본문 바로가기

First step89

[TIL]21.07.12Keras 1일차 #예제 from tensorflow.keras.models import Sequential from tensorflow.keras.layers import Dense import numpy as np import tensorflow as tf seed=0 np.random.seed(3) tf.random.set_seed(3) Data_set=np.loadtxt("/content/drive/MyDrive/Colab Notebooks/dataset/ThoraricSurgery.csv",delimiter=",") X=Data_set[:,0:17] Y=Data_set[:,17] model= Sequential() model.add(Dense(30, input_dim=17,activation='sigmoid')).. 2021. 7. 12.
[TIL] 21.07.09퍼셉트론,Relu ,실습 #저번시간에 실습한 코드를 ver1 에서 ver2로 변환해보기 import tensorflow as tf import numpy as np from datetime import datetime %load_ext tensorboard %tensorboard --logdir=logs/mylogs learning_rate=0.01 tf.random.set_seed(0) np.random.seed(0) x_data=np.array([[0,0],[0,1],[1,0],[1,1]],dtype=np.float32) y_data=np.array([[0],[1],[1],[0]], dtype=np.float32) w1=tf.Variable(tf.random.normal([2,2]), name='weight1') b1=tf... 2021. 7. 9.
[TIL]21.07.08로지스틱 회귀2 , 퍼셉트론 import tensorflow.compat.v1 as tf tf.disable_v2_behavior() import numpy as np seed=0 np.random.seed(seed) tf.set_random_seed(seed) x_data = np.array([[2,3],[4,3],[6,4],[8,6],[10,7],[12,8],[14,9]]) y_data = np.array([0,0,0,1,1,1,1]).reshape(7,1) X=tf.placeholder(tf.float64 , shape=[None,2]) Y=tf.placeholder(tf.float64 , shape=[None,1]) #기울기 a 와 bias b를 의미 a는a1,a2 로 [2,1]형태를 가짐 a=tf.Variable(tf.ra.. 2021. 7. 8.
[TIL] 21.07.07로지스틱 회귀 #로지스틱 회귀 import tensorflow.compat.v1 as tf tf.disable_v2_behavior() import numpy as np data=[[2,0],[4,0],[6,0],[8,1],[10,1],[12,1],[14,1]] x_data=[x_row[0] for x_row in data] y_data=[y_row[0] for y_row in data] #임의의 값 a,b a= tf.Variable(tf.random_normal([1], dtype=tf.float64,seed=0)) b= tf.Variable(tf.random_normal([1], dtype=tf.float64,seed=0)) #시그모이드 함수의 방정식을 세운다 y= 1/(1+ np.e**-(a*x_data)+b) .. 2021. 7. 7.