{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"},"colab":{"name":"DL_Application_Planesnet_CNN.ipynb","provenance":[{"file_id":"1GuinfW8s8JE4N0CzT792xiw0yqaRTJS4","timestamp":1648436816591},{"file_id":"1IrvtfkBGUpea56SI2FHsJ5xgOqEFlz7R","timestamp":1648436787091}],"collapsed_sections":[]}},"nbformat_minor":0,"nbformat":4,"cells":[{"cell_type":"code","source":[""],"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2021-11-24T12:19:43.092646Z","iopub.execute_input":"2021-11-24T12:19:43.09335Z","iopub.status.idle":"2021-11-24T12:19:46.085199Z","shell.execute_reply.started":"2021-11-24T12:19:43.093264Z","shell.execute_reply":"2021-11-24T12:19:46.084508Z"},"trusted":true,"id":"r-UmqOmZIJMf"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":["## CNN classifier for the planesnet data"],"metadata":{"id":"_9aqwCIad4pS"}},{"cell_type":"code","source":["## import packages\n","\n","import numpy as np # linear algebra\n","import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n","import matplotlib.pyplot as plt\n","from sklearn.model_selection import train_test_split\n","from sklearn.preprocessing import MinMaxScaler\n","from keras.models import Sequential, Model\n","from tensorflow.keras.layers import Conv2D, MaxPooling2D, Dense, Activation, Dropout, Flatten\n","from tensorflow.keras.layers import BatchNormalization\n","\n","from tensorflow.keras.optimizers import Adam\n","from keras.callbacks import LearningRateScheduler\n","from keras.regularizers import l2, l1\n","import math\n"],"metadata":{"id":"6Al4ArJ5d21l"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["## Mount drive folder\n","from google.colab import drive\n","\n","drive.mount('/content/drive')"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"iKat3xvMIsN7","executionInfo":{"status":"ok","timestamp":1648435557018,"user_tz":240,"elapsed":771,"user":{"displayName":"Guray Erus","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GiGnBNnSM10DAl86Xzx2wV9MnzBNDvcAv6FeVBn=s64","userId":"15374812584437350386"}},"outputId":"90b717b3-4bad-445e-a9c9-841f634787c8"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n"]}]},{"cell_type":"code","source":["## Read data in json format\n","data = pd.read_json('/content/drive/MyDrive/CommonFiles/MUSA650-Data/planesnet.json')"],"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","execution":{"iopub.status.busy":"2021-11-24T12:19:46.086133Z","iopub.execute_input":"2021-11-24T12:19:46.086408Z","iopub.status.idle":"2021-11-24T12:19:52.796249Z","shell.execute_reply.started":"2021-11-24T12:19:46.086358Z","shell.execute_reply":"2021-11-24T12:19:52.795603Z"},"trusted":true,"id":"tUGZwlGzIJMm"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["## View the dataframe\n","data.head()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":206},"id":"2hWPtM8HLnIH","executionInfo":{"status":"ok","timestamp":1648435565755,"user_tz":240,"elapsed":215,"user":{"displayName":"Guray Erus","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GiGnBNnSM10DAl86Xzx2wV9MnzBNDvcAv6FeVBn=s64","userId":"15374812584437350386"}},"outputId":"4d0115b1-0f7d-4527-c2e6-28c5bd0ff0d7"},"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/plain":["                                                data  labels  \\\n","0  [206, 195, 187, 183, 177, 175, 174, 193, 198, ...       1   \n","1  [215, 209, 200, 196, 192, 197, 205, 168, 155, ...       1   \n","2  [204, 214, 220, 219, 213, 205, 198, 193, 199, ...       1   \n","3  [179, 174, 179, 178, 173, 170, 168, 168, 168, ...       1   \n","4  [222, 222, 218, 214, 208, 205, 207, 206, 206, ...       1   \n","\n","                                   locations             scene_ids  \n","0  [-118.40497658522878, 33.940618514147936]  20170620_175442_0e30  \n","1            [-122.392469714, 37.6176425378]  20161212_180859_0e30  \n","2            [-122.397578597, 37.6209247852]  20170524_181349_0e2f  \n","3            [-122.214849831, 37.7203378331]  20161110_180707_0e1f  \n","4            [-117.862173435, 33.6796854072]  20160813_184932_0c64  "],"text/html":["\n","  <div id=\"df-716e4948-ffd9-4f60-ba6c-a8661df0b188\">\n","    <div class=\"colab-df-container\">\n","      <div>\n","<style scoped>\n","    .dataframe tbody tr th:only-of-type {\n","        vertical-align: middle;\n","    }\n","\n","    .dataframe tbody tr th {\n","        vertical-align: top;\n","    }\n","\n","    .dataframe thead th {\n","        text-align: right;\n","    }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n","  <thead>\n","    <tr style=\"text-align: right;\">\n","      <th></th>\n","      <th>data</th>\n","      <th>labels</th>\n","      <th>locations</th>\n","      <th>scene_ids</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>[206, 195, 187, 183, 177, 175, 174, 193, 198, ...</td>\n","      <td>1</td>\n","      <td>[-118.40497658522878, 33.940618514147936]</td>\n","      <td>20170620_175442_0e30</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>[215, 209, 200, 196, 192, 197, 205, 168, 155, ...</td>\n","      <td>1</td>\n","      <td>[-122.392469714, 37.6176425378]</td>\n","      <td>20161212_180859_0e30</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>[204, 214, 220, 219, 213, 205, 198, 193, 199, ...</td>\n","      <td>1</td>\n","      <td>[-122.397578597, 37.6209247852]</td>\n","      <td>20170524_181349_0e2f</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>[179, 174, 179, 178, 173, 170, 168, 168, 168, ...</td>\n","      <td>1</td>\n","      <td>[-122.214849831, 37.7203378331]</td>\n","      <td>20161110_180707_0e1f</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>[222, 222, 218, 214, 208, 205, 207, 206, 206, ...</td>\n","      <td>1</td>\n","      <td>[-117.862173435, 33.6796854072]</td>\n","      <td>20160813_184932_0c64</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>\n","      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-716e4948-ffd9-4f60-ba6c-a8661df0b188')\"\n","              title=\"Convert this dataframe to an interactive table.\"\n","              style=\"display:none;\">\n","        \n","  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n","       width=\"24px\">\n","    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n","    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n","  </svg>\n","      </button>\n","      \n","  <style>\n","    .colab-df-container {\n","      display:flex;\n","      flex-wrap:wrap;\n","      gap: 12px;\n","    }\n","\n","    .colab-df-convert {\n","      background-color: #E8F0FE;\n","      border: none;\n","      border-radius: 50%;\n","      cursor: pointer;\n","      display: none;\n","      fill: #1967D2;\n","      height: 32px;\n","      padding: 0 0 0 0;\n","      width: 32px;\n","    }\n","\n","    .colab-df-convert:hover {\n","      background-color: #E2EBFA;\n","      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n","      fill: #174EA6;\n","    }\n","\n","    [theme=dark] .colab-df-convert {\n","      background-color: #3B4455;\n","      fill: #D2E3FC;\n","    }\n","\n","    [theme=dark] .colab-df-convert:hover {\n","      background-color: #434B5C;\n","      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n","      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n","      fill: #FFFFFF;\n","    }\n","  </style>\n","\n","      <script>\n","        const buttonEl =\n","          document.querySelector('#df-716e4948-ffd9-4f60-ba6c-a8661df0b188 button.colab-df-convert');\n","        buttonEl.style.display =\n","          google.colab.kernel.accessAllowed ? 'block' : 'none';\n","\n","        async function convertToInteractive(key) {\n","          const element = document.querySelector('#df-716e4948-ffd9-4f60-ba6c-a8661df0b188');\n","          const dataTable =\n","            await google.colab.kernel.invokeFunction('convertToInteractive',\n","                                                     [key], {});\n","          if (!dataTable) return;\n","\n","          const docLinkHtml = 'Like what you see? Visit the ' +\n","            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n","            + ' to learn more about interactive tables.';\n","          element.innerHTML = '';\n","          dataTable['output_type'] = 'display_data';\n","          await google.colab.output.renderOutput(dataTable, element);\n","          const docLink = document.createElement('div');\n","          docLink.innerHTML = docLinkHtml;\n","          element.appendChild(docLink);\n","        }\n","      </script>\n","    </div>\n","  </div>\n","  "]},"metadata":{},"execution_count":4}]},{"cell_type":"code","source":["## Read image data into a 2D matrix\n","X = np.array(data.data.tolist())\n","X.shape"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"21QdYsAuJH_q","executionInfo":{"status":"ok","timestamp":1648435575302,"user_tz":240,"elapsed":9549,"user":{"displayName":"Guray Erus","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GiGnBNnSM10DAl86Xzx2wV9MnzBNDvcAv6FeVBn=s64","userId":"15374812584437350386"}},"outputId":"a161ff6b-87f7-4667-f6bb-51a7b64079fc"},"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/plain":["(32000, 1200)"]},"metadata":{},"execution_count":5}]},{"cell_type":"code","source":["## Reshape the image data to 20x20 image patches with 3 channels (RGB)\n","X = X.reshape(32000, 3, 20, 20)\n","X.shape"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"jTFk1Q3EJ-R_","executionInfo":{"status":"ok","timestamp":1648435575303,"user_tz":240,"elapsed":18,"user":{"displayName":"Guray Erus","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GiGnBNnSM10DAl86Xzx2wV9MnzBNDvcAv6FeVBn=s64","userId":"15374812584437350386"}},"outputId":"f4367ce0-f369-44b8-b0e2-54da0e71f834"},"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/plain":["(32000, 3, 20, 20)"]},"metadata":{},"execution_count":6}]},{"cell_type":"code","source":["## Standard format for RGB is \"the channels at the end\"; move the axis for channels to the end\n","X = np.moveaxis(X, 1, 3)\n","X.shape"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"xzmQw5xpLJQB","executionInfo":{"status":"ok","timestamp":1648435575304,"user_tz":240,"elapsed":17,"user":{"displayName":"Guray Erus","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GiGnBNnSM10DAl86Xzx2wV9MnzBNDvcAv6FeVBn=s64","userId":"15374812584437350386"}},"outputId":"9b9c097b-5788-44d2-8a66-7fe3274b694d"},"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/plain":["(32000, 20, 20, 3)"]},"metadata":{},"execution_count":7}]},{"cell_type":"code","source":["## View few images\n","tmpI = X[46,:,:,:]\n","plt.imshow(tmpI)\n","plt.show()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":265},"id":"jBTiowdeKTJL","executionInfo":{"status":"ok","timestamp":1648435575830,"user_tz":240,"elapsed":540,"user":{"displayName":"Guray Erus","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GiGnBNnSM10DAl86Xzx2wV9MnzBNDvcAv6FeVBn=s64","userId":"15374812584437350386"}},"outputId":"6ee1b9bd-3ccd-4774-facb-9403ed6cabd8"},"execution_count":null,"outputs":[{"output_type":"display_data","data":{"text/plain":["<Figure size 432x288 with 1 Axes>"],"image/png":"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\n"},"metadata":{"needs_background":"light"}}]},{"cell_type":"code","source":["## Read the labels\n","y = np.array(data['labels'])\n","y.shape"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"m0odKOySLcBu","executionInfo":{"status":"ok","timestamp":1648435575830,"user_tz":240,"elapsed":7,"user":{"displayName":"Guray Erus","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GiGnBNnSM10DAl86Xzx2wV9MnzBNDvcAv6FeVBn=s64","userId":"15374812584437350386"}},"outputId":"13e0508d-f0b2-4601-8882-025a6cfaf3b7"},"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/plain":["(32000,)"]},"metadata":{},"execution_count":9}]},{"cell_type":"code","source":["## Split the data into training ans testing sets\n","X_tr, X_te, y_tr, y_te = train_test_split(X, y, test_size = 0.20)\n","\n","## Scale the data\n","scalar = MinMaxScaler()\n","scalar.fit(X_tr.reshape(X_tr.shape[0], -1))\n","X_tr = scalar.transform(X_tr.reshape(X_tr.shape[0], -1)).reshape(X_tr.shape)\n","X_te = scalar.transform(X_te.reshape(X_te.shape[0], -1)).reshape(X_te.shape)"],"metadata":{"_uuid":"dda6b94e09cd92efe0ef3d99b4315b66a1381fca","execution":{"iopub.status.busy":"2021-11-24T12:19:58.677162Z","iopub.execute_input":"2021-11-24T12:19:58.67761Z","iopub.status.idle":"2021-11-24T12:19:59.663545Z","shell.execute_reply.started":"2021-11-24T12:19:58.677557Z","shell.execute_reply":"2021-11-24T12:19:59.662813Z"},"trusted":true,"id":"-tn7GBw8IJMn"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["## Show data size\n","print(X_tr.shape)\n","print(y_tr.shape)\n","print(X_te.shape)\n","print(y_te.shape)"],"metadata":{"_uuid":"262910e541bc1078d426bb561166e5984618e70d","execution":{"iopub.status.busy":"2021-11-24T12:19:59.666542Z","iopub.execute_input":"2021-11-24T12:19:59.666772Z","iopub.status.idle":"2021-11-24T12:19:59.674235Z","shell.execute_reply.started":"2021-11-24T12:19:59.666724Z","shell.execute_reply":"2021-11-24T12:19:59.673451Z"},"trusted":true,"colab":{"base_uri":"https://localhost:8080/"},"id":"aJC0pFrIIJMo","executionInfo":{"status":"ok","timestamp":1648435577439,"user_tz":240,"elapsed":8,"user":{"displayName":"Guray Erus","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GiGnBNnSM10DAl86Xzx2wV9MnzBNDvcAv6FeVBn=s64","userId":"15374812584437350386"}},"outputId":"42e5d96a-4b54-4887-994a-6c8ecc086513"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["(25600, 20, 20, 3)\n","(25600,)\n","(6400, 20, 20, 3)\n","(6400,)\n"]}]},{"cell_type":"code","source":["## Get the shape of a single sample\n","dshape = X_tr.shape[1:]\n","dshape"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"ri6uqSbQOyVB","executionInfo":{"status":"ok","timestamp":1648435577440,"user_tz":240,"elapsed":7,"user":{"displayName":"Guray Erus","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GiGnBNnSM10DAl86Xzx2wV9MnzBNDvcAv6FeVBn=s64","userId":"15374812584437350386"}},"outputId":"901545ec-2624-4073-fcd0-d959ba20c478"},"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/plain":["(20, 20, 3)"]},"metadata":{},"execution_count":12}]},{"cell_type":"code","source":["## Construct the model\n","model = Sequential()\n","model.add(Conv2D(32, kernel_size=(3, 3), strides=(1,1), input_shape=dshape))\n","model.add(BatchNormalization())\n","model.add(Activation('relu'))\n","model.add(MaxPooling2D((2,2)))\n","\n","model.add(Conv2D(32, kernel_size=(3, 3), strides=(1,1)))\n","model.add(BatchNormalization())\n","model.add(Activation('relu'))\n","model.add(MaxPooling2D((2,2)))\n","\n","model.add(Flatten())\n","model.add(Dense(64, activation='relu'))\n","model.add(Dropout(0.5))\n","\n","model.add(Dense(1, activation='sigmoid'))\n","\n","print(model.summary())\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"NKlaHd00NeYu","executionInfo":{"status":"ok","timestamp":1648435578198,"user_tz":240,"elapsed":762,"user":{"displayName":"Guray Erus","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GiGnBNnSM10DAl86Xzx2wV9MnzBNDvcAv6FeVBn=s64","userId":"15374812584437350386"}},"outputId":"4216bb55-3a82-4d19-86ed-630f5fb0710b"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Model: \"sequential\"\n","_________________________________________________________________\n"," Layer (type)                Output Shape              Param #   \n","=================================================================\n"," conv2d (Conv2D)             (None, 18, 18, 32)        896       \n","                                                                 \n"," batch_normalization (BatchN  (None, 18, 18, 32)       128       \n"," ormalization)                                                   \n","                                                                 \n"," activation (Activation)     (None, 18, 18, 32)        0         \n","                                                                 \n"," max_pooling2d (MaxPooling2D  (None, 9, 9, 32)         0         \n"," )                                                               \n","                                                                 \n"," conv2d_1 (Conv2D)           (None, 7, 7, 32)          9248      \n","                                                                 \n"," batch_normalization_1 (Batc  (None, 7, 7, 32)         128       \n"," hNormalization)                                                 \n","                                                                 \n"," activation_1 (Activation)   (None, 7, 7, 32)          0         \n","                                                                 \n"," max_pooling2d_1 (MaxPooling  (None, 3, 3, 32)         0         \n"," 2D)                                                             \n","                                                                 \n"," flatten (Flatten)           (None, 288)               0         \n","                                                                 \n"," dense (Dense)               (None, 64)                18496     \n","                                                                 \n"," dropout (Dropout)           (None, 64)                0         \n","                                                                 \n"," dense_1 (Dense)             (None, 1)                 65        \n","                                                                 \n","=================================================================\n","Total params: 28,961\n","Trainable params: 28,833\n","Non-trainable params: 128\n","_________________________________________________________________\n","None\n"]}]},{"cell_type":"code","source":["## Compile the model\n","OPT = Adam(learning_rate=0.0001)\n","NUM_EPOCH = 15\n","B_SIZE = 64\n","model.compile(loss='binary_crossentropy', optimizer=OPT, metrics=['accuracy'])\n"],"metadata":{"_uuid":"5ea699424bd684394d87c80855caa40fbc097f01","execution":{"iopub.status.busy":"2021-11-24T12:20:03.869484Z","iopub.execute_input":"2021-11-24T12:20:03.869729Z","iopub.status.idle":"2021-11-24T12:21:15.972553Z","shell.execute_reply.started":"2021-11-24T12:20:03.869683Z","shell.execute_reply":"2021-11-24T12:21:15.971879Z"},"trusted":true,"id":"OHH6RfcjIJMp"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["## Train the model\n","mdl_tr = model.fit(X_tr, y_tr, batch_size=B_SIZE, epochs=NUM_EPOCH, shuffle=True, validation_data=(X_te, y_te))\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"IojQRhucRjmD","executionInfo":{"status":"ok","timestamp":1648436610054,"user_tz":240,"elapsed":263361,"user":{"displayName":"Guray Erus","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GiGnBNnSM10DAl86Xzx2wV9MnzBNDvcAv6FeVBn=s64","userId":"15374812584437350386"}},"outputId":"28c415cd-032d-41a6-cd29-ee3676760237"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Epoch 1/15\n","400/400 [==============================] - 19s 44ms/step - loss: 0.3205 - accuracy: 0.8585 - val_loss: 0.7776 - val_accuracy: 0.7542\n","Epoch 2/15\n","400/400 [==============================] - 16s 40ms/step - loss: 0.1881 - accuracy: 0.9271 - val_loss: 0.1466 - val_accuracy: 0.9458\n","Epoch 3/15\n","400/400 [==============================] - 16s 40ms/step - loss: 0.1545 - accuracy: 0.9420 - val_loss: 0.1438 - val_accuracy: 0.9456\n","Epoch 4/15\n","400/400 [==============================] - 21s 52ms/step - loss: 0.1347 - accuracy: 0.9498 - val_loss: 0.1248 - val_accuracy: 0.9536\n","Epoch 5/15\n","400/400 [==============================] - 21s 53ms/step - loss: 0.1224 - accuracy: 0.9544 - val_loss: 0.1179 - val_accuracy: 0.9592\n","Epoch 6/15\n","400/400 [==============================] - 16s 40ms/step - loss: 0.1120 - accuracy: 0.9591 - val_loss: 0.1039 - val_accuracy: 0.9628\n","Epoch 7/15\n","400/400 [==============================] - 17s 41ms/step - loss: 0.1031 - accuracy: 0.9619 - val_loss: 0.1323 - val_accuracy: 0.9503\n","Epoch 8/15\n","400/400 [==============================] - 17s 42ms/step - loss: 0.0972 - accuracy: 0.9639 - val_loss: 0.0926 - val_accuracy: 0.9638\n","Epoch 9/15\n","400/400 [==============================] - 16s 41ms/step - loss: 0.0923 - accuracy: 0.9664 - val_loss: 0.1069 - val_accuracy: 0.9609\n","Epoch 10/15\n","400/400 [==============================] - 17s 42ms/step - loss: 0.0848 - accuracy: 0.9700 - val_loss: 0.0822 - val_accuracy: 0.9712\n","Epoch 11/15\n","400/400 [==============================] - 18s 44ms/step - loss: 0.0816 - accuracy: 0.9698 - val_loss: 0.0769 - val_accuracy: 0.9733\n","Epoch 12/15\n","400/400 [==============================] - 17s 43ms/step - loss: 0.0774 - accuracy: 0.9726 - val_loss: 0.0792 - val_accuracy: 0.9723\n","Epoch 13/15\n","400/400 [==============================] - 17s 42ms/step - loss: 0.0748 - accuracy: 0.9729 - val_loss: 0.0762 - val_accuracy: 0.9708\n","Epoch 14/15\n","400/400 [==============================] - 17s 42ms/step - loss: 0.0689 - accuracy: 0.9755 - val_loss: 0.1070 - val_accuracy: 0.9598\n","Epoch 15/15\n","400/400 [==============================] - 18s 45ms/step - loss: 0.0665 - accuracy: 0.9765 - val_loss: 0.0920 - val_accuracy: 0.9656\n"]}]},{"cell_type":"code","source":["## Plot the learning stats\n","fig, ax = plt.subplots(1,2, figsize=[18,6])\n","ax[0].plot(range(1, NUM_EPOCH+1), mdl_tr.history['loss'], c='blue', label='Training loss')\n","ax[0].plot(range(1, NUM_EPOCH+1), mdl_tr.history['val_loss'], c='red', label='Validation loss')\n","ax[0].legend()\n","ax[0].set_xlabel('epochs')\n","\n","ax[1].plot(range(1, NUM_EPOCH+1), mdl_tr.history['accuracy'], c='blue', label='Training accuracy')\n","ax[1].plot(range(1, NUM_EPOCH+1), mdl_tr.history['val_accuracy'], c='red', label='Validation accuracy')\n","ax[1].legend()\n","ax[1].set_xlabel('epochs')\n"],"metadata":{"_uuid":"653018d22e7eaab2d582fd1e878cf90527503170","execution":{"iopub.status.busy":"2021-11-24T12:22:21.574019Z","iopub.execute_input":"2021-11-24T12:22:21.574293Z","iopub.status.idle":"2021-11-24T12:22:22.103168Z","shell.execute_reply.started":"2021-11-24T12:22:21.574244Z","shell.execute_reply":"2021-11-24T12:22:22.10244Z"},"trusted":true,"colab":{"base_uri":"https://localhost:8080/","height":405},"id":"0jHSPccTIJMq","executionInfo":{"status":"ok","timestamp":1648436647612,"user_tz":240,"elapsed":1120,"user":{"displayName":"Guray Erus","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GiGnBNnSM10DAl86Xzx2wV9MnzBNDvcAv6FeVBn=s64","userId":"15374812584437350386"}},"outputId":"0c20472c-e096-44ff-f2dc-73648354ae85"},"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/plain":["Text(0.5, 0, 'epochs')"]},"metadata":{},"execution_count":18},{"output_type":"display_data","data":{"text/plain":["<Figure size 1296x432 with 2 Axes>"],"image/png":"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\n"},"metadata":{"needs_background":"light"}}]}]}