2020 기초인공지능 플젝3
- 최초 등록일
- 2022.11.07
- 최종 저작일
- 2020.10
- 21페이지/
어도비 PDF
- 가격 3,500원
![할인쿠폰받기](/images/v4/document/ico_det_coupon.gif)
소개글
"2020 기초인공지능 플젝3"에 대한 내용입니다.
목차
1. Question 1: AlexNet with CIFAR-10
2. Question 2: Transfer Learning
3. Conclusion
본문내용
Question 1: AlexNet with CIFAR-10
We will use the structure of AlexNet and adjust the parameter to apply CIFAR-10 dataset.
(a)
The project was implemented on Google Colab with tensorflow 2.4.0.
Several training setup is done for this question.
- Data pre-processing / Data Augmentation
- # load train and test dataset
- def load_dataset():
- # load dataset
- (x_train, y_train), (x_test, y_test) = cifar10.load_data()
-
- """
- # split into train, validation, test dataset
- x_valid, y_valid = x_train[:5000], y_train[:5000]
- x_train, y_train = x_train[5000:], y_train[5000:]
- """
-
- # one hot encode target values
- y_train = to_categorical(y_train)
- y_test = to_categorical(y_test)
-
- return x_train, y_train, x_test, y_test
▶ First, we load the dataset and convert label data into one-hot-encoding values.
# scale pixels
def prep_pixels(train, test):
# convert from integers to floats
train_norm = train.astype('float32')
test_norm = test.astype('float32')
# normalize to range 0-1
train_norm = train_norm / 255.0
test_norm = test_norm / 255.0
참고 자료
없음