Open LuletterSoul opened 11 months ago
I'm pleased that you're following our work, in mobilenetv2 we train with a quantization bit width of 3bit-8bit, unlike the 2bit-8bit of the resnet series, due to the severe weight competition problem caused by separable convolution.
@HanLeI187
I'm pleased that you're following our work, in mobilenetv2 we train with a quantization bit width of 3bit-8bit, unlike the 2bit-8bit of the resnet series, due to the severe weight competition problem caused by separable convolution.
Do you mean that I only need to change the bit range of w_bit_list and a_bit_list to [3, 4, 5, 6, 7, 8] ?
Yes, it is.
@HanLeI187
很高兴您关注我们的工作,在mobilenetv2中我们采用3bit-8bit的量化位宽进行训练,与resnet系列的2bit-8bit不同,这是由于可分离卷积引起的严重的权重竞争问题。
你的意思是我只需要将 w_bit_list 和 a_bit_list 的位范围改为 [3, 4, 5, 6, 7, 8] 吗?
估计您跑通了所以没回复啊哈哈哈
I changed the "arch" in the config to "mobilenetv2" and the number of cards to 8. After training for 79 epochs, the accuracy is only around 40+%.
What mistakes did I make?