ACmix

ACmix copied to clipboard

已解决： RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.cuda.HalfTensor) should be the same

5

在position coding时，输入固定float，在yolo训练val时会自动进行半精度训练，将position()输出类型转换成input就好 position(......).to(x.dtype)

dorannn

疑问

1

请问这个投影部分为什么用三个重复的1*1操作呀，卷积的过程没太看明白，可以帮我解释一下吗？谢谢

yuwanting828

Hi！ Could you please share which tool was used to create Figure 1 in your paper ? Thank you,

qqaazxddrr


marxouse

RuntimeError: Input type (float) and bias type (c10::Half) should be the same

2

使用YOLOv7结合ACmix，出现如下报错： ``` `Traceback (most recent call last): File "/home/liu/桌面/zwx/YOLOv7-main/train.py", line 613, in train(hyp, opt, device, tb_writer) File "/home/liu/桌面/zwx/YOLOv7-main/train.py", line 415, in train results, maps, times = test.test(data_dict, File "/home/liu/桌面/zwx/YOLOv7-main/test.py", line...

Zzzz1zzz

Help！I meet a mistake when I run this project using Terminal；picture is as followed.

3

Haruhi1216

Paige-Norton

我自己测试了一下用nn.Conv2d(16, 64, 1)，输入大小是(1, 16, 224, 224)，这个参数量只有1088，但是如果用ACmix得到的参数量是8604，这差了快8倍了，但是文章说 “同时与纯卷积或self-attention相比具有最小的计算开销”，好像没有体现，这是咋回事啊？

HeiHeiCCC

![Uploading image.png…]()

17860511195

RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.cuda.HalfTensor) should be the same

Wisdom2wisdom