3,3), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.MaxPool2D(pool_size=(3,3), strides=(2,2)),\n",
|
|
" keras.layers.Flatten(),\n",
|
|
" keras.layers.Dense(4096, activation='relu'),\n",
|
|
" keras.layers.Dense(4096, activation='relu'),\n",
|
|
" keras.layers.Dense(10, activation='softmax')\n",
|
|
"])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"model_conv_drop.compile(loss='sparse_categorical_crossentropy', optimizer=tf.optimizers.SGD(lr=.001), metrics=['accuracy'])\n",
|
|
"model_conv_drop.summary()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"checkpoint = ModelCheckpoint(\"alex_3.h5\", monitor='val_accuracy', verbose=1, save_best_only=True, save_weights_only=False, mode='auto', period=1)\n",
|
|
"early = EarlyStopping(monitor='val_accuracy', min_delta=0, patience=20, verbose=1, mode='auto')\n",
|
|
"\n",
|
|
"alex3 = model_conv_drop.fit_generator(\n",
|
|
" steps_per_epoch=len(train_ds), \n",
|
|
" generator=train_ds, \n",
|
|
" validation_data= validation_ds, \n",
|
|
" validation_steps=len(validation_ds), \n",
|
|
" epochs=25, \n",
|
|
" callbacks=[checkpoint,early])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"plt.plot(alex3.history[\"accuracy\"])\n",
|
|
"plt.plot(alex3.history['val_accuracy'])\n",
|
|
"plt.plot(alex3.history['loss'])\n",
|
|
"plt.plot(alex3.history['val_loss'])\n",
|
|
"plt.title(\"Model accuracy\")\n",
|
|
"plt.ylabel(\"Value\")\n",
|
|
"plt.xlabel(\"Epoch\")\n",
|
|
"plt.legend([\"Accuracy\",\"Validation Accuracy\",\"Loss\",\"Validation Loss\"])\n",
|
|
"plt.show()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"alex3.evaluate(test_ds)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"### Do warstw spłaszczonych i maxpooling"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"model_flat_pool_drop = keras.models.Sequential([\n",
|
|
" keras.layers.Conv2D(filters=96, kernel_size=(11,11), strides=(4,4), activation='relu', input_shape=(227,227,3)),\n",
|
|
" keras.layers.MaxPool2D(pool_size=(3,3), strides=(2,2)),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.Conv2D(filters=256, kernel_size=(5,5), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.MaxPool2D(pool_size=(3,3), strides=(2,2)),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.Conv2D(filters=384, kernel_size=(3,3), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.Conv2D(filters=384, kernel_size=(3,3), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.Conv2D(filters=256, kernel_size=(3,3), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.MaxPool2D(pool_size=(3,3), strides=(2,2)),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.Flatten(),\n",
|
|
" keras.layers.Dense(4096, activation='relu'),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.Dense(4096, activation='relu'),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.Dense(10, activation='softmax')\n",
|
|
"])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"model_flat_pool_drop.compile(loss='sparse_categorical_crossentropy', optimizer=tf.optimizers.SGD(lr=.001), metrics=['accuracy'])\n",
|
|
"model_flat_pool_drop.summary()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"checkpoint = ModelCheckpoint(\"alex_4.h5\", monitor='val_accuracy', verbose=1, save_best_only=True, save_weights_only=False, mode='auto', period=1)\n",
|
|
"early = EarlyStopping(monitor='val_accuracy', min_delta=0, patience=20, verbose=1, mode='auto')\n",
|
|
"\n",
|
|
"alex4 = model_flat_pool_drop.fit_generator(\n",
|
|
" steps_per_epoch=len(train_ds), \n",
|
|
" generator=train_ds, \n",
|
|
" validation_data= validation_ds, \n",
|
|
" validation_steps=len(validation_ds), \n",
|
|
" epochs=25, \n",
|
|
" callbacks=[checkpoint,early])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"plt.plot(alex4.history[\"accuracy\"])\n",
|
|
"plt.plot(alex4.history['val_accuracy'])\n",
|
|
"plt.plot(alex4.history['loss'])\n",
|
|
"plt.plot(alex4.history['val_loss'])\n",
|
|
"plt.title(\"Model accuracy\")\n",
|
|
"plt.ylabel(\"Value\")\n",
|
|
"plt.xlabel(\"Epoch\")\n",
|
|
"plt.legend([\"Accuracy\",\"Validation Accuracy\",\"Loss\",\"Validation Loss\"])\n",
|
|
"plt.show()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"alex4.evaluate(test_ds)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"### Do warstw spłaszczonych i splotowych"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"model_flat_conv_drop = keras.models.Sequential([\n",
|
|
" keras.layers.Conv2D(filters=96, kernel_size=(11,11), strides=(4,4), activation='relu', input_shape=(227,227,3)),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.MaxPool2D(pool_size=(3,3), strides=(2,2)),\n",
|
|
" keras.layers.Conv2D(filters=256, kernel_size=(5,5), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.MaxPool2D(pool_size=(3,3), strides=(2,2)),\n",
|
|
" keras.layers.Conv2D(filters=384, kernel_size=(3,3), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.Conv2D(filters=384, kernel_size=(3,3), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.Conv2D(filters=256, kernel_size=(3,3), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.MaxPool2D(pool_size=(3,3), strides=(2,2)),\n",
|
|
" keras.layers.Flatten(),\n",
|
|
" keras.layers.Dense(4096, activation='relu'),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.Dense(4096, activation='relu'),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.Dense(10, activation='softmax')\n",
|
|
"])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"model_flat_conv_drop.compile(loss='sparse_categorical_crossentropy', optimizer=tf.optimizers.SGD(lr=.001), metrics=['accuracy'])\n",
|
|
"model_flat_conv_drop.summary()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"checkpoint = ModelCheckpoint(\"alex_5.h5\", monitor='val_accuracy', verbose=1, save_best_only=True, save_weights_only=False, mode='auto', period=1)\n",
|
|
"early = EarlyStopping(monitor='val_accuracy', min_delta=0, patience=20, verbose=1, mode='auto')\n",
|
|
"\n",
|
|
"alex5 = model_flat_conv_drop.fit_generator(\n",
|
|
" steps_per_epoch=len(train_ds), \n",
|
|
" generator=train_ds, \n",
|
|
" validation_data= validation_ds, \n",
|
|
" validation_steps=len(validation_ds), \n",
|
|
" epochs=25, \n",
|
|
" callbacks=[checkpoint,early])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"plt.plot(alex5.history[\"accuracy\"])\n",
|
|
"plt.plot(alex5.history['val_accuracy'])\n",
|
|
"plt.plot(alex5.history['loss'])\n",
|
|
"plt.plot(alex5.history['val_loss'])\n",
|
|
"plt.title(\"Model accuracy\")\n",
|
|
"plt.ylabel(\"Value\")\n",
|
|
"plt.xlabel(\"Epoch\")\n",
|
|
"plt.legend([\"Accuracy\",\"Validation Accuracy\",\"Loss\",\"Validation Loss\"])\n",
|
|
"plt.show()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"alex5.evaluate(test_ds)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"### Do warstw maxpooling i splotowych"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"model_pool_conv_drop = keras.models.Sequential([\n",
|
|
" keras.layers.Conv2D(filters=96, kernel_size=(11,11), strides=(4,4), activation='relu', input_shape=(227,227,3)),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.MaxPool2D(pool_size=(3,3), strides=(2,2)),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.Conv2D(filters=256, kernel_size=(5,5), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.MaxPool2D(pool_size=(3,3), strides=(2,2)),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.Conv2D(filters=384, kernel_size=(3,3), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.Conv2D(filters=384, kernel_size=(3,3), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.Conv2D(filters=256, kernel_size=(3,3), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.MaxPool2D(pool_size=(3,3), strides=(2,2)),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.Flatten(),\n",
|
|
" keras.layers.Dense(4096, activation='relu'),\n",
|
|
" keras.layers.Dense(4096, activation='relu'),\n",
|
|
" keras.layers.Dense(10, activation='softmax')\n",
|
|
"])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"model_pool_conv_drop.compile(loss='sparse_categorical_crossentropy', optimizer=tf.optimizers.SGD(lr=.001), metrics=['accuracy'])\n",
|
|
"model_pool_conv_drop.summary()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"checkpoint = ModelCheckpoint(\"alex_6.h5\", monitor='val_accuracy', verbose=1, save_best_only=True, save_weights_only=False, mode='auto', period=1)\n",
|
|
"early = EarlyStopping(monitor='val_accuracy', min_delta=0, patience=20, verbose=1, mode='auto')\n",
|
|
"\n",
|
|
"alex6 = model_pool_conv_drop.fit_generator(\n",
|
|
" steps_per_epoch=len(train_ds), \n",
|
|
" generator=train_ds, \n",
|
|
" validation_data= validation_ds, \n",
|
|
" validation_steps=len(validation_ds), \n",
|
|
" epochs=25, \n",
|
|
" callbacks=[checkpoint,early])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"plt.plot(alex6.history[\"accuracy\"])\n",
|
|
"plt.plot(alex6.history['val_accuracy'])\n",
|
|
"plt.plot(alex6.history['loss'])\n",
|
|
"plt.plot(alex6.history['val_loss'])\n",
|
|
"plt.title(\"Model accuracy\")\n",
|
|
"plt.ylabel(\"Value\")\n",
|
|
"plt.xlabel(\"Epoch\")\n",
|
|
"plt.legend([\"Accuracy\",\"Validation Accuracy\",\"Loss\",\"Validation Loss\"])\n",
|
|
"plt.show()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"alex6.evaluate(test_ds)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"### Do warstw spłaszczonych, maxpooling i splotowych"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"model_drop = keras.models.Sequential([\n",
|
|
" keras.layers.Conv2D(filters=96, kernel_size=(11,11), strides=(4,4), activation='relu', input_shape=(227,227,3)),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.MaxPool2D(pool_size=(3,3), strides=(2,2)),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.Conv2D(filters=256, kernel_size=(5,5), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.MaxPool2D(pool_size=(3,3), strides=(2,2)),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.Conv2D(filters=384, kernel_size=(3,3), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.Conv2D(filters=384, kernel_size=(3,3), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.Conv2D(filters=256, kernel_size=(3,3), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.MaxPool2D(pool_size=(3,3), strides=(2,2)),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.Flatten(),\n",
|
|
" keras.layers.Dense(4096, activation='relu'),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.Dense(4096, activation='relu'),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.Dense(10, activation='softmax')\n",
|
|
"])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"model_drop.compile(loss='sparse_categorical_crossentropy', optimizer=tf.optimizers.SGD(lr=.001), metrics=['accuracy'])\n",
|
|
"model_drop.summary()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"checkpoint = ModelCheckpoint(\"alex_7.h5\", monitor='val_accuracy', verbose=1, save_best_only=True, save_weights_only=False, mode='auto', period=1)\n",
|
|
"early = EarlyStopping(monitor='val_accuracy', min_delta=0, patience=20, verbose=1, mode='auto')\n",
|
|
"\n",
|
|
"alex7 = model_drop.fit_generator(\n",
|
|
" steps_per_epoch=len(train_ds), \n",
|
|
" generator=train_ds, \n",
|
|
" validation_data= validation_ds, \n",
|
|
" validation_steps=len(validation_ds), \n",
|
|
" epochs=25, \n",
|
|
" callbacks=[checkpoint,early])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"plt.plot(alex7.history[\"accuracy\"])\n",
|
|
"plt.plot(alex7.history['val_accuracy'])\n",
|
|
"plt.plot(alex7.history['loss'])\n",
|
|
"plt.plot(alex7.history['val_loss'])\n",
|
|
"plt.title(\"Model accuracy\")\n",
|
|
"plt.ylabel(\"Value\")\n",
|
|
"plt.xlabel(\"Epoch\")\n",
|
|
"plt.legend([\"Accuracy\",\"Validation Accuracy\",\"Loss\",\"Validation Loss\"])\n",
|
|
"plt.show()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"alex7.evaluate(test_ds)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Batch Regularization"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"### Bez dropoutu"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"model_batch = keras.models.Sequential([\n",
|
|
" keras.layers.Conv2D(filters=96, kernel_size=(11,11), strides=(4,4), activation='relu', input_shape=(227,227,3)),\n",
|
|
" keras.layers.BatchNormalization(),\n",
|
|
" keras.layers.MaxPool2D(pool_size=(3,3), strides=(2,2)),\n",
|
|
" keras.layers.Conv2D(filters=256, kernel_size=(5,5), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.BatchNormalization(),\n",
|
|
" keras.layers.MaxPool2D(pool_size=(3,3), strides=(2,2)),\n",
|
|
" keras.layers.Conv2D(filters=384, kernel_size=(3,3), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.BatchNormalization(),\n",
|
|
" keras.layers.Conv2D(filters=384, kernel_size=(3,3), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.BatchNormalization(),\n",
|
|
" keras.layers.Conv2D(filters=256, kernel_size=(3,3), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.BatchNormalization(),\n",
|
|
" keras.layers.MaxPool2D(pool_size=(3,3), strides=(2,2)),\n",
|
|
" keras.layers.Flatten(),\n",
|
|
" keras.layers.Dense(4096, activation='relu'),\n",
|
|
" keras.layers.Dense(4096, activation='relu'),\n",
|
|
" keras.layers.Dense(10, activation='softmax')\n",
|
|
"])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"model_batch.compile(loss='sparse_categorical_crossentropy', optimizer=tf.optimizers.SGD(lr=.001), metrics=['accuracy'])\n",
|
|
"model_batch.summary()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"checkpoint = ModelCheckpoint(\"alex_8.h5\", monitor='val_accuracy', verbose=1, save_best_only=True, save_weights_only=False, mode='auto', period=1)\n",
|
|
"early = EarlyStopping(monitor='val_accuracy', min_delta=0, patience=20, verbose=1, mode='auto')\n",
|
|
"\n",
|
|
"alex8 = model_batch.fit_generator(\n",
|
|
" steps_per_epoch=len(train_ds), \n",
|
|
" generator=train_ds, \n",
|
|
" validation_data= validation_ds, \n",
|
|
" validation_steps=len(validation_ds), \n",
|
|
" epochs=25, \n",
|
|
" callbacks=[checkpoint,early])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"plt.plot(alex8.history[\"accuracy\"])\n",
|
|
"plt.plot(alex8.history['val_accuracy'])\n",
|
|
"plt.plot(alex8.history['loss'])\n",
|
|
"plt.plot(alex8.history['val_loss'])\n",
|
|
"plt.title(\"Model accuracy\")\n",
|
|
"plt.ylabel(\"Value\")\n",
|
|
"plt.xlabel(\"Epoch\")\n",
|
|
"plt.legend([\"Accuracy\",\"Validation Accuracy\",\"Loss\",\"Validation Loss\"])\n",
|
|
"plt.show()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"alex8.evaluate(test_ds)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"### Z dropoutem"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"model_batch_drop = keras.models.Sequential([\n",
|
|
" keras.layers.Conv2D(filters=96, kernel_size=(11,11), strides=(4,4), activation='relu', input_shape=(227,227,3)),\n",
|
|
" keras.layers.BatchNormalization(),\n",
|
|
" keras.layers.MaxPool2D(pool_size=(3,3), strides=(2,2)),\n",
|
|
" keras.layers.Conv2D(filters=256, kernel_size=(5,5), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.BatchNormalization(),\n",
|
|
" keras.layers.MaxPool2D(pool_size=(3,3), strides=(2,2)),\n",
|
|
" keras.layers.Conv2D(filters=384, kernel_size=(3,3), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.BatchNormalization(),\n",
|
|
" keras.layers.Conv2D(filters=384, kernel_size=(3,3), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.BatchNormalization(),\n",
|
|
" keras.layers.Conv2D(filters=256, kernel_size=(3,3), strides=(1,1), activation='relu', padding=\"same\"),\n",
|
|
" keras.layers.BatchNormalization(),\n",
|
|
" keras.layers.MaxPool2D(pool_size=(3,3), strides=(2,2)),\n",
|
|
" keras.layers.Flatten(),\n",
|
|
" keras.layers.Dense(4096, activation='relu'),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.Dense(4096, activation='relu'),\n",
|
|
" keras.layers.Dropout(.5),\n",
|
|
" keras.layers.Dense(10, activation='softmax')\n",
|
|
"])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"model_batch_drop.compile(loss='sparse_categorical_crossentropy', optimizer=tf.optimizers.SGD(lr=.001), metrics=['accuracy'])\n",
|
|
"model_batch_drop.summary()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"checkpoint = ModelCheckpoint(\"alex_9.h5\", monitor='val_accuracy', verbose=1, save_best_only=True, save_weights_only=False, mode='auto', period=1)\n",
|
|
"early = EarlyStopping(monitor='val_accuracy', min_delta=0, patience=20, verbose=1, mode='auto')\n",
|
|
"\n",
|
|
"alex9 = model_batch_drop.fit_generator(\n",
|
|
" steps_per_epoch=len(train_ds), \n",
|
|
" generator=train_ds, \n",
|
|
" validation_data= validation_ds, \n",
|
|
" validation_steps=len(validation_ds), \n",
|
|
" epochs=25, \n",
|
|
" callbacks=[checkpoint,early])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"plt.plot(alex9.history[\"accuracy\"])\n",
|
|
"plt.plot(alex9.history['val_accuracy'])\n",
|
|
"plt.plot(alex9.history['loss'])\n",
|
|
"plt.plot(alex9.history['val_loss'])\n",
|
|
"plt.title(\"Model accuracy\")\n",
|
|
"plt.ylabel(\"Value\")\n",
|
|
"plt.xlabel(\"Epoch\")\n",
|
|
"plt.legend([\"Accuracy\",\"Validation Accuracy\",\"Loss\",\"Validation Loss\"])\n",
|
|
"plt.show()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31mRunning cells with '/Users/jonas/.pyenv/versions/3.9.6/bin/python' requires ipykernel package.\n",
|
|
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
|
|
"\u001b[1;31mCommand: '/Users/jonas/.pyenv/versions/3.9.6/bin/python -m pip install ipykernel -U --force-reinstall'"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"alex9.evaluate(test_ds)"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "Python 3",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.9.6"
|
|
},
|
|
"orig_nbformat": 4,
|
|
"vscode": {
|
|
"interpreter": {
|
|
"hash": "31f2aee4e71d21fbe5cf8b01ff0e069b9275f58929596ceb00d14d90e3e16cd6"
|
|
}
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 2
|
|
}
|