From 1ea65f0ffa3e4f600e72a20bbe34069fb648b61c Mon Sep 17 00:00:00 2001 From: rick7211728 Date: Tue, 17 Mar 2020 18:59:39 -0700 Subject: [PATCH] Removing non-using stuff --- CNN_test_0312.ipynb | 264 -------------------------------------------- 1 file changed, 264 deletions(-) delete mode 100644 CNN_test_0312.ipynb diff --git a/CNN_test_0312.ipynb b/CNN_test_0312.ipynb deleted file mode 100644 index 1195cc3..0000000 --- a/CNN_test_0312.ipynb +++ /dev/null @@ -1,264 +0,0 @@ -{ - "cells": [ - { - "cell_type": "code", - "execution_count": 1, - "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "Using TensorFlow backend.\n" - ] - } - ], - "source": [ - "import numpy as np\n", - "import pandas as pd\n", - "import matplotlib.pyplot as plt\n", - "\n", - "from sklearn.model_selection import train_test_split\n", - "\n", - "from keras.datasets import mnist\n", - "from keras.preprocessing.image import ImageDataGenerator\n", - "from keras.callbacks import ReduceLROnPlateau\n", - "\n", - "from keras.utils import to_categorical\n", - "from keras import layers\n", - "from keras import models\n", - "from keras import optimizers" - ] - }, - { - "cell_type": "code", - "execution_count": 2, - "metadata": {}, - "outputs": [], - "source": [ - "import Image_Preprocess\n", - "BCC_train=Image_Preprocess.BCC_train()\n", - "BCC_test=Image_Preprocess.BCC_test()\n", - "FCC_train=Image_Preprocess.FCC_train()\n", - "FCC_test=Image_Preprocess.FCC_test()" - ] - }, - { - "cell_type": "code", - "execution_count": 6, - "metadata": {}, - "outputs": [], - "source": [ - "FCC_test=np.array(FCC_test)\n", - "BCC_test=np.array(BCC_test)\n", - "FCC_train=np.array(FCC_train)\n", - "BCC_train=np.array(BCC_train)\n" - ] - }, - { - "cell_type": "code", - "execution_count": 7, - "metadata": {}, - "outputs": [], - "source": [ - "# making training data and test data\n", - "\n", - "train_data=np.append(FCC_train,BCC_train,axis=0)\n", - "test_data=np.append(FCC_test,BCC_test,axis=0)\n", - "\n", - "# making train_label\n", - "train_label=[]\n", - "for i in range(FCC_train.shape[0]):\n", - " train_label.append('FCC')\n", - "for i in range(BCC_train.shape[0]):\n", - " train_label.append('BCC')\n", - " \n", - "test_label=[]\n", - "for i in range(FCC_test.shape[0]):\n", - " test_label.append('FCC')\n", - "for i in range(BCC_test.shape[0]):\n", - " test_label.append('BCC')\n", - " \n", - "train_label=np.array(train_label)\n", - "test_label=np.array(test_label)\n" - ] - }, - { - "cell_type": "code", - "execution_count": 10, - "metadata": {}, - "outputs": [], - "source": [ - "# reshaping data\n", - "train_data = train_data.reshape(-1,288,432,1).astype('float32')/255\n", - "test_data = test_data.reshape(-1,288,432,1).astype('float32')/255" - ] - }, - { - "cell_type": "code", - "execution_count": 11, - "metadata": {}, - "outputs": [], - "source": [ - "# one hot encoder\n", - "from sklearn.preprocessing import LabelEncoder\n", - "\n", - "label_encoder = LabelEncoder()\n", - "train_label_10 = label_encoder.fit_transform(train_label)\n", - "test_label_10 = label_encoder.fit_transform(test_label)\n", - "train_label = to_categorical(train_label_10)\n", - "test_label = to_categorical(test_label_10)" - ] - }, - { - "cell_type": "code", - "execution_count": 12, - "metadata": {}, - "outputs": [], - "source": [ - "# cross validation\n", - "train_data,val_data,train_label,val_label=train_test_split(train_data,train_label,test_size=0.25,random_state=13)" - ] - }, - { - "cell_type": "code", - "execution_count": 13, - "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/opt/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:6: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(32, (3, 3), input_shape=(288, 432,..., activation=\"relu\")`\n", - " \n", - "/opt/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:8: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(64, (3, 3), input_shape=(288, 432,..., activation=\"relu\")`\n", - " \n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Model: \"sequential_2\"\n", - "_________________________________________________________________\n", - "Layer (type) Output Shape Param # \n", - "=================================================================\n", - "conv2d_3 (Conv2D) (None, 286, 430, 32) 320 \n", - "_________________________________________________________________\n", - "max_pooling2d_3 (MaxPooling2 (None, 143, 215, 32) 0 \n", - "_________________________________________________________________\n", - "conv2d_4 (Conv2D) (None, 141, 213, 64) 18496 \n", - "_________________________________________________________________\n", - "max_pooling2d_4 (MaxPooling2 (None, 70, 106, 64) 0 \n", - "_________________________________________________________________\n", - "flatten_2 (Flatten) (None, 474880) 0 \n", - "_________________________________________________________________\n", - "dense_3 (Dense) (None, 64) 30392384 \n", - "_________________________________________________________________\n", - "dropout_2 (Dropout) (None, 64) 0 \n", - "_________________________________________________________________\n", - "dense_4 (Dense) (None, 2) 130 \n", - "=================================================================\n", - "Total params: 30,411,330\n", - "Trainable params: 30,411,330\n", - "Non-trainable params: 0\n", - "_________________________________________________________________\n" - ] - } - ], - "source": [ - "from keras.models import Sequential\n", - "from keras.layers import Convolution2D,MaxPool2D,Flatten,Dense,Dropout\n", - "from keras.callbacks import TensorBoard\n", - "\n", - "model=Sequential([\n", - " Convolution2D(32,3,3,input_shape=(288,432,1),activation='relu'),\n", - " MaxPool2D(pool_size=(2,2)),\n", - " Convolution2D(64,3,3,input_shape=(288,432,1),activation='relu'),\n", - " MaxPool2D(pool_size=(2,2)),\n", - " Flatten(),\n", - " Dense(64,activation='relu'),\n", - " Dropout(0.5),\n", - " Dense(2,activation='sigmoid')\n", - "])\n", - "\n", - "model.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])\n", - "model.summary()\n", - "\n", - "\n" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 1/12\n", - "6/5 [================================] - 19s 3s/step - loss: 4.1112 - accuracy: 0.4972\n", - "Epoch 2/12\n", - "6/5 [================================] - 15s 3s/step - loss: 0.9155 - accuracy: 0.4916\n", - "Epoch 3/12\n", - "2/5 [=========>....................] - ETA: 10s - loss: 0.6685 - accuracy: 0.5625" - ] - } - ], - "source": [ - "# fitting model, 測試1\n", - "datagen = ImageDataGenerator(\n", - " featurewise_center=True,\n", - " featurewise_std_normalization=True,\n", - " rotation_range=20,\n", - " width_shift_range=0.2,\n", - " height_shift_range=0.2,\n", - " horizontal_flip=True)\n", - "\n", - "# compute quantities required for featurewise normalization\n", - "# (std, mean, and principal components if ZCA whitening is applied)\n", - "datagen.fit(train_data)\n", - "\n", - "# fits the model on batches with real-time data augmentation:\n", - "model.fit_generator(datagen.flow(train_data, train_label, batch_size=32),\n", - " steps_per_epoch=len(train_data) / 32, epochs=12)" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - } - ], - "metadata": { - "kernelspec": { - "display_name": "Python 3", - "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": "3.7.4" - } - }, - "nbformat": 4, - "nbformat_minor": 4 -}