This media is not supported in your browser
VIEW IN TELEGRAM
🌄 NAFSSR: Stereo Image Super-Resolution Using NAFNet
Github: https://github.com/megvii-research/NAFNet
Paper: https://arxiv.org/abs/2204.08714v1
Dataset: https://paperswithcode.com/dataset/kitti
Demo: https://colab.research.google.com/drive/1dkO5AyktmBoWwxBwoKFUurIDn0m4qDXT?usp=sharing
@ai_machinelearning_big_data
Github: https://github.com/megvii-research/NAFNet
Paper: https://arxiv.org/abs/2204.08714v1
Dataset: https://paperswithcode.com/dataset/kitti
Demo: https://colab.research.google.com/drive/1dkO5AyktmBoWwxBwoKFUurIDn0m4qDXT?usp=sharing
@ai_machinelearning_big_data
👍11🔥4
Anomaly detection using zscore and modified zscore
https://www.kaggle.com/code/jainyk/anomaly-detection-using-zscore-and-modified-zscore/notebook
@ai_machinelearning_big_data
https://www.kaggle.com/code/jainyk/anomaly-detection-using-zscore-and-modified-zscore/notebook
@ai_machinelearning_big_data
👍5👎4❤1
🛠 MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment
Github: https://github.com/iigroup/maniqa
Paper: https://arxiv.org/abs/2204.08958v1
Dataset: https://paperswithcode.com/dataset/kitti
Demo: https://paperswithcode.com/dataset/pipal-perceptual-iqa-dataset
@ai_machinelearning_big_data
Github: https://github.com/iigroup/maniqa
Paper: https://arxiv.org/abs/2204.08958v1
Dataset: https://paperswithcode.com/dataset/kitti
Demo: https://paperswithcode.com/dataset/pipal-perceptual-iqa-dataset
@ai_machinelearning_big_data
👍6❤3🔥1🤩1
🚰 Simulating Fluids in Real-World Still Images
surface-based layered representation(SLR), which decomposes the fluid and the static objects in the scene, to better synthesize the animated videos from a single fluid imagе
Code: https://github.com/generalizable-neural-performer/gnr
Paper: http://arxiv.org/abs/2204.11335
Project: https://simulatingfluids.github.io/
surface-based layered representation(SLR), which decomposes the fluid and the static objects in the scene, to better synthesize the animated videos from a single fluid imagе
Code: https://github.com/generalizable-neural-performer/gnr
Paper: http://arxiv.org/abs/2204.11335
Project: https://simulatingfluids.github.io/
GitHub
GitHub - generalizable-neural-performer/gnr: Implementation of "Generalizable Neural Performer: Learning Robust Radiance Fields…
Implementation of "Generalizable Neural Performer: Learning Robust Radiance Fields for Human Novel View Synthesis" - generalizable-neural-performer/gnr
👎8👍7
🚀 TorchSparse: Efficient Point Cloud Inference Engine
Github: https://github.com/mit-han-lab/torchsparse
Paper: https://arxiv.org/abs/2204.10319v1
Dataset: https://paperswithcode.com/dataset/nuscenes
Demo: https://paperswithcode.com/dataset/pipal-perceptual-iqa-dataset
@ai_machinelearning_big_data
Github: https://github.com/mit-han-lab/torchsparse
Paper: https://arxiv.org/abs/2204.10319v1
Dataset: https://paperswithcode.com/dataset/nuscenes
Demo: https://paperswithcode.com/dataset/pipal-perceptual-iqa-dataset
@ai_machinelearning_big_data
👍7🔥2🎉1
Мониторинги показывают, что GPU загружены, при этом видно, что они не потребляют электричества. Что делать? Хорошая статья с ответом на этот вопрос.
Будет полезно почитать, даже если вы занимаетесь обучением моделек на домашних GPU.
Будет полезно почитать, даже если вы занимаетесь обучением моделек на домашних GPU.
Хабр
Почему GPU обманывают о своей нагрузке и как с этим бороться
В предыдущем посте я рассказывал о том, как мы строили свои суперкомпьютеры. В этом — поделюсь опытом, который мы накопили, эксплуатируя наши кластеры. Этот опыт будет полезен не только тем, кто...
👍15🔥2😁1😢1
🔹 Exploring a Fine-Grained Multiscale Method for Cross-Modal Remote Sensing Image Retrieval
Github: https://github.com/xiaoyuan1996/AMFMN
Paper: https://arxiv.org/abs/2204.09868v1
Dataset: https://paperswithcode.com/dataset/kitti
@ai_machinelearning_big_data
Github: https://github.com/xiaoyuan1996/AMFMN
Paper: https://arxiv.org/abs/2204.09868v1
Dataset: https://paperswithcode.com/dataset/kitti
@ai_machinelearning_big_data
🔥4👍2🎉2😢1
This media is not supported in your browser
VIEW IN TELEGRAM
🧍♂ StyleGAN-Human: A Data-Centric Odyssey of Human Generation
human image dataset with over 230K samples capturing diverse poses and textures
Github: https://github.com/stylegan-human/stylegan-human
Demo video: https://youtu.be/nIrb9hwsdcI
Paper: https://arxiv.org/abs/2204.11823v1
Dataset: https://paperswithcode.com/dataset/market-1501
Colab: https://colab.research.google.com/drive/1sgxoDM55iM07FS54vz9ALg1XckiYA2On
@ai_machinelearning_big_data
human image dataset with over 230K samples capturing diverse poses and textures
Github: https://github.com/stylegan-human/stylegan-human
Demo video: https://youtu.be/nIrb9hwsdcI
Paper: https://arxiv.org/abs/2204.11823v1
Dataset: https://paperswithcode.com/dataset/market-1501
Colab: https://colab.research.google.com/drive/1sgxoDM55iM07FS54vz9ALg1XckiYA2On
@ai_machinelearning_big_data
👍9🔥5❤1😢1
🧊 Focal Sparse Convolutional Networks for 3D Object Detection (CVPR 2022, Oral)
Github: https://github.com/dvlab-research/focalsconv
Paper: https://arxiv.org/abs/2204.12463
Dataset: https://paperswithcode.com/dataset/nuscenes
@ai_machinelearning_big_data
Github: https://github.com/dvlab-research/focalsconv
Paper: https://arxiv.org/abs/2204.12463
Dataset: https://paperswithcode.com/dataset/nuscenes
@ai_machinelearning_big_data
🔥4👍2❤1🎉1
Media is too big
VIEW IN TELEGRAM
🚗 MMRotate: A Rotated Object Detection Benchmark using Pytorch
Github: https://github.com/open-mmlab/mmrotate
Documentation: https://mmrotate.readthedocs.io/en/latest/
Paper: https://arxiv.org/abs/2204.13317v1
Dataset: https://paperswithcode.com/dataset/dota
@ai_machinelearning_big_data
Github: https://github.com/open-mmlab/mmrotate
Documentation: https://mmrotate.readthedocs.io/en/latest/
Paper: https://arxiv.org/abs/2204.13317v1
Dataset: https://paperswithcode.com/dataset/dota
@ai_machinelearning_big_data
❤8👍3🔥1🎉1
🔝 OPT (Open Pre-trained Transformers) is a family of NLP models trained on billions of tokens of text obtained from the internet.
175B GPT-3
Github: https://github.com/facebookresearch/metaseq
Instructions: https://github.com/facebookresearch/metaseq/blob/main/docs/setup.md
Paper: https://arxiv.org/abs/2205.01068v2
Dataset: https://paperswithcode.com/dataset/superglue
@ai_machinelearning_big_data
175B GPT-3
Github: https://github.com/facebookresearch/metaseq
Instructions: https://github.com/facebookresearch/metaseq/blob/main/docs/setup.md
Paper: https://arxiv.org/abs/2205.01068v2
Dataset: https://paperswithcode.com/dataset/superglue
@ai_machinelearning_big_data
👍9❤2🔥2👎1👏1
⚡️ EmotionFlow: Capture the Dialogue Level Emotion Transitions
Code: https://github.com/fpcsong/emotionflow
Paper: https://arxiv.org/abs/2204.10298v1
Dataset: https://paperswithcode.com/dataset/meld
@ai_machinelearning_big_data
Code: https://github.com/fpcsong/emotionflow
Paper: https://arxiv.org/abs/2204.10298v1
Dataset: https://paperswithcode.com/dataset/meld
@ai_machinelearning_big_data
👍3👎3
💬 Textual Entailment for Event Argument Extraction: Zero- and Few-Shot with Multi-Source Learning
Github: https://github.com/osainz59/Ask2Transformers
Instructions: https://github.com/facebookresearch/metaseq/blob/main/docs/setup.md
Paper: https://arxiv.org/abs/2205.01376v1
Dataset: https://paperswithcode.com/dataset/snli
@ai_machinelearning_big_data
Github: https://github.com/osainz59/Ask2Transformers
Instructions: https://github.com/facebookresearch/metaseq/blob/main/docs/setup.md
Paper: https://arxiv.org/abs/2205.01376v1
Dataset: https://paperswithcode.com/dataset/snli
@ai_machinelearning_big_data
👍7❤3🔥2
📌 Список потрясающих фреймворков, библиотек и программного обеспечения для машинного обучения (по языкам)
Статья
@ai_machinelearning_big_data
Статья
@ai_machinelearning_big_data
👍15👎4
↘️ PyRDF2Vec: A Python Implementation and Extension of RDF2Vec
Create a 2D feature matrix from a Knowledge Graph for downstream ML tasks.
Github: https://github.com/IBCNServices/pyRDF2Vec
RDF2Vec: http://rdf2vec.org/
Paper: https://arxiv.org/abs/2205.02283v1
Examples: https://github.com/IBCNServices/pyRDF2Vec/tree/main/examples
How to Create Representations of Entities in a Knowledge Graph
@ai_machinelearning_big_data
Create a 2D feature matrix from a Knowledge Graph for downstream ML tasks.
Github: https://github.com/IBCNServices/pyRDF2Vec
RDF2Vec: http://rdf2vec.org/
Paper: https://arxiv.org/abs/2205.02283v1
Examples: https://github.com/IBCNServices/pyRDF2Vec/tree/main/examples
How to Create Representations of Entities in a Knowledge Graph
@ai_machinelearning_big_data
👍9❤4🔥1
Centroid Initialization Methods for k-means Clustering
https://www.kdnuggets.com/2020/06/centroid-initialization-k-means-clustering.html
@ai_machinelearning_big_data
https://www.kdnuggets.com/2020/06/centroid-initialization-k-means-clustering.html
@ai_machinelearning_big_data
👍10
This media is not supported in your browser
VIEW IN TELEGRAM
🪄 Language Models Can See: Plugging Visual Controls in Text Generation
Github: https://github.com/yxuansu/magic
Paper: https://arxiv.org/abs/2205.02655v1
Dataset: https://paperswithcode.com/dataset/coco
Contrastive Framework for Neural Text Generation: https://github.com/yxuansu/simctg
Colab: https://colab.research.google.com/drive/19lyyMXDRNr-Op8vwUOiRmbhMxI_s3rwW?usp=sharing
@ai_machinelearning_big_data
Github: https://github.com/yxuansu/magic
Paper: https://arxiv.org/abs/2205.02655v1
Dataset: https://paperswithcode.com/dataset/coco
Contrastive Framework for Neural Text Generation: https://github.com/yxuansu/simctg
Colab: https://colab.research.google.com/drive/19lyyMXDRNr-Op8vwUOiRmbhMxI_s3rwW?usp=sharing
@ai_machinelearning_big_data
👍9🔥2❤1🎉1
📝 EasyNLP is an easy-to-use NLP development and application toolkit in PyTorch
$ pip install pai-easynlp.
Github: https://github.com/alibaba/EasyNLP
Paper: https://arxiv.org/abs/2205.03071v1
Dataset: https://paperswithcode.com/dataset/natural-questions
Documentation: https://www.yuque.com/easyx/easynlp/kkhkai
@ai_machinelearning_big_data
$ pip install pai-easynlp.
Github: https://github.com/alibaba/EasyNLP
Paper: https://arxiv.org/abs/2205.03071v1
Dataset: https://paperswithcode.com/dataset/natural-questions
Documentation: https://www.yuque.com/easyx/easynlp/kkhkai
@ai_machinelearning_big_data
👍21
🗯 DeepFilterNet
A Low Complexity Speech Enhancement Framework for Full-Band Audio (48kHz) using on Deep Filtering.
Github: https://github.com/rikorose/deepfilternet
Paper: https://arxiv.org/abs/2205.05474v1
Demo: https://huggingface.co/spaces/hshr/DeepFilterNet2
@ai_machinelearning_big_data
A Low Complexity Speech Enhancement Framework for Full-Band Audio (48kHz) using on Deep Filtering.
Github: https://github.com/rikorose/deepfilternet
Paper: https://arxiv.org/abs/2205.05474v1
Demo: https://huggingface.co/spaces/hshr/DeepFilterNet2
@ai_machinelearning_big_data
👍10🔥4
KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learning
Github: https://github.com/explainableml/kg-sp
Paper: https://arxiv.org/abs/2205.06784v1
Dataset: https://paperswithcode.com/dataset/conceptnet
@ArtificialIntelligencedl
Github: https://github.com/explainableml/kg-sp
Paper: https://arxiv.org/abs/2205.06784v1
Dataset: https://paperswithcode.com/dataset/conceptnet
@ArtificialIntelligencedl
👍12👎3
🦉 OWL-ViT: Open-World Object Detection with Vision Transformers
OWL-ViT is an open-vocabulary object detector.
Github: https://github.com/google-research/scenic/tree/main/scenic/projects/owl_vit
Paper: https://arxiv.org/abs/2205.06230
Colab: https://colab.research.google.com/github/google-research/scenic/blob/main/scenic/projects/owl_vit/notebooks/OWL_ViT_minimal_example.ipynb
Dataset: https://paperswithcode.com/dataset/objects365
@ai_machinelearning_big_data
OWL-ViT is an open-vocabulary object detector.
Github: https://github.com/google-research/scenic/tree/main/scenic/projects/owl_vit
Paper: https://arxiv.org/abs/2205.06230
Colab: https://colab.research.google.com/github/google-research/scenic/blob/main/scenic/projects/owl_vit/notebooks/OWL_ViT_minimal_example.ipynb
Dataset: https://paperswithcode.com/dataset/objects365
@ai_machinelearning_big_data
👍12🔥3