zhenhao Shang

Results 4 comments of zhenhao Shang

报错：RuntimeError: The size of tensor a (80) must match the size of tensor b (44) at non-singleton dimension 3，这个维度对不上要改哪里呢

会改了吗 蹲

报错：RuntimeError: The size of tensor a (80) must match the size of tensor b (44) at non-singleton dimension 3，这个维度对不上要改哪里呢

嗨嗨嗨兄弟我找到错了，44应该是你用的数据集的class数量吧 在teacher.py里面，teacher模型在初始化的时候根本没用到nc参数，所以默认直接用的80，所以前向传播出来的值的那个维度就是80。所以把teacher.py里的初始化按照train_distill里面初始化student模型的方法重写一遍就好了

On the small model, the actual GPU memory usage of Mamba2 is much higher than that of Mamba1.

> > huh there's no requirement d_state / head_dim % 8 == 0 there's d_model / head_dim % 8 == 0 you can try the dimensions similar to the language...

Some questions about different implementations of the SSD algorithm

OK I understand, thank you