pytorch2keras
deepvision
pytorch2keras | deepvision | |
---|---|---|
2 | 1 | |
846 | 30 | |
- | - | |
0.0 | 5.1 | |
over 1 year ago | 10 months ago | |
Python | Python | |
MIT License | 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.
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.
deepvision
-
PyTorch/TensorFlow image models with automatic weight conversions
Link: https://github.com/DavidLandup0/deepvision
What are some alternatives?
NudeNet - Neural Nets for Nudity Detection and Censoring
awesome-modular-pytorch-lightning - LightCollections⚡️: Ready-to-use implementations such as `LightningModules` for various computer vision papers.
InvoiceNet - Deep neural network to extract intelligent information from invoice documents.
SHREC2023-ANIMAR - Source codes of team TikTorch (1st place solution) for track 2 and 3 of the SHREC2023 Challenge
facenet-pytorch - Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models
Open3D-ML - An extension of Open3D to address 3D Machine Learning tasks
efficientnet-lite-keras - Keras reimplementation of EfficientNet Lite.
datasets - 🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
onnx-tensorflow - Tensorflow Backend for ONNX
Efficient-AI-Backbones - Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.
cnn-watermark-removal - Fully convolutional deep neural network to remove transparent overlays from images
dream-creator - Quickly and easily create / train a custom DeepDream model