ModelListadosExterno

Mosquitoscope Convnextv2 Tiny

Production checkpoint for the MosquitoScope web demo: 41 mosquito species, hybrid class-weighted training (v2enhancedmemsafe).

Fontehuggingface.co/Sahil35077/mosquitoscope-convnextv2-tiny/tree/b401f404107fdf33b4904cb67ea00c5846292589

TipoOtherVersãoRevision b401f40

Fonte do modelo

Tipo: Other
Tamanho do arquivo: 107 MB
Versão: vRevision b401f40
Atualizado: 22 de set. de 2026
Downloads: 0
Fonte: Hugging Face

Descrição da fonte

MosquitoScope — ConvNeXt V2 Tiny (41 classes)

Production checkpoint for the MosquitoScope web demo: 41 mosquito species, hybrid class-weighted training (v2_enhanced_memsafe).

Metrics

Metric	Value
Test accuracy (TTA)	74.0%
CV mean accuracy	73.9%
Architecture	convnextv2_tiny @ 288px
Classes	41
Train / test	1228 / 308

Usage

import torch
import timm

checkpoint = torch.load("mosquito_convnextv2_tiny_final.pth", map_location="cpu", weights_only=False)
model = timm.create_model(checkpoint["model_name"], pretrained=False, num_classes=len(checkpoint["classes"]))
model.load_state_dict(checkpoint["model_state_dict"])
model.eval()

Bundled with the MosquitoScope Flask app; Render pulls this file at deploy time via HF_MODEL_REPO.

Fontes

1 fonte

Hugging FacePrimárioVersão b401f404107fdf33b4904cb67ea00c5846292589

huggingface.co/Sahil35077/mosquitoscope-convnextv2-tiny/tree/b401f404107fdf33b4904cb67ea00c5846292589

Verificado 10 de set.

Artefatos de modelo

1 artefato

mosquito_convnextv2_tiny_final.pth

pth · 107 MB · SHA-256 957b292a8d83…95b5 · Hugging Face

Baixar

Trechos de fonte

2 trechos

Readme10 de set.huggingface.co/Sahil35077/mosquitoscope-convnextv2-tiny

--- license: mit tags: - image-classification - mosquitoes - convnext - fine-grained-classification library_name: timm --- # MosquitoScope — ConvNeXt V2 Tiny (41 classes) Production checkpoint for the [MosquitoScope](https://github.com) web demo: 41 mosquito species, hybrid class-weighted training (`v2_enhanced_memsafe`). ## Metrics | Metric | Value | |--------|-------| | Test accuracy (TTA) | 74.0% | | CV mean accuracy | 73.9% | | Architecture | convnextv2_tiny @ 288px | | Classes | 41 | | Train / test | 1228 / 308 | ## Usage ```python import torch import timm checkpoint = torch.load("mosquito_convnextv2_tiny_final.pth", map_location="cpu", weights_only=False) model = timm.create_model(checkpoint["model_name"], pretrained=False, num_classes=len(checkpoint["classes"])) model.load_state_dict(checkpoint["model_state_dict"]) model.eval() ``` Bundled with the MosquitoScope Flask app; Render pulls this file at deploy time via `HF_MODEL_REPO`.

Note10 de set.huggingface.co/Sahil35077/mosquitoscope-convnextv2-tiny

Source context: 0 downloads · 0 likes · Pipeline image-classification · Library timm · Repo Sahil35077/mosquitoscope-convnextv2-tiny