tensor로 만들어줄 경우 import torch data = [[1, 2],[3, 4]] x_data = torch.tensor(data) pos = x_data > 0 print(pos) 결과 List일 경우 data = [[1, 2],[3, 4]] pos = data > 0 print(pos) 이 연산 자체가 불가능 for문 사용해야함 data = [[1, 2],[3, 4]] pos = [[a > 0, b > 0] for a, b in data] print(pos)

논문 링크:arxiv.org/pdf/2004.07570.pdfarxiv.org/abs/2004.07570 Spatially Attentive Output Layer for Image Classification Most convolutional neural networks (CNNs) for image classification use a global average pooling (GAP) followed by a fully-connected (FC) layer for output logits. However, this spatial aggregation procedure inherently restricts the utilization of location-s arxiv.org ● introduction..