pytorch2keras
ModelZoo.pytorch
pytorch2keras | ModelZoo.pytorch | |
---|---|---|
2 | 1 | |
846 | 48 | |
- | - | |
0.0 | 0.0 | |
over 1 year ago | over 3 years ago | |
Python | Python | |
MIT License | MIT License |
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.
pytorch2keras
-
Help Needed: Converting PlantNet-300k Pretrained Model Weights from Tar to h5 Format Help
It's almost certainly a pickled pytorch model so you will first need to load it using pytorch and then write it out to h5 (legacy keras format) with https://github.com/gmalivenko/pytorch2keras.
-
Is Pytorch good deployment wise?
But of course, you can always train a model with one framework and run inference with another. For instance, pytorch2keras does exactly this.
ModelZoo.pytorch
-
[D] Any good resources/repositories to get ImageNet trained models?
Google for 'model zoo' and the terms you want. Here's one that comes up with label smoothing: https://github.com/PistonY/ModelZoo.pytorch
What are some alternatives?
NudeNet - Neural Nets for Nudity Detection and Censoring
mmpretrain - OpenMMLab Pre-training Toolbox and Benchmark
InvoiceNet - Deep neural network to extract intelligent information from invoice documents.
simpleT5 - simpleT5 is built on top of PyTorch-lightning⚡️ and Transformers🤗 that lets you quickly train your T5 models.
facenet-pytorch - Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models
models - Models and examples built with TensorFlow
efficientnet-lite-keras - Keras reimplementation of EfficientNet Lite.
segmentation_models - Segmentation models with pretrained backbones. Keras and TensorFlow Keras.
onnx-tensorflow - Tensorflow Backend for ONNX
MEAL-V2 - MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks. In NeurIPS 2020 workshop.
cnn-watermark-removal - Fully convolutional deep neural network to remove transparent overlays from images
TensorFlow-object-detection-tutorial - The purpose of this tutorial is to learn how to install and prepare TensorFlow framework to train your own convolutional neural network object detection classifier for multiple objects, starting from scratch