Computer Vision8 MnasNet 쉬운 논문 리뷰 MnasNet [Reference] 논문 링크: MnasNet: Platform-Aware Neural Architecture Search for Mobile github: https://github.com/tensorflow/tpu/tree/master/models/official/mnasnet 2019년 4월 (Arxiv) Google Inc. Mingxing Tan, Bo Chen, Ruoming Pang, Vijay Vasudevan, Mark Sandler, Andrew Howard, Quoc V. Le blog: https://m.blog.naver.com/PostView.naver?isHttpsRedirect=true&blogId=za_bc&logNo=221570652712 [TODOS] P.. 2022. 8. 1. ShuffleNet 쉬운 논문 리뷰/구현 ShuffleNet [reference] 논문 링크: ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices 2017년 7월 Xiangyu Zhang, Xinyu Zhou, Mengxiao Lin, Jian Sun Blog: https://hongl.tistory.com/38 목차 [TOC] 용어 Depthwise Convolution: 기존 Standard Convolution과 달리 각 채널별로 Convolution 연산 진행 / 링크의 1-1, 1-2 참고 Pointwise Convolution: 1x1 Convolution 연산. 연산방식이 Fully Connected Layer와 유사하여, Computa.. 2022. 7. 20. Squeeze-Excitation Network 쉬운 논문 리뷰/구현 Squeeze-and-Excitation Block (SE Block) [Reference] 논문 링크: Squeeze-and-Excitation Networks 2018년 (Arxiv) Jie Hu, Li Shen, Samuel Albanie, Gang Sun, Enhua Wu ILSVRC 2017 1st Blog: https://inhovation97.tistory.com/48 목차 [TOC] 요약 Squeeze Operation: 전체정보를 요약 Excitation Operation: Squeeze Operation을 통해 계산된 Feature map의 중요도를 각 Channel에 곱해줌 Squeeze, Excitation Operation을 통해 Representation power가 높은 Fea.. 2022. 7. 19. MobileNet V2 쉬운 논문 리뷰/구현 MobileNet v2 [Reference] 논문 링크: MobileNets: Inverted Residuals and Linear Bottlenecks Github: https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/README.md 2018년 1월(Arxiv) Google Inc. Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen Blog: https://greeksharifa.github.io/computer%20vision/2022/02/10/MobileNetV2/ 목차 [TOC] 요약 Inverted Residual 구.. 2022. 7. 7. 이전 1 2 다음
