added training ipynb to my project

Week1.ipynb

@@ -0,0 +1,386 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Introduction to Machine Learning\n",
+    "\n",
+    "This notebook is an example of a CNN for recognizing handwritten characters.\n",
+    "\n",
+    "Most of this code is from https://keras.io/examples/vision/mnist_convnet/"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setup"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "from tensorflow import keras\n",
+    "from tensorflow.keras import layers"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Prepare the data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "x_train shape: (60000, 28, 28, 1)\n",
+      "60000 train samples\n",
+      "10000 test samples\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Model / data parameters\n",
+    "num_classes = 10\n",
+    "input_shape = (28, 28, 1)\n",
+    "\n",
+    "# Load the data and split it between train and test sets\n",
+    "(x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()\n",
+    "\n",
+    "# Scale images to the [0, 1] range\n",
+    "x_train = x_train.astype(\"float32\") / 255\n",
+    "x_test = x_test.astype(\"float32\") / 255\n",
+    "\n",
+    "# Make sure images have shape (28, 28, 1)\n",
+    "x_train = np.expand_dims(x_train, -1)\n",
+    "x_test = np.expand_dims(x_test, -1)\n",
+    "print(\"x_train shape:\", x_train.shape)\n",
+    "print(x_train.shape[0], \"train samples\")\n",
+    "print(x_test.shape[0], \"test samples\")\n",
+    "\n",
+    "\n",
+    "# convert class vectors to binary class matrices\n",
+    "y_train = keras.utils.to_categorical(y_train, num_classes)\n",
+    "y_test = keras.utils.to_categorical(y_test, num_classes)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Build the Model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Model: \"sequential\"\n",
+      "_________________________________________________________________\n",
+      " Layer (type)                Output Shape              Param #   \n",
+      "=================================================================\n",
+      " conv2d (Conv2D)             (None, 26, 26, 32)        320       \n",
+      "                                                                 \n",
+      " max_pooling2d (MaxPooling2D  (None, 13, 13, 32)       0         \n",
+      " )                                                               \n",
+      "                                                                 \n",
+      " conv2d_1 (Conv2D)           (None, 11, 11, 64)        18496     \n",
+      "                                                                 \n",
+      " max_pooling2d_1 (MaxPooling  (None, 5, 5, 64)         0         \n",
+      " 2D)                                                             \n",
+      "                                                                 \n",
+      " flatten (Flatten)           (None, 1600)              0         \n",
+      "                                                                 \n",
+      " dropout (Dropout)           (None, 1600)              0         \n",
+      "                                                                 \n",
+      " dense (Dense)               (None, 10)                16010     \n",
+      "                                                                 \n",
+      "=================================================================\n",
+      "Total params: 34,826\n",
+      "Trainable params: 34,826\n",
+      "Non-trainable params: 0\n",
+      "_________________________________________________________________\n"
+     ]
+    }
+   ],
+   "source": [
+    "model = keras.Sequential(\n",
+    "    [\n",
+    "        keras.Input(shape=input_shape),\n",
+    "        layers.Conv2D(32, kernel_size=(3, 3), activation=\"relu\"),\n",
+    "        layers.MaxPooling2D(pool_size=(2, 2)),\n",
+    "        layers.Conv2D(64, kernel_size=(3, 3), activation=\"relu\"),\n",
+    "        layers.MaxPooling2D(pool_size=(2, 2)),\n",
+    "        layers.Flatten(),\n",
+    "        layers.Dropout(0.5),\n",
+    "        layers.Dense(num_classes, activation=\"softmax\"),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "model.summary()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Train the Model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/15\n",
+      "422/422 [==============================] - 6s 3ms/step - loss: 0.3744 - accuracy: 0.8868 - val_loss: 0.0892 - val_accuracy: 0.9763\n",
+      "Epoch 2/15\n",
+      "422/422 [==============================] - 1s 3ms/step - loss: 0.1177 - accuracy: 0.9634 - val_loss: 0.0660 - val_accuracy: 0.9817\n",
+      "Epoch 3/15\n",
+      "422/422 [==============================] - 1s 3ms/step - loss: 0.0876 - accuracy: 0.9732 - val_loss: 0.0480 - val_accuracy: 0.9865\n",
+      "Epoch 4/15\n",
+      "422/422 [==============================] - 1s 3ms/step - loss: 0.0738 - accuracy: 0.9774 - val_loss: 0.0462 - val_accuracy: 0.9872\n",
+      "Epoch 5/15\n",
+      "422/422 [==============================] - 1s 3ms/step - loss: 0.0642 - accuracy: 0.9805 - val_loss: 0.0440 - val_accuracy: 0.9872\n",
+      "Epoch 6/15\n",
+      "422/422 [==============================] - 1s 2ms/step - loss: 0.0585 - accuracy: 0.9818 - val_loss: 0.0373 - val_accuracy: 0.9898\n",
+      "Epoch 7/15\n",
+      "422/422 [==============================] - 1s 3ms/step - loss: 0.0544 - accuracy: 0.9832 - val_loss: 0.0348 - val_accuracy: 0.9908\n",
+      "Epoch 8/15\n",
+      "422/422 [==============================] - 1s 3ms/step - loss: 0.0495 - accuracy: 0.9845 - val_loss: 0.0342 - val_accuracy: 0.9907\n",
+      "Epoch 9/15\n",
+      "422/422 [==============================] - 1s 2ms/step - loss: 0.0462 - accuracy: 0.9853 - val_loss: 0.0313 - val_accuracy: 0.9910\n",
+      "Epoch 10/15\n",
+      "422/422 [==============================] - 1s 2ms/step - loss: 0.0444 - accuracy: 0.9858 - val_loss: 0.0320 - val_accuracy: 0.9907\n",
+      "Epoch 11/15\n",
+      "422/422 [==============================] - 1s 2ms/step - loss: 0.0418 - accuracy: 0.9872 - val_loss: 0.0303 - val_accuracy: 0.9913\n",
+      "Epoch 12/15\n",
+      "422/422 [==============================] - 1s 3ms/step - loss: 0.0410 - accuracy: 0.9874 - val_loss: 0.0276 - val_accuracy: 0.9922\n",
+      "Epoch 13/15\n",
+      "422/422 [==============================] - 1s 3ms/step - loss: 0.0381 - accuracy: 0.9875 - val_loss: 0.0292 - val_accuracy: 0.9912\n",
+      "Epoch 14/15\n",
+      "422/422 [==============================] - 1s 2ms/step - loss: 0.0368 - accuracy: 0.9879 - val_loss: 0.0291 - val_accuracy: 0.9920\n",
+      "Epoch 15/15\n",
+      "422/422 [==============================] - 1s 2ms/step - loss: 0.0356 - accuracy: 0.9888 - val_loss: 0.0257 - val_accuracy: 0.9925\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<keras.callbacks.History at 0x1c9d4871f40>"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "batch_size = 128\n",
+    "epochs = 15\n",
+    "\n",
+    "model.compile(loss=\"categorical_crossentropy\", optimizer=\"adam\", metrics=[\"accuracy\"])\n",
+    "\n",
+    "model.fit(x_train, y_train, batch_size=batch_size, epochs=epochs, validation_split=0.1)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Evaluate the Trained Model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Test loss: 0.026043808087706566\n",
+      "Test accuracy: 0.9907000064849854\n"
+     ]
+    }
+   ],
+   "source": [
+    "score = model.evaluate(x_test, y_test, verbose=0)\n",
+    "print(\"Test loss:\", score[0])\n",
+    "print(\"Test accuracy:\", score[1])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model.save(\"mnist.h5\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Example GUI"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "4\n"
+     ]
+    }
+   ],
+   "source": [
+    "from tkinter import *\n",
+    "from PIL import ImageGrab\n",
+    "import imageio\n",
+    "import tkinter.font as font\n",
+    "\n",
+    "class Paint(object):\n",
+    "    def __init__(self):\n",
+    "        self.root=Tk()\n",
+    "        self.root.title('Playing with numbers')\n",
+    "        # self.root.wm_iconbitmap('44143.ico')\n",
+    "        self.root.configure(background='light salmon')\n",
+    "        self.c = Canvas(self.root,bg='light cyan', height=330, width=400)\n",
+    "        self.label = Label(self.root, text='Draw any numer', font=20, bg='light salmon')\n",
+    "        self.label.grid(row=0, column=3)\n",
+    "        self.c.grid(row=1, columnspan=9)\n",
+    "        self.c.create_line(0,0,400,0,width=20,fill='midnight blue')\n",
+    "        self.c.create_line(0,0,0,330,width=20,fill='midnight blue')\n",
+    "        self.c.create_line(400,0,400,330,width=20,fill='midnight blue')\n",
+    "        self.c.create_line(0,330,400,330,width=20,fill='midnight blue')\n",
+    "        self.myfont = font.Font(size=20,weight='bold')\n",
+    "        self.predicting_button=Button(self.root,text='Predict', fg='white', bg='blue', height=2, width=6, font=self.myfont, command=lambda:self.classify(self.c))\n",
+    "        self.predicting_button.grid(row=2,column=1)\n",
+    "        self.clear=Button(self.root,text='Clear', fg='white', bg='orange', height=2, width=6, font=self.myfont, command=self.clear)\n",
+    "        self.clear.grid(row=2,column=5)\n",
+    "        self.prediction_text = Text(self.root, height=5, width=5)\n",
+    "        self.prediction_text.grid(row=4, column=3)\n",
+    "        self.label=Label(self.root, text=\"Predicted Number is\", fg=\"black\", font=30, bg='light salmon')\n",
+    "\n",
+    "        self.label.grid(row=3,column=3)\n",
+    "        self.model=model\n",
+    "        self.setup()\n",
+    "        self.root.mainloop()\n",
+    "\n",
+    "\n",
+    "    def setup(self):\n",
+    "        self.old_x=None\n",
+    "        self.old_y=None\n",
+    "        self.color='black'\n",
+    "        self.linewidth=15\n",
+    "        self.c.bind('<B1-Motion>', self.paint)\n",
+    "        self.c.bind('<ButtonRelease-1>', self.reset)\n",
+    "\n",
+    "\n",
+    "    def paint(self,event):\n",
+    "        paint_color=self.color\n",
+    "        if self.old_x and self.old_y:\n",
+    "            self.c.create_line(self.old_x,self.old_y,event.x,event.y,fill=paint_color,width=self.linewidth,capstyle=ROUND,\n",
+    "                              smooth=TRUE,splinesteps=48)\n",
+    "        self.old_x=event.x\n",
+    "        self.old_y=event.y\n",
+    "\n",
+    "\n",
+    "    def clear(self):\n",
+    "        \"\"\"Clear drawing area\"\"\"\n",
+    "        self.c.delete(\"all\")\n",
+    "\n",
+    "    def reset(self, event):\n",
+    "        \"\"\"reset old_x and old_y if the left mouse button is released\"\"\"\n",
+    "        self.old_x, self.old_y = None, None\n",
+    "\n",
+    "\n",
+    "    def classify(self,widget):\n",
+    "        x=self.root.winfo_rootx()+widget.winfo_x()\n",
+    "        y=self.root.winfo_rooty()+widget.winfo_y()\n",
+    "        x1=widget.winfo_width()\n",
+    "        y1=widget.winfo_height()\n",
+    "        ImageGrab.grab().crop((x,y,x1,y1)).resize((28,28)).save('classify.png')\n",
+    "        img=imageio.imread('classify.png', as_gray=True, pilmode='P')\n",
+    "        img=np.array(img)\n",
+    "        img=np.reshape(img,(1,28,28,1))\n",
+    "        img[img==0] = 255\n",
+    "        img[img==225] = 0\n",
+    "        # Predict digit\n",
+    "        pred = self.model.predict([img])\n",
+    "        # Get index with highest probability\n",
+    "        pred = np.argmax(pred)\n",
+    "        print(pred)\n",
+    "        self.prediction_text.delete(\"1.0\", END)\n",
+    "        self.prediction_text.insert(END, pred)\n",
+    "        labelfont = ('times', 30, 'bold')\n",
+    "        self.prediction_text.config(font=labelfont)\n",
+    "\n",
+    "if __name__ == '__main__':\n",
+    "    Paint()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3.9.7 ('base')",
+   "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": "3.9.7"
+  },
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "ad2bdc8ecc057115af97d19610ffacc2b4e99fae6737bb82f5d7fb13d2f2c186"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}