데이터 불러오기 from tensorflow.examples.tutorials.mnist import input_data mnist=input_data.read_data_sets("./mnist/data/",one_hot=True) 변수정의 lr = 0.01 total_epoch = 30 batch_size = 128 n_input = 28 # 한번에 입력받는 데이터 갯수 n_step = 28 # 28줄 n_hidden = 128 # 셀에서 나가는 출력의 갯수 n_class = 10 # 숫자의 종류 (0~9) w = tf.Variable(tf.random_normal([n_hidden , n_class ])) b = tf.Variable(tf.random_normal([n_class])) 모델 구성 # ..

import keras fm = keras.datasets.fashion_mnist (trainImage, trainLabel), (testImage, testLabel)= fm.load_data() import pandas as pd import numpy as np from keras.preprocessing.image import * from keras.utils import to_categorical from sklearn.model_selection import train_test_split import matplotlib.pyplot as plt import random import os # 검증데이터 분리 trainImage, valImage= train_test_split(trainImag..

from keras.datasets import mnist from keras.utils import np_utils import numpy as np import sys 데이터 셋 준비 import keras fm = keras.datasets.fashion_mnist (trainImage, trainLabel), (testImage, testLabel)= fm.load_data() xTrain=trainImage.reshape(xTrain.shape[0],28,28,1) xTrain=xTrain.astype("float64") xTrain=xTrain/255 xTest=testImage.reshape(xTest.shape[0],28,28,1).astype("float64")/255 yTrain=np_..

1. 파이썬 입출력함수 x = input("입력:" ) # input에서 여러개 입력시 : split함수로 공백 구분 x, y = input("문자열 두개 입력:").split() x, y = input("문자열 두개 입력:").split(",") # , (comma)로 문자를 구분하게 됌 >>> 문자열 두개 입력 5 10 print(x+y) >>> 510 # 5,10 을 정수로 바꿔서 인식하려면 ? map(int, input("문자열 두개 입력:").split()) # map(함수, 데이터) >>> 문자열 두개 입력:5 10 15 print(1,2,3,4, sep="") >>> 1234 print(1,2,3,4, sep"\n) >>> 1 2 3 4 print(1, end=" ") print(2, end..

데이터 다운로드 https://www.kaggle.com/c/dogs-vs-cats/data Dogs vs. Cats Create an algorithm to distinguish dogs from cats www.kaggle.com ★대용량주의 학습데이터 준비 import pandas as pd import numpy as np from keras.preprocessing.image import * from keras.utils import to_categorical from sklearn.model_selection import train_test_split import matplotlib.pyplot as plt import random import os path = "C:\\Users\\stude..

# TypeError: The added layer must be an instance of class Layer from keras.layers import * from keras.models import Sequential from keras.applications.resnet50 import ResNet50 CLASS_COUNT = 10 base_model = ResNet50( weights='imagenet', include_top=False, input_shape=(224, 224, 3), pooling='avg', ) base_model.trainable = False model = Sequential([ base_model, Dense(CLASS_COUNT, activation='softma..