๐Ÿ“ AI & Bigdata

๐Ÿ“ AI & Bigdata/AI & ML & DL

[DL] CNN-Initializing Weights for the Convolutional and FC Layers

DNN์—์„œ Convolutional ๋ฐ FC Layers์— ๋Œ€ํ•œ ๊ฐ€์ค‘์น˜(Weight)๊ฐ€ ํŠน์ • ๋ฐฉ์‹์œผ๋กœ ์ดˆ๊ธฐํ™”(Initializing). ResNet ๋„คํŠธ์›Œํฌ(https://github.com/pytorch/vision/blob/master/torchvision/models/resnet.py) ๊ฐ€์ค‘์น˜๋ฅผ ์ดˆ๊ธฐํ™”ํ•˜๊ธฐ ์œ„ํ•œ PyTorch ์ฝ”๋“œ n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels m.weight.data.normal_(0, math.sqrt(2. / n)) ๊ฐ€์ค‘์น˜๋Š” ํ‰๊ท ์ด 0์ธ ์ •๊ทœ ๋ถ„ํฌ์™€ ํ•„ํ„ฐ ์ปค๋„ ์ฐจ์›์˜ ํ•จ์ˆ˜์ธ ํ‘œ์ค€ ํŽธ์ฐจ๋ฅผ ์‚ฌ์šฉํ•˜์—ฌ ์ดˆ๊ธฐํ™”๋ฉ๋‹ˆ๋‹ค. ์ด๊ฒƒ์€ ๋„คํŠธ์›Œํฌ ๊ณ„์ธต์˜ ์ถœ๋ ฅ ๋ถ„์‚ฐ์ด ์‚ฌ๋ผ์ง€๊ฑฐ๋‚˜ ํญ๋ฐœํ•˜๋Š” ๊ฒƒ, ์ฆ‰ ๋งค์šฐ ์ปค์ง€๋Š” ๋Œ€์‹  ํ•ฉ๋ฆฌ์ ์ธ ํ•œ๊ณ„ ๋‚ด..

๐Ÿ“ AI & Bigdata/Raspberry Pi

[๋ผ์ฆˆ๋ฒ ๋ฆฌํŒŒ์ด] ๋ผ์ฆˆ๋ฒ ๋ฆฌํŒŒ์ด ์ดํ•ดํ•˜๊ธฐ

๋ผ์ฆˆ๋น„์•ˆ ์„ค์น˜ Operating system images – Raspberry Pi From industries large and small, to the kitchen table tinkerer, to the classroom coder, we make computing accessible and affordable for everybody. www.raspberrypi.com ๋งˆ์ดํฌ๋กœ SD ์นด๋“œ์— ์ด๋ฏธ์ง€ ์˜ฎ๊ธฐ๊ธฐ USB ํฌ๋ฉง Flash OS images to SD cards & USB drives, safely and easily. ์„ค์น˜ balena - The complete IoT fleet management platform Infrastructure and tools to develop, depl..

๐Ÿ“ AI & Bigdata/Raspberry Pi

[๋ผ์ฆˆ๋ฒ ๋ฆฌํŒŒ์ด] ์ง์ ‘ ์“ด ์ˆซ์ž๋ฅผ ์ธ์‹ํ•˜๋Š” ๋”ฅ๋Ÿฌ๋‹ ๊ธฐ์ˆ : 2. ์†๊ธ€์”จ ์ธ์‹ test

์‚ฌ์ง„์€ RGB๋กœ nois๊ฐ€ ์กด์žฌํ•œ๋‹ค. ์ด๋Š” ๋ฐฐ๊ฒฝ๊ณผ ๊ธ€์”จ๋ฅผ ๋ถ„๋ฆฌํ•˜๊ธฐ ์œ„ํ•ด ํ•„ํ„ฐ๋ง ์ž‘์—…์„ ๊ฑฐ์นœ๋‹ค. width: 523 pixels height: 184 pixels channels: 3 1. hsv(hue, saturation, value): value๋ฅผ ํ™•์ธํ•ด ๋ณด์•˜๋‹ค. hsv transform - value = gray image hue: ์ƒ‰์ƒ, saturation: ์ฑ„๋„, value: ๋ช…๋„ hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV) hue, saturation, value = cv2.split(hsv) plt.imshow(value) 2. kernel to use for morphological operations # filter: boundary๋ฅผ ์ฐพ์•„๋‚ด๋Š” ๊ฒƒ kern..

๐Ÿ“ AI & Bigdata/Raspberry Pi

[๋ผ์ฆˆ๋ฒ ๋ฆฌํŒŒ์ด] Firebase, NoSQL Sture์ด๋ž€

๋ณดํ˜ธ๋˜์–ด ์žˆ๋Š” ๊ธ€์ž…๋‹ˆ๋‹ค.

SOIT
'๐Ÿ“ AI & Bigdata' ์นดํ…Œ๊ณ ๋ฆฌ์˜ ๊ธ€ ๋ชฉ๋ก (5 Page)