FcaNet
FcaNet copied to clipboard
cfzd
FcaNet: Frequency Channel Attention Networks
Hi, 请问，如果通道不分组，是不是用以下代码就可以？ > def get_dct_filter(self, tile_size_x, tile_size_y, mapper_x, mapper_y, channel): > dct_filter = torch.zeros(channel, tile_size_x, tile_size_y) > for i in range(channel): > for _, (u_x, v_y) in enumerate(zip(mapper_x, mapper_y)): >...
输入要经过下采样和上采样，输入图片也就需要缩小和放大好几次，那我是不是要在__init__就把input size传进去，有什么办法能实时获取输入大小吗？ 我有尝试在forward函数里获取x的大小，但后面训练很慢，我就意识到dct应该需要在搭建网络时预生成。
Regarding the setting of c2wh = dict([(64,56), (128,28), (256,14) ,(512,7)]) in the fcanet.py file.
In my model, the output feature map shape is (512, 16, 16), but I am worried that the **adaptive_avg_pool2d()** operation in the **layer.py** file will cause information loss. So I...
您好，非常感谢您的杰出工作，我使用了您的代码和模型在imagenet上FcaNet50得到的验证集准确率为78.39，请问是正常的吗，环境是Ubuntu20.04，cuda11.6，pytorch1.10，4卡3090，期待您的回复
How can I set dct_h and dct_w if i want to add FCA layer into another model. My feature maps for the layer I want to inset Fca layer are...
