Share and discover more about AI with social posts from the community.huggingface/OpenAi
Live Portrait Updated to V5
Animals Live animation added
All of the main repo changes and improvements added to our modified and improve app
Link : https://patreon.com/posts/107609670
Animals Live animation added
All of the main repo changes and improvements added to our modified and improve app
Link : https://patreon.com/posts/107609670
Patreon
1-Click Installers and Upgraded APP for LivePortrait - Blazing Fast Static Image or Video to Video to Talking and Moving Animation…
Get more from SECourses: Tutorials, Guides, Resources, Training, FLUX, MidJourney, Voice Clone, TTS, ChatGPT, GPT, LLM, Scripts by Furkan Gözü on Patreon
New smol-vision tutorial dropped: QLoRA fine-tuning IDEFICS3-Llama 8B on VQAv2 🐶
Learn how to efficiently fine-tune the latest IDEFICS3-Llama on visual question answering in this notebook 📖
Fine-tuning notebook: https://github.com/merveenoyan/smol-vision/blob/main/Idefics_FT.ipynb
Resulting model:
merve/idefics3llama-vqav2
Learn how to efficiently fine-tune the latest IDEFICS3-Llama on visual question answering in this notebook 📖
Fine-tuning notebook: https://github.com/merveenoyan/smol-vision/blob/main/Idefics_FT.ipynb
Resulting model:
merve/idefics3llama-vqav2
GitHub
smol-vision/Idefics_FT.ipynb at main · merveenoyan/smol-vision
Recipes for shrinking, optimizing, customizing cutting edge vision models. 💜 - merveenoyan/smol-vision
MobileViT (small-sized model)
MobileViT model pre-trained on ImageNet-1k at resolution 256x256. It was introduced in MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer by Sachin Mehta and Mohammad Rastegari, and first released in this repository. The license used is Apple sample code license.
Disclaimer: The team releasing MobileViT did not write a model card for this model so this model card has been written by the Hugging Face team.
Model description
MobileViT is a light-weight, low latency convolutional neural network that combines MobileNetV2-style layers with a new block that replaces local processing in convolutions with global processing using transformers. As with ViT (Vision Transformer), the image data is converted into flattened patches before it is processed by the transformer layers. Afterwards, the patches are "unflattened" back into feature maps. This allows the MobileViT-block to be placed anywhere inside a CNN. MobileViT does not require any positional embeddings.
Intended uses & limitations
You can use the raw model for image classification. See the model hub to look for fine-tuned versions on a task that interests you.
https://huggingface.co/apple/mobilevit-small
MobileViT model pre-trained on ImageNet-1k at resolution 256x256. It was introduced in MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer by Sachin Mehta and Mohammad Rastegari, and first released in this repository. The license used is Apple sample code license.
Disclaimer: The team releasing MobileViT did not write a model card for this model so this model card has been written by the Hugging Face team.
Model description
MobileViT is a light-weight, low latency convolutional neural network that combines MobileNetV2-style layers with a new block that replaces local processing in convolutions with global processing using transformers. As with ViT (Vision Transformer), the image data is converted into flattened patches before it is processed by the transformer layers. Afterwards, the patches are "unflattened" back into feature maps. This allows the MobileViT-block to be placed anywhere inside a CNN. MobileViT does not require any positional embeddings.
Intended uses & limitations
You can use the raw model for image classification. See the model hub to look for fine-tuned versions on a task that interests you.
https://huggingface.co/apple/mobilevit-small
huggingface.co
apple/mobilevit-small · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Vision Transformer (base-sized model)
Vision Transformer (ViT) model pre-trained on ImageNet-21k (14 million images, 21,843 classes) at resolution 224x224, and fine-tuned on ImageNet 2012 (1 million images, 1,000 classes) at resolution 224x224. It was introduced in the paper An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale by Dosovitskiy et al. and first released in this repository. However, the weights were converted from the timm repository by Ross Wightman, who already converted the weights from JAX to PyTorch. Credits go to him.
Disclaimer: The team releasing ViT did not write a model card for this model so this model card has been written by the Hugging Face team.
https://huggingface.co/google/vit-base-patch16-224
Vision Transformer (ViT) model pre-trained on ImageNet-21k (14 million images, 21,843 classes) at resolution 224x224, and fine-tuned on ImageNet 2012 (1 million images, 1,000 classes) at resolution 224x224. It was introduced in the paper An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale by Dosovitskiy et al. and first released in this repository. However, the weights were converted from the timm repository by Ross Wightman, who already converted the weights from JAX to PyTorch. Credits go to him.
Disclaimer: The team releasing ViT did not write a model card for this model so this model card has been written by the Hugging Face team.
https://huggingface.co/google/vit-base-patch16-224
huggingface.co
google/vit-base-patch16-224 · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Returns whether the face belongs to man or woman based on face image.
See https://www.kaggle.com/code/dima806/man-woman-face-image-detection-vit for more details.
Classification report:
precision recall f1-score support
man 0.9898 0.9908 0.9903 7071
woman 0.9908 0.9898 0.9903 7072
accuracy 0.9903 14143
macro avg 0.9903 0.9903 0.9903 14143
weighted avg 0.9903 0.9903 0.9903 14143
See https://www.kaggle.com/code/dima806/man-woman-face-image-detection-vit for more details.
Classification report:
precision recall f1-score support
man 0.9898 0.9908 0.9903 7071
woman 0.9908 0.9898 0.9903 7072
accuracy 0.9903 14143
macro avg 0.9903 0.9903 0.9903 14143
weighted avg 0.9903 0.9903 0.9903 14143
fashion-images-gender-age-vit-large-patch16-224-in21k-v3
This model is a fine-tuned version of google/vit-large-patch16-224-in21k on the touchtech/fashion-images-gender-age dataset. It achieves the following results on the evaluation set:
Loss: 0.0223
Accuracy: 0.9960
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 1337
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 5.0
This model is a fine-tuned version of google/vit-large-patch16-224-in21k on the touchtech/fashion-images-gender-age dataset. It achieves the following results on the evaluation set:
Loss: 0.0223
Accuracy: 0.9960
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 1337
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 5.0
Model card for eca_botnext26ts_256.c1_in1k
A BotNet image classification model (with Efficient channel attention, based on ResNeXt architecture). Trained on ImageNet-1k in timm by Ross Wightman.
NOTE: this model did not adhere to any specific paper configuration, it was tuned for reasonable training times and reduced frequency of self-attention blocks.
Recipe details:
Based on ResNet Strikes Back C recipes
SGD (w/ Nesterov) optimizer and AGC (adaptive gradient clipping).
Cosine LR schedule with warmup
This model architecture is implemented using timm's flexible BYOBNet (Bring-Your-Own-Blocks Network).
BYOB (with BYOANet attention specific blocks) allows configuration of:
block / stage layout
block-type interleaving
stem layout
output stride (dilation)
activation and norm layers
channel and spatial / self-attention layers
...and also includes timm features common to many other architectures, including:
stochastic depth
gradient checkpointing
layer-wise LR decay
per-stage feature extraction
https://huggingface.co/timm/eca_botnext26ts_256.c1_in1k
A BotNet image classification model (with Efficient channel attention, based on ResNeXt architecture). Trained on ImageNet-1k in timm by Ross Wightman.
NOTE: this model did not adhere to any specific paper configuration, it was tuned for reasonable training times and reduced frequency of self-attention blocks.
Recipe details:
Based on ResNet Strikes Back C recipes
SGD (w/ Nesterov) optimizer and AGC (adaptive gradient clipping).
Cosine LR schedule with warmup
This model architecture is implemented using timm's flexible BYOBNet (Bring-Your-Own-Blocks Network).
BYOB (with BYOANet attention specific blocks) allows configuration of:
block / stage layout
block-type interleaving
stem layout
output stride (dilation)
activation and norm layers
channel and spatial / self-attention layers
...and also includes timm features common to many other architectures, including:
stochastic depth
gradient checkpointing
layer-wise LR decay
per-stage feature extraction
https://huggingface.co/timm/eca_botnext26ts_256.c1_in1k
huggingface.co
timm/eca_botnext26ts_256.c1_in1k · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Model card for poolformer_m36.sail_in1k
A PoolFormer (a MetaFormer) image classification model. Trained on ImageNet-1k by paper authors.
Model Details
Model Type: Image classification / feature backbone
Model Stats:
Params (M): 56.2
GMACs: 8.8
Activations (M): 22.0
Image size: 224 x 224
Papers:
MetaFormer Is Actually What You Need for Vision: https://arxiv.org/abs/2210.13452
Original: https://github.com/sail-sg/poolformer
Dataset: ImageNet-1k
A PoolFormer (a MetaFormer) image classification model. Trained on ImageNet-1k by paper authors.
Model Details
Model Type: Image classification / feature backbone
Model Stats:
Params (M): 56.2
GMACs: 8.8
Activations (M): 22.0
Image size: 224 x 224
Papers:
MetaFormer Is Actually What You Need for Vision: https://arxiv.org/abs/2210.13452
Original: https://github.com/sail-sg/poolformer
Dataset: ImageNet-1k
Model card for res2net101_26w_4s.in1k
A Res2Net (Multi-Scale ResNet) image classification model. Trained on ImageNet-1k by paper authors.
Model Details
Model Type: Image classification / feature backbone
Model Stats:
Params (M): 45.2
GMACs: 8.1
Activations (M): 18.4
Image size: 224 x 224
Papers:
Res2Net: A New Multi-scale Backbone Architecture: https://arxiv.org/abs/1904.01169
Dataset: ImageNet-1k
Original: https://github.com/gasvn/Res2Net/
A Res2Net (Multi-Scale ResNet) image classification model. Trained on ImageNet-1k by paper authors.
Model Details
Model Type: Image classification / feature backbone
Model Stats:
Params (M): 45.2
GMACs: 8.1
Activations (M): 18.4
Image size: 224 x 224
Papers:
Res2Net: A New Multi-scale Backbone Architecture: https://arxiv.org/abs/1904.01169
Dataset: ImageNet-1k
Original: https://github.com/gasvn/Res2Net/
Model card for resnet18.fb_swsl_ig1b_ft_in1k
A ResNet-B image classification model.
This model features:
ReLU activations
single layer 7x7 convolution with pooling
1x1 convolution shortcut downsample
Pretrained on Instagram-1B hashtags dataset using semi-weakly supervised learning and fine-tuned on ImageNet-1k by paper authors.
Model Details
Model Type: Image classification / feature backbone
Model Stats:
Params (M): 11.7
GMACs: 1.8
Activations (M): 2.5
Image size: 224 x 224
Papers:
Billion-scale semi-supervised learning for image classification: https://arxiv.org/abs/1905.00546
Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385
Original: https://github.com/facebookresearch/semi-supervised-ImageNet1K-models
A ResNet-B image classification model.
This model features:
ReLU activations
single layer 7x7 convolution with pooling
1x1 convolution shortcut downsample
Pretrained on Instagram-1B hashtags dataset using semi-weakly supervised learning and fine-tuned on ImageNet-1k by paper authors.
Model Details
Model Type: Image classification / feature backbone
Model Stats:
Params (M): 11.7
GMACs: 1.8
Activations (M): 2.5
Image size: 224 x 224
Papers:
Billion-scale semi-supervised learning for image classification: https://arxiv.org/abs/1905.00546
Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385
Original: https://github.com/facebookresearch/semi-supervised-ImageNet1K-models
Nuno-Tome /simple_image_classifier
Image Classification
This is a simple web app to test and compare different image classifier models using Hugging Face's image-classification pipeline.
From time to time more models will be added to the list. If you want to add a model, please open an issue on the GitHub repository.https://huggingface.co/spaces/Nuno-Tome/simple_image_classifier
Image Classification
This is a simple web app to test and compare different image classifier models using Hugging Face's image-classification pipeline.
From time to time more models will be added to the list. If you want to add a model, please open an issue on the GitHub repository.https://huggingface.co/spaces/Nuno-Tome/simple_image_classifier
huggingface.co
Simple Image Classifier - a Hugging Face Space by Nuno-Tome
compare different image classifier models
ONNX version of MoritzLaurer/deberta-v3-base-zeroshot-v1
This model is a conversion of MoritzLaurer/deberta-v3-base-zeroshot-v1 to ONNX format using the 🤗 Optimum library.
MoritzLaurer/deberta-v3-large-zeroshot-v1 is designed for zero-shot classification, capable of determining whether a hypothesis is true or not_true based on a text, a format based on Natural Language Inference (NLI).
https://huggingface.co/protectai/deberta-v3-base-zeroshot-v1-onnx
This model is a conversion of MoritzLaurer/deberta-v3-base-zeroshot-v1 to ONNX format using the 🤗 Optimum library.
MoritzLaurer/deberta-v3-large-zeroshot-v1 is designed for zero-shot classification, capable of determining whether a hypothesis is true or not_true based on a text, a format based on Natural Language Inference (NLI).
https://huggingface.co/protectai/deberta-v3-base-zeroshot-v1-onnx
huggingface.co
protectai/deberta-v3-base-zeroshot-v1-onnx · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.