{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":3004,"databundleVersionId":861823,"sourceType":"competition"}],"dockerImageVersionId":30665,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-03-07T07:51:42.571892Z","iopub.execute_input":"2024-03-07T07:51:42.572464Z","iopub.status.idle":"2024-03-07T07:51:43.427070Z","shell.execute_reply.started":"2024-03-07T07:51:42.572435Z","shell.execute_reply":"2024-03-07T07:51:43.426147Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import warnings\nimport  itertools\nimport tensorflow as tf\nfrom sklearn.model_selection import train_test_split\nfrom tensorflow.keras.utils import to_categorical\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Dense,Dropout,Flatten,Conv2D,MaxPool2D\nfrom tensorflow.keras.optimizers import RMSprop\nfrom tensorflow.keras.callbacks import ReduceLROnPlateau\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nimport numpy as np\nimport pandas as pd","metadata":{"execution":{"iopub.status.busy":"2024-03-07T07:51:46.184189Z","iopub.execute_input":"2024-03-07T07:51:46.184686Z","iopub.status.idle":"2024-03-07T07:51:58.023573Z","shell.execute_reply.started":"2024-03-07T07:51:46.184656Z","shell.execute_reply":"2024-03-07T07:51:58.022813Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(tf.__version__)","metadata":{"execution":{"iopub.status.busy":"2024-03-07T07:27:47.250494Z","iopub.execute_input":"2024-03-07T07:27:47.250925Z","iopub.status.idle":"2024-03-07T07:27:47.254948Z","shell.execute_reply.started":"2024-03-07T07:27:47.250890Z","shell.execute_reply":"2024-03-07T07:27:47.254143Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"batch_size = 86\nepochs = 35\n#加载数据\ntrain = pd.read_csv(\"/kaggle/input/digit-recognizer/train.csv\")\ntest = pd.read_csv(\"/kaggle/input/digit-recognizer/test.csv\")\n\nprint(\"训练集大小\",train.shape)\nprint(\"测试集大小\",test.shape)\n","metadata":{"execution":{"iopub.status.busy":"2024-03-07T07:52:08.632640Z","iopub.execute_input":"2024-03-07T07:52:08.633806Z","iopub.status.idle":"2024-03-07T07:52:14.348585Z","shell.execute_reply.started":"2024-03-07T07:52:08.633769Z","shell.execute_reply":"2024-03-07T07:52:14.347531Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#取出标签类做统计\nY_train = train[\"label\"]\nX_train = train.drop(labels=[\"label\"],axis=1)\n#数据预处理 查看有没有空值\nprint(X_train.isnull().any().describe())\n\nprint(test.isnull().any().describe())\n\n#没有缺失值\n#灰度归一化  减少照明差异影响 加快收敛速度\nX_train = X_train/255.0\ntest = test/255.0\n","metadata":{"execution":{"iopub.status.busy":"2024-03-07T07:52:19.232290Z","iopub.execute_input":"2024-03-07T07:52:19.232647Z","iopub.status.idle":"2024-03-07T07:52:19.459306Z","shell.execute_reply.started":"2024-03-07T07:52:19.232619Z","shell.execute_reply":"2024-03-07T07:52:19.458184Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from tensorflow.keras.models import Sequential\nX_train =X_train.values.reshape(-1,28,28,1)\ntest = test.values.reshape(-1,28,28,1)\nY_train = to_categorical(Y_train,num_classes=10)\n\nX_train,X_val,Y_train,Y_val = train_test_split(X_train,Y_train,test_size=0.1,random_state=2)\n\n#cnn\nmodel = Sequential()\n\n\nmodel.add(Conv2D(filters=32,kernel_size=(5,5),padding=\"Same\",activation=\"relu\",input_shape=(28,28,1)))\nmodel.add(MaxPool2D(pool_size=(2,2),strides=(2,2)))\nmodel.add(Dropout(0.25))\n\nmodel.add(Conv2D(filters=64,kernel_size=(5,5),padding=\"Same\",activation=\"relu\"))\nmodel.add(MaxPool2D(pool_size=(2,2),strides=(2,2)))\nmodel.add(Dropout(0.25))\n\nmodel.add(Flatten())\n\nmodel.add(Dense(1000,activation=\"relu\"))\nmodel.add(Dropout(0.5))\nmodel.add(Dense(10,activation=\"softmax\"))\n\noptimizer = RMSprop(learning_rate=0.001,rho=0.9,epsilon=1e-08,decay=0.0)\nmodel.compile(optimizer=optimizer,loss=\"categorical_crossentropy\",metrics=[\"accuracy\"])\nlearning_rate_reduction =ReduceLROnPlateau(monitor=\"val_acc\",\n                                           factor=0.5,\n                                           patience=3,\n                                           verbose=1,\n                                           min_lr=0.00001\n                                           )\n\ndatagen = ImageDataGenerator(featurewise_center=False,\n                             samplewise_center=False,\n                             featurewise_std_normalization=False,\n                             samplewise_std_normalization=False,\n                             zca_whitening=False,\n                             rotation_range=10,\n                             zoom_range=0.1,\n                             width_shift_range=0.1,\n                             height_shift_range=0.1,\n                             horizontal_flip=False,\n                             vertical_flip=False\n\n                             )\n\n\ntrain_data =datagen.flow(X_train,Y_train,batch_size=batch_size)\n\nvalidata_data = (X_val,\n        Y_val\n        )\n\n\nhistory = model.fit(train_data,\n                              epochs=epochs,\n                              validation_data=validata_data,\n                              verbose=2,\n                              steps_per_epoch=None,\n                              callbacks=[learning_rate_reduction]\n                              )\n\n\n","metadata":{"execution":{"iopub.status.busy":"2024-03-07T07:52:41.094827Z","iopub.execute_input":"2024-03-07T07:52:41.095659Z","iopub.status.idle":"2024-03-07T08:01:03.699823Z","shell.execute_reply.started":"2024-03-07T07:52:41.095626Z","shell.execute_reply":"2024-03-07T08:01:03.699009Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"results = model.predict(test) \nresults = np.argmax(results,axis=1) \nresults = pd.Series(results,name=\"Label\")\nsubmission =pd.concat([pd.Series(range(1,28001),name=\"ImageId\"),results],axis=1)\nsubmission.to_csv(\"submission.csv\",index=False)\n\nmodel.save(\"mnist_cnn.h5\")","metadata":{"execution":{"iopub.status.busy":"2024-03-07T08:14:32.671969Z","iopub.execute_input":"2024-03-07T08:14:32.672744Z","iopub.status.idle":"2024-03-07T08:14:35.117352Z","shell.execute_reply.started":"2024-03-07T08:14:32.672712Z","shell.execute_reply":"2024-03-07T08:14:35.116315Z"},"trusted":true},"execution_count":null,"outputs":[]}]}