Pico scale at 224x224
According to the model card, this pico-sized model was fine-tuned on ImageNet-1K at 224x224 resolution.
Open Source Model Profile · facebook
convnextv2-pico-1k-224
convnextv2-pico-1k-224 is a 9.07M-parameter ConvNeXt V2 image model from facebook. Its model card documents FCMAE pretraining and ImageNet-1K fine-tuning at 224x224.
- Publisher
- Task
- image-classification
- Model type
- convnextv2
- License
- apache-2.0
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
convnextv2-pico-1k-224 is published by facebook as an image-classification model. The captured configuration identifies ConvNextV2ForImageClassification, and Safetensors metadata reports about 9.07M parameters. According to the model card, it was pretrained with the FCMAE framework and fine-tuned on ImageNet-1K at 224x224.
Recorded capabilities
FCMAE and GRN design
The model card describes a fully convolutional masked autoencoder framework plus a Global Response Normalization layer.
Documented Transformers usage
The model card documents classifying images into 1,000 ImageNet classes with AutoImageProcessor and Transformers.
Use cases in the source record
- Raw image classification over the documented 1,000 ImageNet classes.
- Transformers experiments that load the checkpoint with AutoImageProcessor for 224x224 inputs.
Limitations and unknowns
- No evaluation results were extracted from this record.
- Provider state is historical snapshot data, not independently refreshed current availability.
- The model card states it was written by the Hugging Face team, not the releasing team.
Source and provenance
Source: facebook/convnextv2-pico-1k-224
Captured: Unknown. Processed: 2026-09-07T19:34:44.278404+00:00.
ConvNeXt V2 (pico-sized model) ConvNeXt V2 model pretrained using the FCMAE framework and fine-tuned on the ImageNet-1K dataset at resolution 224x224. It was introduced in the paper ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders by Woo et al. and first released in this repository . Disclaimer: The team releasing ConvNeXT V2 did not write a model card for this model so this model card has been written by the Hugging Face team. Model description ConvNeXt V2 is a pure convolutional model (ConvNet) that introduces a fully convolutional masked autoencoder framework (FCMAE) and a new Global Response Normalization…
F001F002F003F004F005F006F007F008F009F010F011F012F013F014F015F016