Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
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)
| Date | Stars |
|---|---|
| 2026-07-31 | 944 |
| 2026-08-01 | 944 |
| 2026-08-02 | 944 |
| 2026-08-03 | 945 |
| 2026-08-05 | 946 |
| 2026-08-06 | 946 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<!-- markdownlint-disable first-line-h1 -->
<!-- markdownlint-disable html -->
<div align="center">
<h1>
calflops: a FLOPs and Params calculate tool for neural networks
</h1>
</div>
[](https://pypi.org/project/calflops/)
[](https://github.com/MrYxJ/calculate-flops.pytorch/blob/main/LICENSE)
<h4 align="center">
<p>
<b>English</b> |
<a href="https://github.com/MrYxJ/calculate-flops.pytorch/blob/main/README_CN.md">中文</a>
<p>
</h4>
# Introduction
This tool(calflops) is designed to compute the theoretical amount of FLOPs(floating-point operations)、MACs(multiply-add operations) and Parameters in all various neural networks, such as Linear、 CNN、 RNN、 GCN、**Transformer(Bert、LlaMA etc Large Language Model)**，even including **any custom models** via ```torch.nn.function.*``` as long as based on the Pytorch implementation. Meanwhile this tool supports the printing of FLOPS, Parameter calculation value and proportion of each submodule of the model, it is convient for users to understand the performance consumption of each part of the model.
Latest news, calflops has launched a tool on Huggingface Space, which is more convenient for computing FLOPS in the model of 🤗Huggingface Platform. Welcome to use it:https://huggingface.co/spaces/MrYXJ/calculate-model-flops
<img width="1480" alt="截屏2023-09-13 23 25 05" src="https://github.com/MrYxJ/calculate-flops.pytorch/assets/21152077/75b77665-9c72-49a9-a86c-0114da1945fd">
For LLM, this is probably the easiest tool to calculate FLOPs and it is very convenient for **huggingface** platform models. You can use ```calflops.calculate_flops_hf(model_name)``` by `model_name` which in [huggingface models](https://huggingface.co/models) to calculate model FLOPs without downloading entire model weights locally.Notice this method requires the model to support the empty model being created for model inference in meta device.
``` python
from calflops import calculate_flops_hf
model_name = "meta-llama/Llama-2-7b"
access_token = "..." # your application token for using llama2
flops, macs, params = calculate_flops_hf(model_name=model_name, access_token=access_token) # default input shape: (1, 128)
print("%s FLOPs:%s MACs:%s Params:%s \n" %(model_name, flops, macs, params))
```
If model can't inference in meta device, you just need assign llm corresponding tokenizer to the parameter: ```transformers_tokenizer``` to pass in funcional of ```calflops.calculate_flops()```, and it will automatically help you build the model input data whose size is input_shape. Alternatively, you also can pass in the input data of models which need multi data as input that you have constructed.
In addition, the implementation process of this package inspired by [ptflops](https://github.com/sovrasov/flops-counter.pytorch)、[deepspeed](https://github.com/microsoft/DeepSpeed/tree/master/deepspeed)、[hf accelerate](https://github.com/huggingface/accelerate) libraries, Thanks for their great efforts, they are both very good work. Meanwhile this package also improves some aspects to calculate FLOPs based on them.
## How to install
### Install the latest version
#### From PyPI:
```python
pip install --upgrade calflops
```
And you also can download latest `calflops-*-py3-none-any.whl` files from https://pypi.org/project/calflops/
```python
pip install calflops-*-py3-none-any.whl
```
## How to use calflops
### Example
### CNN Model
If model has only one input, you just need set the model input size by parameter ```input_shape``` , it can automatically generate random model input to complete the calculation:
```python
from calflops import calculate_flops
from torchvision import models
model = models.alexnet()
batch_size = 1
input_shape = (batch_size, 3, 224, 224)
Excerpt of 30,892 characters
Read on GitHub
coder
43
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:e87dd6353d781ae7, topic:pytorch
matched fp:e87dd6353d781ae7, topic:large-language-models