Introduce kimm
: a collection of image models, blocks and layers written in Keras3
#19718
james77777778
started this conversation in
Show and tell
Replies: 1 comment 4 replies
-
Thanks for your great work.
However, model.predict(x) throws
Thanks |
Beta Was this translation helpful? Give feedback.
4 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Repository: https://github.com/james77777778/keras-image-models
If you want to try a different model that isn't available in Keras, you can explore this library.
Feel free to contact me if you encounter any issues or have ideas.
Introduction
Keras Image Models (
kimm
) aims to provide SOTA models with pretrained weights in a user-friendly manner.Features:
.tflite
and.onnx
.Usage
Quickstart
An end-to-end example: fine-tuning an image classification model on a cats vs. dogs dataset
Using
kimm.models.EfficientNetLiteB0
:Reference: Transfer learning & fine-tuning (keras.io)
Grad-CAM
Using
kimm.models.MobileViTS
:Reference: Grad-CAM class activation visualization (keras.io)
Model Zoo
timm
kimm.models.ConvMixer*
timm
kimm.models.ConvNeXt*
timm
kimm.models.DenseNet*
timm
kimm.models.EfficientNet*
timm
kimm.models.EfficientNetLite*
timm
kimm.models.EfficientNetV2*
timm
kimm.models.GhostNet*
timm
kimm.models.GhostNetV2*
timm
kimm.models.HGNet*
timm
kimm.models.HGNetV2*
timm
kimm.models.InceptionNeXt*
timm
kimm.models.InceptionV3
timm
kimm.models.LCNet*
timm
kimm.models.MobileNetV2*
timm
kimm.models.MobileNetV3*
timm
kimm.models.MobileOne*
timm
kimm.models.MobileViT*
timm
kimm.models.MobileViTV2*
timm
kimm.models.RegNet*
timm
kimm.models.RepVGG*
timm
kimm.models.ResNet*
timm
kimm.models.TinyNet*
timm
kimm.models.VGG*
timm
kimm.models.VisionTransformer*
keras
kimm.models.Xception
Beta Was this translation helpful? Give feedback.
All reactions