Image Classification
Transformers
Safetensors
English
model_hub_mixin
pytorch_model_hub_mixin
Eval Results (legacy)
Instructions to use X01D/6DRepNET-RepVGGA0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use X01D/6DRepNET-RepVGGA0 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="X01D/6DRepNET-RepVGGA0") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("X01D/6DRepNET-RepVGGA0", dtype="auto") - Notebooks
- Google Colab
- Kaggle
metadata
tags:
- model_hub_mixin
- pytorch_model_hub_mixin
license: apache-2.0
language:
- en
metrics:
- mae
This model has been pushed to the Hub using the PytorchModelHubMixin integration:
- Library: torch==2.2.1+cu118 torchaudio==2.2.1+cu118 torchvision==0.17.1
- Docs:
A reduced version of 6DRepNet model using the backbone of RepVGG A0 backbone
model-index:
- name: 6DRepNet-RepVGGA0
results:
- task:
type: head pose estimation
dataset:
name: BIWI
type: Benchmarking
metrics:
- name: MAE type: MAE value: 3.70 verified: false
- task:
type: head pose estimation
dataset:
name: BIWI
type: Benchmarking
metrics:
- name: 6DRepNet-RepVGGA0
results: