241 lines
6.8 KiB
Plaintext
241 lines
6.8 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "13fa2f64",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# In this example, we used the TensorFlow library to load the MNIST data,\n",
|
|
"# define an MLP model with three dense layers, compile the model, train it\n",
|
|
"# for 10 epochs, evaluate it on the test set, and make predictions on\n",
|
|
"# the test set. Finally, we plot some examples of the predictions made\n",
|
|
"# by the model."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "1c4405f8",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import tensorflow as tf\n",
|
|
"from tensorflow import keras\n",
|
|
"import numpy as np\n",
|
|
"import matplotlib.pyplot as plt\n",
|
|
"(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "1e7e58fb",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Normalize the pixel values to be between 0 and 1\n",
|
|
"x_train = x_train / 255\n",
|
|
"x_test = x_test / 255"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "3d8a7370",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Flatten the 2D images into 1D arrays\n",
|
|
"x_train = x_train.reshape(x_train.shape[0], -1)\n",
|
|
"x_test = x_test.reshape(x_test.shape[0], -1)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "c2df0f54",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Convert the labels into one-hot encoded arrays\n",
|
|
"y_train = tf.keras.utils.to_categorical(y_train, num_classes=10)\n",
|
|
"y_test = tf.keras.utils.to_categorical(y_test, num_classes=10)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "e2b249ea",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Define the model\n",
|
|
"# The number of parameters depends on the shapes and sizes of the layers.\n",
|
|
"# In the given model, the first layer Dense(512, activation='relu',\n",
|
|
"# input_shape=(784,)) has 784 input nodes and 512 output nodes. Therefore,\n",
|
|
"# the number of parameters in this layer would be (784 * 512) + 512 = 401920,\n",
|
|
"# where the +512 term is for the bias terms.\n",
|
|
"# The second layer also has 512 input nodes and 512 output nodes, which makes\n",
|
|
"# 512512 = 262,144 parameters. The third and last layer has 512 input nodes\n",
|
|
"# and 10 output nodes, which makes 512*10 = 5,120 parameters.\n",
|
|
"model = tf.keras.models.Sequential()\n",
|
|
"model.add(tf.keras.layers.Dense(512, activation='relu', input_shape=(784,)))\n",
|
|
"model.add(tf.keras.layers.Dense(512, activation='relu'))\n",
|
|
"model.add(tf.keras.layers.Dense(10, activation='softmax'))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "bab8730a",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# over come overfitting by regularization\n",
|
|
"#model = tf.keras.models.Sequential([\n",
|
|
"# tf.keras.layers.Dense(64, activation='relu', kernel_regularizer=tf.keras.regularizers.l2(0.001),input_shape=(784,)),\n",
|
|
"# tf.keras.layers.Dense(64, activation='relu', kernel_regularizer=tf.keras.regularizers.l2(0.001)),\n",
|
|
"# tf.keras.layers.Dense(10, activation='softmax')\n",
|
|
"#])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "e3223c61",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Compile the model\n",
|
|
"model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "51e7758f",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Train the model and record the history\n",
|
|
"history = model.fit(x_train, y_train, epochs=10, batch_size=64, validation_data=(x_test, y_test))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "e3240069",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Get the weights of the Dense layer\n",
|
|
"# plot the weights as a heatmap or image, where the weights are represented\n",
|
|
"# as pixel values.\n",
|
|
"# model.layers[2].get_weights()[0] returns only the weights of the third\n",
|
|
"# layer. If you wanted to get the biases, you would use\n",
|
|
"# model.layers[2].get_weights()[1].\n",
|
|
"dense_weights = model.layers[2].get_weights()[0]\n",
|
|
"\n",
|
|
"# Plot the weights as a heatmap\n",
|
|
"plt.imshow(dense_weights, cmap='coolwarm')\n",
|
|
"plt.colorbar()\n",
|
|
"plt.title('weights in the output layer')\n",
|
|
"plt.show()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "13118686",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Evaluate the model on the test set\n",
|
|
"test_loss, test_acc = model.evaluate(x_test, y_test)\n",
|
|
"print('Test accuracy:', test_acc)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "40f35fe5",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Plot loss and accuracy\n",
|
|
"plt.figure(figsize=(12, 4))\n",
|
|
"\n",
|
|
"# Plot the loss and accuracy for training and validation data\n",
|
|
"plt.subplot(1, 2, 1)\n",
|
|
"plt.plot(history.history['loss'], label='training loss')\n",
|
|
"plt.plot(history.history['val_loss'], label='validation loss')\n",
|
|
"plt.xlabel('Epoch')\n",
|
|
"plt.ylabel('Loss')\n",
|
|
"plt.legend()\n",
|
|
"\n",
|
|
"plt.subplot(1, 2, 2)\n",
|
|
"plt.plot(history.history['accuracy'])\n",
|
|
"plt.plot(history.history['val_accuracy'])\n",
|
|
"plt.xlabel('Epoch')\n",
|
|
"plt.ylabel('Accuracy')\n",
|
|
"plt.legend()\n",
|
|
"\n",
|
|
"plt.show()\n",
|
|
"\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "6176ce1e",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Make predictions on the test set\n",
|
|
"y_pred = model.predict(x_test)\n",
|
|
"y_pred = np.argmax(y_pred, axis=1)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "3635ded5",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Plot some examples from the test set and their predictions\n",
|
|
"fig, axes = plt.subplots(4, 4, figsize=(14, 14))\n",
|
|
"for i, ax in enumerate(axes.ravel()):\n",
|
|
" ax.matshow(x_test[i].reshape(28, 28), cmap='gray')\n",
|
|
" ax.set_title(\"True: %d\\nPredict: %d\" % (np.argmax(y_test[i]), y_pred[i]))\n",
|
|
" ax.axis(\"off\")\n",
|
|
"\n",
|
|
"plt.show()"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "Python 3 (ipykernel)",
|
|
"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": "3.8.16"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|