{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","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"}],"dockerImageVersionId":30615,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport os\n\nimport keras\n#from keras.layers.convolutional import Conv2DTranspose\n#from keras.layers.merge import concatenate\nfrom keras.layers import UpSampling2D, Conv2D, Activation, Input, Dropout, MaxPooling2D, Conv2DTranspose, Lambda, concatenate\nfrom keras import Model \nfrom keras import backend as K\n#from keras.layers.core import Lambda\n\nx = pd.read_csv(\"/kaggle/input/digit-recognizer/train.csv\")\nx.head()\nprint(x.size)","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2023-12-23T13:01:46.834244Z","iopub.execute_input":"2023-12-23T13:01:46.834693Z","iopub.status.idle":"2023-12-23T13:01:50.090639Z","shell.execute_reply.started":"2023-12-23T13:01:46.834661Z","shell.execute_reply":"2023-12-23T13:01:50.08943Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"x_train = x.iloc[range(70),range(1,785,1)]\nx_train.head()\nx_train.size","metadata":{"execution":{"iopub.status.busy":"2023-12-23T12:58:41.79646Z","iopub.execute_input":"2023-12-23T12:58:41.79724Z","iopub.status.idle":"2023-12-23T12:58:41.807396Z","shell.execute_reply.started":"2023-12-23T12:58:41.7972Z","shell.execute_reply":"2023-12-23T12:58:41.806103Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"inputs = Input(shape = (28,28,1))\nc1 = Conv2D(\n    16,(3,3), \n    activation = 'relu', \n    kernel_initializer = 'he_normal', \n    padding = 'same')(inputs)\nc1 = Dropout(0.1)(c1)\nc1 = Conv2D(\n    16,(3,3),\n    activation = 'relu',\n    kernel_initializer = 'he_normal',\n    padding = 'same')(c1)\np1 = MaxPooling2D(2,2)(c1)\nc2 = Conv2D(\n    32,\n    (3,3),\n    activation = 'relu',\n    kernel_initializer = 'he_normal',\n    padding ='same')(p1)\nc2 = Dropout(0.1)(c2)\nc2 = Conv2D(\n    32,\n    (3,3),\n    activation = 'relu',\n    kernel_initializer = 'he_normal',\n    padding = 'same') (c2)\n\nu1 = Conv2DTranspose(\n    16,\n    (2,2),\n    strides = (2,2),\n    padding = 'same') (c2)\nu1 = concatenate([u1,c1])\nu1 = Conv2D(\n    16,\n    (3,3),\n    activation = 'relu',\n    kernel_initializer = 'he_normal',\n    padding = 'same')(u1)\n\noutputs = Conv2D(\n    1,\n    (1,1),\n    activation = 'sigmoid') (u1)\n\nmodel = Model(inputs = [inputs], outputs = [outputs])\nmodel.compile(optimizer = 'adam', loss = 'binary_crossentropy')\nbatch_size = 1\nresults = model.fit_generator(\n    keras_generator = batch_size,\n    steps_per_epoch = 10,\n    epochs = 2)\n\npred = model.predict(x_train)\n","metadata":{"execution":{"iopub.status.busy":"2023-12-23T13:01:56.239255Z","iopub.execute_input":"2023-12-23T13:01:56.239934Z","iopub.status.idle":"2023-12-23T13:01:56.447396Z","shell.execute_reply.started":"2023-12-23T13:01:56.239874Z","shell.execute_reply":"2023-12-23T13:01:56.446266Z"},"trusted":true},"execution_count":null,"outputs":[]}]}