A Python library for model FLOPs and throughput benchmarking
Project description
from modelinfo import ModelProfiler
from torchvision.models import resnet18
model = resnet18()
input_size = (1, 3, 224, 224)
profiler = ModelProfiler(model, input_size)
profiler.summary()
profiler.flops_memory(precision='fp16')
profiler.benchmark(precision='fp16', training=True)
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
modelinfo-0.0.1.tar.gz
(3.4 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file modelinfo-0.0.1.tar.gz.
File metadata
- Download URL: modelinfo-0.0.1.tar.gz
- Upload date:
- Size: 3.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.11.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
6a44c81a465465251f52965a56d34ef3ed195e934f3cefee1cfcc96773e6e9de
|
|
| MD5 |
f71b65b22d9ce19514b016d11f9a448c
|
|
| BLAKE2b-256 |
981e68dde5733373a8588117c24d31fe6cd0fc0eb5c730b07c9cab077d96ec40
|
File details
Details for the file modelinfo-0.0.1-py3-none-any.whl.
File metadata
- Download URL: modelinfo-0.0.1-py3-none-any.whl
- Upload date:
- Size: 3.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.11.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e26c1c0907234e7f224dce8fa97e5255177830928eb48725b9e65b1582ba0749
|
|
| MD5 |
9448aaf086b41523bc8db95db3bd4dbe
|
|
| BLAKE2b-256 |
7ccdbe86b21496371939be30276f365da28df5500229ae932583cb7c2c191c84
|
