{"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":3004,"databundleVersionId":861823,"sourceType":"competition"},{"sourceId":9243,"sourceType":"datasetVersion","datasetId":2243}],"dockerImageVersionId":23025,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Introduction\n\nThe models you've built so far have relied on pre-trained models.  But they aren't the ideal solution for many use cases.  In this lesson, you will learn how to build totally new models.\n\n# Lesson\n","metadata":{}},{"cell_type":"code","source":"from IPython.display import YouTubeVideo\nYouTubeVideo('YbNE3zhtsoo', width=1280, height=460)","metadata":{"_kg_hide-input":true,"trusted":true,"execution":{"iopub.status.busy":"2024-12-22T06:18:07.722602Z","iopub.execute_input":"2024-12-22T06:18:07.723000Z","iopub.status.idle":"2024-12-22T06:18:39.752329Z","shell.execute_reply.started":"2024-12-22T06:18:07.722945Z","shell.execute_reply":"2024-12-22T06:18:39.751285Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Sample Code","metadata":{}},{"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nfrom sklearn.model_selection import train_test_split\nfrom tensorflow.python import keras\nfrom tensorflow.python.keras.models import Sequential\nfrom tensorflow.python.keras.layers import Dense, Flatten, Conv2D, Dropout\n\n\nimg_rows, img_cols = 28, 28\nnum_classes = 10\n\ndef data_prep(raw):\n    out_y = keras.utils.to_categorical(raw.label, num_classes)\n\n    num_images = raw.shape[0]\n    x_as_array = raw.values[:,1:]\n    x_shaped_array = x_as_array.reshape(num_images, img_rows, img_cols, 1)\n    out_x = x_shaped_array / 255\n    return out_x, out_y\n\ntrain_file = \"../input/digit-recognizer/train.csv\"\nraw_data = pd.read_csv(train_file)\n\nx, y = data_prep(raw_data)\n\nmodel = Sequential()\nmodel.add(Conv2D(20, kernel_size=(3, 3),\n                 activation='relu',\n                 input_shape=(img_rows, img_cols, 1)))\nmodel.add(Conv2D(20, kernel_size=(3, 3), activation='relu'))\nmodel.add(Flatten())\nmodel.add(Dense(128, activation='relu'))\nmodel.add(Dense(num_classes, activation='softmax'))\n\nmodel.compile(loss=keras.losses.categorical_crossentropy,\n              optimizer='adam',\n              metrics=['accuracy'])\nmodel.fit(x, y,\n          batch_size=128,\n          epochs=2,\n          validation_split = 0.2)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-22T06:19:51.195280Z","iopub.execute_input":"2024-12-22T06:19:51.195656Z","iopub.status.idle":"2024-12-22T06:21:13.588006Z","shell.execute_reply.started":"2024-12-22T06:19:51.195602Z","shell.execute_reply":"2024-12-22T06:21:13.587169Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Your Turn\nYou are ready to **[build your own model](https://www.kaggle.com/kernels/fork/3349938)**.\n","metadata":{}}]}