There are 4 repositories under pre-trained topic.
Segmentation models with pretrained backbones. Keras and TensorFlow Keras.
A LITE BERT FOR SELF-SUPERVISED LEARNING OF LANGUAGE REPRESENTATIONS, 海量中文预训练ALBERT模型
RoBERTa中文预训练模型: RoBERTa for Chinese
:smiley_cat: Pretty & simple image classifier app template. Deploy your own trained model or pre-trained model (VGG, ResNet, Densenet) to a web app using Flask in 10 minutes.
ImageNet pre-trained models with batch normalization for the Caffe framework
BOND: BERT-Assisted Open-Domain Name Entity Recognition with Distant Supervision
TensorFlow implementation of GoogLeNet and Inception for image classification.
Convenient wrapper for TensorFlow feature extraction from pre-trained models using tf.contrib.slim
Cluster images based on image content using a pre-trained deep neural network, optional time distance scaling and hierarchical clustering.
A collection of Audio and Speech pre-trained models.
Easy to use neural networks for NVIDIA Jetson (and desktop too!)
Mask R-CNN, FPN, LinkNet, PSPNet and UNet with multiple backbone architectures support readily available
[this repo is no longer maintained] Neural Network image classifier (inception-bn network architecture), developed via MxNet
Hands on Imagenet training. Unofficial ModelZoo project on Pytorch. MobileNetV3 Top1 75.64🌟 GhostNet1.3x 75.78🌟
Pretrained model for Chinese Scientific Text
Pre-trained VGG-Net Model for image classification using tensorflow
A speaker gender classifier. MFC feature engineering and a pre-trained ResNet-50. GradCAM interpretation.
Example on how to use pre trained networks on new classification problems.
Earth observations, especially satellite data, have produced a wealth of methods and results in meeting global challenges, often presented in unstructured texts such as papers or reports. Accurate extraction of satellite and instrument entities from these unstructured texts can help to link and reuse Earth observation resources.
Played with Tensorspace a library for Neural network 3D visualization, building interactive and intuitive models in browsers, supports pre-trained deep learning models from TensorFlow, Keras, TensorFlow.js
Pre-train Embedding in LightFM Recommender System Framework
Image Classification via Transfer Learning: Using Pre-trained Densely Connected Convolutional Network (DenseNet) weights
Contrast multiple facial expression recognition experiments and found that using SVM instead of softmax layer can achieve better classification results(65.47% accuracy on fer2013 dataset).
Pretrained on ImageNet ResNet-152 model in Keras
Pre-trained word embeddings for Romanian and Romanian list of inflected forms
Tensorflow Keras based pre-trained model to predict gender and ethnicity of Indian Names using Python