MrYxJ calculate-flops.pytorch issues

MrYxJ / calculate-flops.pytorch

The calflops is designed to calculate FLOPs、MACs and Parameters in all various neural networks, such as Linear、 CNN、 RNN、 GCN、Transformer(Bert、LlaMA etc Large Language Model)

https://pypi.org/project/calflops/

MIT License

390 stars 14 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

MACs for ConvTranspose2d

#33 qiuzidian opened 8 hours ago
0
Formatting and docstring fixes

#32 bhavika closed 1 week ago
0
gated models do not work

#31 mohbay opened 1 week ago
0
How to calculate the FLOPs when the model has some freezed variables, or using LoRA?

#30 Ledzy opened 1 week ago
0
On the calculation of FLOPs for SAM/MobileSAM

#29 BeliverK opened 2 weeks ago
0
评价Gemma的时候参数量为0

#28 JackeyWang777 closed 2 weeks ago
1
关于百分比的问题

#27 lzd-1230 closed 4 weeks ago
2
你好，比如llama这些LLM模型，我看统计的结果好像没有包括attention矩阵的Q@K.T那部分计算量。

#26 ywh187 opened 4 weeks ago
2
Is it considering output length of transformer models?

#25 liut89 closed 4 weeks ago
1
flops percent wrong

#24 Lix1993 closed 4 weeks ago
1
Can this support StableDiffusion？

#23 sunzhe09 opened 1 month ago
0
[Bug] Upsample flops not being assigned after calculation

#22 Ridhamz-nd opened 1 month ago
0
Add sentence-transformers

#21 bhavika closed 1 month ago
0
What is the difference between the 'forward' mode and the 'generate' mode?

#20 AboveParadise opened 2 months ago
1
Please make a CITATION file

#19 Livioni closed 4 weeks ago
1
Library `gpt-neox` is not supported yet

#18 melisa-writer closed 4 weeks ago
1
How to calculate model with more than one input?

#17 yuanzhi-zhu opened 4 months ago
0
Why the unit of fwd FLOPs is FLOPS?

#16 Fibonacci43 opened 4 months ago
0
allow for non-tensor kwargs in calculate_flops

#15 vzantedeschi closed 4 months ago
1
error with the example code

#14 tranlm closed 4 months ago
1
about 3D object detection

#13 ouyangziyao opened 7 months ago
0
Library `diffusers` is not supported yet

#12 XianweiC opened 7 months ago
2
Cannot calculate EfficientNet

#11 QingyuLiu closed 4 weeks ago
1
访存量的计算

#10 Amanda-Barbara closed 5 months ago
2
why I can not find transformers.modeling_outputs,Can you tell me your vision of transformers

#9 kingofengineer closed 8 months ago
1
why seq_len of llm is 128?

#8 LinglingGreat closed 8 months ago
1
Why is the proportion of FLOPs in each submodule always half of the proportion of MACS

#7 wulinunu opened 8 months ago
1
ImportError: cannot import name 'is_timm_available' from 'accelerate.utils'

#6 jiabao-wang closed 7 months ago
2
This project can be used on large visual language models?

#5 jiabao-wang closed 7 months ago
4
Support sparse model calculation

#4 pingzhili closed 9 months ago
3
给的示例无法运行

#3 Arcmoon-Hu closed 9 months ago
1
ImportError at 'from calflops import calculate_flops': cannot import name 'is_timm_available' from 'accelerate.utils'

#2 biplob1ly closed 9 months ago
3
大模型微调

#1 Pobby321 closed 9 months ago
1