efficientnet-lite-keras
tpu
| efficientnet-lite-keras | tpu | |
|---|---|---|
| 1 | 5 | |
| 38 | 5,180 | |
| - | 0.1% | |
| 0.0 | 7.5 | |
| about 1 year ago | 17 days ago | |
| Python | Jupyter Notebook | |
| Apache License 2.0 | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
efficientnet-lite-keras
-
[P] EfficientNet-lite in Keras (functional API).
Github Link
tpu
-
Variance in reported results on ImageNet between papers [D]
Found relevant code at https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet + all code implementations here
-
[D] What is the smallest, most capable, generative language model available now?
I'm looking for a generative-LM equivalent of an EfficientNet-Lite, for inference on devices with limited to no VRAM. I know about some popular ones like DistilGPT2. But it's been 2 years after its release. Surely, someone improved their size/performance ratio, right... right?
-
Open source - that means free to use commercially right? ... right?
tensorflow/TPU 'apache' license - https://github.com/tensorflow/tpu/commit/6b3236d0271d2f2c3b2dfdc9d233ff00c4ba21cd
-
[P] EfficientNet-lite in Keras (functional API).
According to original repository, the lite variants:
-
Why do some architectures use no bias?
I was quite surprised to see that some architectures, like efficient net (official implementation: https://github.com/tensorflow/tpu/blob/master/models/official/efficientnet/efficientnet_model.py) don't use bias (bias=False). Does anyone know why is that? Apart from the obvious benefit of reducing parameters, doesn't it make the network less capable of learning certain representations?
What are some alternatives?
segmentation_models - Segmentation models with pretrained backbones. Keras and TensorFlow Keras.
mask-rcnn - Mask-RCNN training and prediction in MATLAB for Instance Segmentation
ssd_keras - A Keras port of Single Shot MultiBox Detector
Mask_RCNN - Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
pytorch2keras - PyTorch to Keras model convertor
Deep-Residual-Learning-for-Image-Recognition - Implementation of https://arxiv.org/pdf/1512.03385.pdf
GLOM-TensorFlow - An attempt at the implementation of GLOM, Geoffrey Hinton's paper for emergent part-whole hierarchies from data
PINTO_model_zoo - A repository for storing models that have been inter-converted between various frameworks. Supported frameworks are TensorFlow, PyTorch, ONNX, OpenVINO, TFJS, TFTRT, TensorFlowLite (Float32/16/INT8), EdgeTPU, CoreML.
nobuco - Pytorch to Keras/Tensorflow conversion made intuitive
LTC-SUM - Implementation of LTC-SUM: Lightweight Client-driven Personalized Video Summarization Framework Using 2D CNN