Pre-trained models based on TensorLayerX. TensorLayerX is a multi-backend AI framework, which can run on almost all operation systems and AI hardwares, and support hybrid-framework programming. The currently version supports TensorFlow, MindSpore, PaddlePaddle, PyTorch, OneFlow and Jittor as the backends.
Motionformer This is an official pytorch implementation of paper Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers. In this rep
We envision models that are pre-trained on a vast range of domain-relevant tasks to become key for molecule property prediction. This repository aims to give easy access to state-of-the-art pre-trained models.
Knowledge-Inheritance Source code paper: Knowledge Inheritance for Pre-trained Language Models (preprint). The trained model parameters (in Fairseq fo
Adaptive Segmentation Mask Attack This repository contains the implementation of the Adaptive Segmentation Mask Attack (ASMA), a targeted adversarial
Hailo Model Zoo The Hailo Model Zoo provides pre-trained models for high-performance deep learning applications. Using the Hailo Model Zoo you can mea
Vision Guided Generative Pre-trained Language Models for Multimodal Abstractive Summarization [Paper] accepted at the EMNLP 2021: Vision Guided Genera
TorchGeo is a PyTorch domain library, similar to torchvision, that provides datasets, transforms, samplers, and pre-trained models specific to geospatial data.
Ancient Greek BERT The first and only available Ancient Greek sub-word BERT model! State-of-the-art post fine-tuning on Part-of-Speech Tagging and Mor
OpenVINO™ Toolkit - Open Model Zoo repository This repository includes optimized deep learning models and a set of demos to expedite development of hi
Change make_layerto features, which is the same as torchvision.
Change end_withto include_top, which is the same as Keras.
Change classifier, 4096 output units.
Tested training on demo/vision/image_classification/vgg/train.py. The training process still needs some modifications.
t5-japanese Codes to pre-train T5 (Text-to-Text Transfer Transformer) models pre-trained on Japanese web texts. The following is a list of models that
mtdp Library containing implementation related to the research paper "Multi-task pre-training of deep neural networks for digital pathology" (Mormont
KoRean based ELECTRA (KR-ELECTRA) This is a release of a Korean-specific ELECTRA model with comparable or better performances developed by the Computa
Models Playground ??️ Upload a Preprocessed Dataset ?? Choose whether to perform Classification or Regression ?? Enter the Dependent Variable ?
merged_depth runs (1) AdaBins, (2) DiverseDepth, (3) MiDaS, (4) SGDepth, and (5) Monodepth2, and calculates a weighted-average per-pixel absolute dept
InversePrompting Paper: Controllable Generation from Pre-trained Language Models via Inverse Prompting Code: The code is provided in the "chinese_ip"
K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters This repository is the implementation of the paper "K-Adapter: Infusing Knowledge
Lottery Jackpots Exist in Pre-trained Models (Paper Link) Requirements Python >= 3.7.4 Pytorch >= 1.6.1 Torchvision >= 0.4.1 Reproduce the Experiment
Dynamic-Vision-Transformer (Pytorch) This repo contains the official code and pre-trained models for the Dynamic Vision Transformer (DVT). Not All Ima
ERICA Source code and dataset for ACL2021 paper: "ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive L
192 Dec 23, 2022
90 Jan 8, 2023
31 Nov 19, 2022
53 Jul 4, 2022
50 Dec 7, 2022
42 Jan 7, 2023
1.3k Dec 30, 2022
22 Dec 8, 2022
3.4k Dec 31, 2022
1 Dec 13, 2021
27 Oct 14, 2022
12 Jun 3, 2022
19 Dec 10, 2022
39 Nov 21, 2022
101 Dec 16, 2022
118 Dec 13, 2022
27 Jun 28, 2022
210 Dec 18, 2022
75 Nov 2, 2022