Turtle Developer

New 포스트

• 

  python TypeError: can't convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first. 오류해결방법 Pytorch(파이토치)를 사용하다보면, TypeError: can't convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first. 와 같은 오류 문구가 발생하는 경우가 있습니다. 저와 같은 경우는 아래와 같이 model을 학습하여 모델의 output tensor를 이용하여 작업을 할때 이런 오류가 발생했는데요, 해당 오류가 발생하는 이유는 cuda device (gpu)에 할당되어있는 tensor 객체를 numpy 형태로 변경하려고 할때 발생하는 오류라고 합니다. 위의 코드 같은 경우는 model의 output인 activation에 대해서 np.concatenate() 함수를 사용..

• 

  논문리뷰 [논문리뷰] Group Knowledge Transfer: Federated Learning of Large CNNs at the Edge 논문 링크 : https://proceedings.neurips.cc/paper/2020/hash/a1d4c20b182ad7137ab3606f0e3fc8a4-Abstract.html Group Knowledge Transfer: Federated Learning of Large CNNs at the Edge Requests for name changes in the electronic proceedings will be accepted with no questions asked. However name changes may cause bibliographic tracking issues. Authors are asked to consider this carefully and discuss it with ..

• 

  논문리뷰 [논문리뷰] Semantically Coherent Out-of-Distribution Detection 논문 링크 : https://arxiv.org/abs/2108.11941 Semantically Coherent Out-of-Distribution Detection Current out-of-distribution (OOD) detection benchmarks are commonly built by defining one dataset as in-distribution (ID) and all others as OOD. However, these benchmarks unfortunately introduce some unwanted and impractical goals, e.g., to perfectly disti arxiv.org 해당 논문은 기존의 Out-of-Distribution Detecti..