jrryzh

RuntimeError: Error(s) in loading state_dict for DALLE

2

During trying to load the dalle pre-trained weights, I meet a loading error, and it seems that the current dalle model has different structures and different weight keys. I'm guessing...

The answer for EC1 is probably not correct, and I didn't work it out either, if anyone sees this i'm grateful for your help. PS: many thanks for recommending all...

pip install -r requirements.txt Collecting Markdown==3.3.7 (from -r tmp_requirements.txt (line 1)) Using cached Markdown-3.3.7-py3-none-any.whl (97 kB) Collecting MarkupSafe==2.0.1 (from -r tmp_requirements.txt (line 2)) Using cached MarkupSafe-2.0.1-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl (30 kB) Collecting matplotlib==3.4.3...

How to use LDA for topic modeling

1

Thanks for your work again! In the paper the topic modeling of OBELICS is implemented using LDA, and I am wondering what is the specific LDA model was used, what...

练习 7.1.4

1

[练习 7.1.4](https://datawhalechina.github.io/d2l-ai-solutions-manual/#/ch07/ch07?id=%e7%bb%83%e4%b9%a0-714)这里应该占用显存和计算量大的都是后面的全连接层 来自gpt3.5的答案: 在AlexNet中，主要占用显存的部分是最后两个隐藏层，它们分别需要计算大小为64004096和40964096的矩阵，这对应于164 MB的内存占用。这两个隐藏层的计算量较大，需要进行81 MFLOPs的计算，这也是计算上的主要开销。 在计算性能方面，最后两个隐藏层需要更多的计算资源，因为它们的参数数量庞大，分别有超过4000万个参数。这导致了81 MFLOPs的计算开销，相对较高。