fidelity / sim2real-docs
Synthesize image datasets of documents in natural scenes with Python+Blender3D
☆58Updated 2 years ago
Alternatives and similar repositories for sim2real-docs:
Users that are interested in sim2real-docs are comparing it to the libraries listed below
- A non-JIT version implementation / replication of CLIP of OpenAI in pytorch☆34Updated 4 years ago
- An open source implementation of CLIP.☆32Updated 2 years ago
- ☆17Updated 5 years ago
- Official PyTorch Implementation of DocSynth: A Layout Guided Approach for Controllable Document Image Synthesis - ICDAR 2021☆78Updated 3 years ago
- Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch☆59Updated 4 years ago
- ☆27Updated 4 years ago
- Pytorch augmentation☆119Updated last year
- A Unet based deeplearning model to line/box/spurious artifacts from text images. Unsupervised training.☆59Updated 5 years ago
- Code for the ICDAR2021 paper "Visual FUDGE: Form Understanding via Dynamic Graph Editing"☆33Updated 3 years ago
- Code for scaling Transformers☆26Updated 4 years ago
- ☆39Updated 3 years ago
- ☆15Updated 3 years ago
- Code for CVPR21 paper A Multiplexed Network for End-to-End, Multilingual OCR☆80Updated 2 years ago
- ☆44Updated 3 years ago
- code and data for paper "One-shot Text Field Labeling using Attention and BeliefPropagation for Structure Information Extraction"☆61Updated 4 years ago
- clip retrieval benchmark☆17Updated 2 years ago
- ☆15Updated 2 years ago
- Explore the image embeddings of Unsplash using CLIP's image similarity☆50Updated 4 years ago
- Implementation of Feedback Transformer in Pytorch☆105Updated 4 years ago
- Script and models for clustering LAION-400m CLIP embeddings.☆26Updated 3 years ago
- A simple wrapper library for binding timm models as detectron2 backbones☆42Updated last year
- A criticism of a recent paper on buggy image downsampling methods in popular image processing and deep learning libraries.☆72Updated 2 years ago
- ☆81Updated last year
- TF2 implementation of knowledge distillation using the "function matching" hypothesis from https://arxiv.org/abs/2106.05237.☆87Updated 3 years ago
- (unofficial) - customized fork of DETR, optimized for intelligent obj detection on 'real world' custom datasets☆12Updated 4 years ago
- Another attempt at a long-context / efficient transformer by me☆37Updated 3 years ago
- Public implementation of our CVPR Paper "OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page TextRecognition by learnin…☆144Updated 3 years ago
- ☆80Updated 2 years ago
- Distorted Document Images dataset (DDI-100).☆136Updated 2 years ago
- A dashboard for exploring timm learning rate schedulers☆19Updated 5 months ago