###### tags: `Lecture5` # question 1.不太懂第36頁,為什麼從32*32*3變成28*28*6又變24*24*10? 2.關於zero-padding,為什麼要讓輸入跟convolution layer的輸出的長寬高一樣?輸入跟輸出不一樣會有甚麼影響? 3.在pooling layer的最後我們看到現在喜歡用larger stride in CONV layer取代pooling layer,那在什麼狀況下使用pooling layer會比較好呢? 4.同一組圖片旋轉會不會影響到他的結果?
×
Sign in
Email
Password
Forgot password
or
By clicking below, you agree to our
terms of service
.
Sign in via Facebook
Sign in via Twitter
Sign in via GitHub
Sign in via Dropbox
Sign in with Wallet
Wallet (
)
Connect another wallet
New to HackMD?
Sign up