{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Keras and Tensor flow Introduction\n"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'2.2.4-tf'"
]
},
"execution_count": 1,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import tensorflow as tf\n",
"from tensorflow import keras\n",
"keras.__version__"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'2.1.0'"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tf.__version__"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"fashion_mnist=keras.datasets.fashion_mnist\n",
"(X_train_full, y_train_full),(X_test,y_test) = fashion_mnist.load_data()\n"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(60000, 28, 28)"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X_train_full.shape\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"dtype('uint8')"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X_train_full.dtype # should be an byte value from 0 to 255\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'Ankle boot'"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',\n",
" 'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']\n",
"class_names[y_train_full[0]] \n",
"\n",
" \n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"#The dataset is randomised so choose first 5000 of training set for validation and remaining 55000 for training\n",
"#and normalize into range 0->1.0 instead of 0->255\n",
"X_valid = X_train_full[:5000]/255.0\n",
"X_train=X_train_full[5000:]/255.0\n",
"#similarly for the y target labels\n",
"y_valid=y_train_full[:5000]\n",
"y_train=y_train_full[5000:]\n"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"model = tf.keras.Sequential([\n",
" tf.keras.layers.Flatten(input_shape=(28, 28)),\n",
" tf.keras.layers.Dense(128, activation='relu'),\n",
" keras.layers.Dense(10, activation='softmax')\n",
"])\n",
"#model = tf.keras.Sequential()\n",
"#model.add(keras.layers.Flatten(input_shape=(28, 28)))\n",
"#model.add(keras.layers.Dense(128, activation='relu'))\n",
"#model.add(keras.layers.Dense(10, activation='softmax'))\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Model: \"sequential\"\n",
"_________________________________________________________________\n",
"Layer (type) Output Shape Param # \n",
"=================================================================\n",
"flatten (Flatten) (None, 784) 0 \n",
"_________________________________________________________________\n",
"dense (Dense) (None, 128) 100480 \n",
"_________________________________________________________________\n",
"dense_1 (Dense) (None, 10) 1290 \n",
"=================================================================\n",
"Total params: 101,770\n",
"Trainable params: 101,770\n",
"Non-trainable params: 0\n",
"_________________________________________________________________\n"
]
}
],
"source": [
"model.summary()"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"model.compile(optimizer=keras.optimizers.SGD(lr=0.001),\n",
" loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),\n",
" metrics=['accuracy'])\n",
"#cross entropy measures how well the estimated class probabilities match the target classes.\n",
"#model.compile(optimizer='adam',\n",
"# loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),\n",
"# metrics=['accuracy'])\n",
"#model.compile(loss='sparse_categorical_crossentropy',optimizer='sgd',metrics=[\"accuracy\"])"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'.\\\\my_newlogs2\\\\run_2020_11_23_11_34_45'"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#Create a function that creates a unique folder for training logs\n",
"import os\n",
"root_logdir = os.path.join(os.curdir,\"my_newlogs2\")\n",
"def get_run_logdir():\n",
" import time\n",
" run_id=time.strftime(\"run_%Y_%m_%d_%H_%M_%S\")\n",
" return os.path.join(root_logdir,run_id)\n",
"run_logdir=get_run_logdir()\n",
"run_logdir\n"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Train on 55000 samples, validate on 5000 samples\n",
"Epoch 1/10\n",
"55000/55000 [==============================] - 3s 63us/sample - loss: 2.2682 - accuracy: 0.2229 - val_loss: 2.2255 - val_accuracy: 0.3670\n",
"Epoch 2/10\n",
"55000/55000 [==============================] - 4s 65us/sample - loss: 2.1684 - accuracy: 0.4271 - val_loss: 2.1004 - val_accuracy: 0.4650\n",
"Epoch 3/10\n",
"55000/55000 [==============================] - 3s 63us/sample - loss: 2.0653 - accuracy: 0.4933 - val_loss: 2.0175 - val_accuracy: 0.5402\n",
"Epoch 4/10\n",
"55000/55000 [==============================] - 3s 56us/sample - loss: 2.0031 - accuracy: 0.5342 - val_loss: 1.9707 - val_accuracy: 0.5502\n",
"Epoch 5/10\n",
"55000/55000 [==============================] - 3s 54us/sample - loss: 1.9513 - accuracy: 0.5979 - val_loss: 1.9205 - val_accuracy: 0.6208\n",
"Epoch 6/10\n",
"55000/55000 [==============================] - 3s 51us/sample - loss: 1.9145 - accuracy: 0.6199 - val_loss: 1.8968 - val_accuracy: 0.6216\n",
"Epoch 7/10\n",
"55000/55000 [==============================] - 3s 55us/sample - loss: 1.8954 - accuracy: 0.6220 - val_loss: 1.8819 - val_accuracy: 0.6238\n",
"Epoch 8/10\n",
"55000/55000 [==============================] - 3s 58us/sample - loss: 1.8830 - accuracy: 0.6235 - val_loss: 1.8719 - val_accuracy: 0.6248\n",
"Epoch 9/10\n",
"55000/55000 [==============================] - 3s 60us/sample - loss: 1.8739 - accuracy: 0.6247 - val_loss: 1.8642 - val_accuracy: 0.6264\n",
"Epoch 10/10\n",
"55000/55000 [==============================] - 3s 59us/sample - loss: 1.8668 - accuracy: 0.6259 - val_loss: 1.8578 - val_accuracy: 0.6272\n"
]
}
],
"source": [
"#create a tensorboard callback function that makes use of folder logger\n",
"tensorboard_cb=keras.callbacks.TensorBoard(run_logdir)\n",
"\n",
"#train model - specify callback to place logs in folder\n",
"\n",
"history=model.fit(X_train,y_train,epochs=10,\n",
" validation_data=(X_valid,y_valid),\n",
" callbacks=[tensorboard_cb])\n"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"#history=model.fit(X_train,y_train,epochs=30,validation_data=(X_valid,y_valid))"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Ankle boot\n",
"Pullover\n",
"Trouser\n",
"Trouser\n",
"Shirt\n"
]
},
{
"data": {
"text/plain": [
"array([[0., 0., 0., 0., 0., 0., 0., 0., 0., 1.],\n",
" [0., 0., 0., 0., 1., 0., 0., 0., 0., 0.],\n",
" [0., 1., 0., 0., 0., 0., 0., 0., 0., 0.],\n",
" [0., 1., 0., 0., 0., 0., 0., 0., 0., 0.],\n",
" [1., 0., 0., 0., 0., 0., 0., 0., 0., 0.],\n",
" [0., 1., 0., 0., 0., 0., 0., 0., 0., 0.]], dtype=float32)"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X_new=X_test[:6]\n",
"y_proba=model.predict(X_new)\n",
"for i in range(5):\n",
" print(class_names[y_test[i]])\n",
"y_proba\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"first image is class 9, second class 2, third is class 1"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Reusing TensorBoard on port 6006 (pid 14068), started 15:25:13 ago. (Use '!kill 14068' to kill it.)"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"\n",
" \n",
" \n",
" "
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"%load_ext tensorboard\n",
"\n",
"#%reload_ext tensorboard\n",
"%tensorboard --logdir=./mynew_logs2 --port=6006"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"The tensorboard extension is already loaded. To reload it, use:\n",
" %reload_ext tensorboard\n"
]
},
{
"data": {
"text/plain": [
"Reusing TensorBoard on port 6006 (pid 14068), started 15:25:13 ago. (Use '!kill 14068' to kill it.)"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"\n",
" \n",
" \n",
" "
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"%load_ext tensorboard\n",
"%tensorboard --logdir=./mynew_logs2 --port=6006"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"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": "3.7.9"
}
},
"nbformat": 4,
"nbformat_minor": 4
}