Image classification models for Keras
Project description
Large-scale image classification networks
Several large-scale image classification models on Keras (with MXNet backend), trained on the ImageNet-1k dataset.
Installation
To install, use:
pip install kerascv mxnet>=1.2.1
To enable different hardware supports such as GPUs, check out MXNet variants. For example, you can install with CUDA-9.2 supported MXNet:
pip install kerascv mxnet-cu92>=1.2.1
After installation change the value of the field image_data_format
to channels_first
in the file ~/.keras/keras.json
.
Usage
Example of using the pretrained ResNet-18 model:
from kerascv.model_provider import get_model as kecv_get_model
net = kecv_get_model("resnet18", pretrained=True)
Project details
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
kerascv-0.0.3.tar.gz
(28.7 kB
view hashes)
Built Distribution
Close
Hashes for kerascv-0.0.3-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 62865e8a8d6ddc234ac73a0e1c4c58a406623a6bab2e2a8bf9c9713f64c94742 |
|
MD5 | 263028208ed9784c483b3c500d11192f |
|
BLAKE2b-256 | 42c08bf1bc70906b2b3c9f1a416e0ec34428e3fddf3ef4cd7caf8927f4b2dbe7 |