Awesome Backbones
1.0.0
Como remover aprimoramentos? Se o arquivo de configuração do TRAIN_PIPELE
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='RandomResizedCrop',
size=192,
efficientnet_style=True,
interpolation='bicubic'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='ToTensor', keys=['gt_label']),
dict(type='Collect', keys=['img', 'gt_label'])
] Se o seu conjunto de dados tiver alterado a forma para o tamanho exigido pela rede com antecedência, a operação Resize também poderá ser removida.
2024.09.06
2023.12.02
Adicionado os resultados mencionados por muitas pessoas em questão , treinar o ACC e Val Loss
metrics_outputs.csv salva train_loss, train_acc, train_precision, train_recall, train_f1-score, val_loss, val_acc, val_precision, val_recall, val_f1-score para todos para desenhar 2023.08.05
2023.03.07
2022.11.20
| Conjunto de dados | Tutorial em vídeo | Grupo de discussão sobre tecnologia de inteligência artificial |
|---|---|---|
Código de extração花卉数据集: 0zat | Clique em mim para pular | Grupo 1: 78174903 Grupo 3: 584723646 |
python tools/single_test.py datas/cat-dog.png models/mobilenet/mobilenet_v3_small.py --classes-map datas/imageNet1kAnnotation.txt| nome | Peso | nome | Peso | nome | Peso |
|---|---|---|---|---|---|
| LENET5 | Nenhum | Alexnet | Nenhum | VGG | VGG-11 VGG-13 VGG-16 VGG-19 VGG-11-BN VGG-13-BN VGG-16-BN VGG-19-bn |
| Resnet | Resnet-18 Resnet-34 Resnet-50 Resnet-101 Resnet-152 | Resnetv1c | Resnetv1C-50 Resnetv1C-101 Resnetv1C-152 | Resnetv1d | Resnetv1d-50 Resnetv1D-101 Resnetv1d-152 |
| Resnext | Resnext-50 Resnext-101 Resnext-152 | Seresnet | Seresnet-50 Seresnet-101 | Seresnext | Nenhum |
| Regnet | REGNETX-400MF REGNETX-800MF REGNETX-1.6GF Regnetx-3.2GF Regnetx-4.0GF Regnetx-6.4gf Regnetx-8.0GF REGNETX-12GF | MobileNetv2 | MobileNetv2 | MobileNetv3 | MobileNetv3-small MobileNetv3-Large |
| Shufflenetv1 | Shufflenetv1 | Shufflenetv2 | Shufflenetv2 | EficienteNET | EficienteNET-B0 EficienteNET-B1 EficienteNET-B2 EficienteNET-B3 EficienteNET-B4 EficienteNET-B5 EficienteNET-B6 EficienteNET-B7 EficienteNET-B8 |
| Repvgg | Repvgg-a0 Repvgg-a1 Repvgg-a2 Repvgg-b0 Repvgg-b1 Repvgg-a1 REPVGG-B1G2 REPVGG-B1G4 Repvgg-b2 REPVGG-B2G4 REPVGG-B2G4 Repvgg-b3 REPVGG-B3G4 Repvgg-d2se | Res2net | Res2Net-50-14W-8S Res2Net-50-26W-8S Res2Net-101-26W-4S | Convnext | Convnext Tiny Convnext-small Convnext-Base Convnext-Large Convnext-Xlarge |
| Hrnet | HRNET-W18 HRNET-W30 HRNET-W32 Hrnet-w40 Hrnet-w44 Hrnet-w48 Hrnet-w64 | Convmixer | Convmixer-768/32 Convmixer-1024/20 Convmixer-1536/20 | Cspnet | CSPDARKNET50 CSPRESNET50 CSPRESNEXT50 |
| Transformador Swin | Tiny-224 Small-224 Base-224 grande-224 Base-384 Large-384 | Transformador de visão | VIT_BASE_P16_224 vit_base_p32_224 VIT_LARGE_P16_224 VIT_BASE_P16_384 VIT_BASE_P32_384 VIT_LARGE_P16_384 | Transformador no transformador | Tnt-small |
| Mixer MLP | base_p16 grande_p16 | Deit | Deit minúsculo Deit minúsculo destilado Deit-small Deit-pequeno destilado Deit-Base Deit-base destilado Deit-base 384px Deit-base destilado 384px | Conformador | Conformista Tiny-P16 Conformer-small-p32 Conformer-small-p16 Conformista-BASE-P16 |
| T2T-Vit | T2T-VIT_T-14 T2T-VIT_T-19 T2T-VIT_T-24 | Gêmeos | Pcpvt-small PCPVT-BASE PCPVT-Large Svt-small SVT-BASE SVT-Large | PoolFormer | PoolFormer-S12 PoolFormer-S24 PoolFormer-S36 PoolFormer-M36 Poolformer-M48 |
| Densenet | Densenet121 Densenet161 Densenet169 Densenet201 | Rede de atenção visual (van) | Van Tiny Van-small Van-base Van-Large | REDEMA DE ARDENÇÃO | WRN-50 WRN-101 |
| Hornet | Tarquinho de vespa Hornet Tiny-GF Hornet-small Hornet-small-gf Base Hornet Hornet-Base-GF Hornet-Large Hornet-Large-GF Hornet-Large-GF384 | EficienteFormer | eficienteFormer-L1 eficienteFormer-L3 eficienteFormer-L7 | Transformador Swin V2 | Janela Tiny-256 8 Janela Tiny-256 16 Janela Small-256 8 Janela Small-256 16 Janela base-256 8 Janela Base-256 16 Janela grande de 256 Janela grande-384 24 |
| Mvitv2 | Mvitv2 pequeno Mvitv2-small MVITV2-BASE MVITV2-Large | MobileVit | MobileVit-XXSmall MobileVit-Xsmall MobileVit-small | Turco | Davit-t Davit-S Davit-B |
| Replknet | Replknet-31b-224 Replknet-31b-384 Replknet-31L-384 Replknet-xl | Beit | Beit-base | Eva | EVA-G-P14-224 EVA-G-P14-336 EVA-G-P14-560 EVA-G-P16-224 EVA-L-P14-224 EVA-L-P14-196 EVA-L-P14-336 |
| Mixmim | Mixmim-Base | EficienteNETV2 | EficienteNETV2-B0 EficienteNETV2-B1 EficienteNETV2-B2 EficienteNETV2-B3 EficienteNETV2-S EficienteNETV2-M EficienteNETV2-l EficienteNETV2-XL | DEIT3 | DEIT3_SMALL_P16 DEIT3_SMALL_P16_384 DEIT3_BASE_P16 DEIT3_BASE_P16_384 deit3_medium_p16 DEIT3_LARGE_P16 DEIT3_LARGE_P16_384 DEIT3_HUGE_P16 |
| Edgenext | Edgext-Base Edgext-small Edgeext-x-small Edgeext-xx-small | RevVisionTransformer | Revvit-small Revvit-Base |
@repo{2020mmclassification,
title={OpenMMLab's Image Classification Toolbox and Benchmark},
author={MMClassification Contributors},
howpublished = {url{https://github.com/open-mmlab/mmclassification}},
year={2020}
}