MobileNetV4 pretrained weights - a timm Collection

timm 's Collections

Searching for Better ViT Baselines

MobileNetV4 pretrained weights

timm Top-20 ImageNet-1k Models

timm Top-20 Fastest Models

timm ImageNet-12k Models

timm Takes on the Classics

Fastest timm models > 75.3% IN-1k Top-1 (Original ResNet-50)

Fastest timm models > 80% Top-1 ImageNet-1k

Fastest timm models > 83% ImageNet-1k Top-1

Fastest timm models > 86% ImageNet-1k Top-1

Fastest timm models > 88% ImageNet-1k Top-1

All the ImageNets

Fine-Tune Image Classification Benchmark Datasets

timm tiny test models

MobileNetV4 pretrained weights

updated Sep 22

Weights for MobileNet-V4 pretrained in timm

timm/mobilenetv4_conv_aa_large.e230_r448_in12k_ft_in1k

Image Classification • Updated Sep 18 • 6.84k • 1
timm/mobilenetv4_conv_aa_large.e230_r384_in12k_ft_in1k

Image Classification • Updated Sep 2 • 3.01k
timm/mobilenetv4_hybrid_large.ix_e600_r384_in1k

Image Classification • Updated Sep 2 • 3.8k • 2

Note 84.36 @ 448x448, 83.99 @ 384x384
timm/mobilenetv4_hybrid_large.e600_r384_in1k

Image Classification • Updated Sep 2 • 649 • 1

Note 84.27 @ 448x448, 83.8 @ 384x384
timm/mobilenetv4_hybrid_medium.ix_e550_r384_in1k

Image Classification • Updated Sep 2 • 1.88k • 3

Note 83.39 @ 448x448, 82.97 @ 384x384
timm/mobilenetv4_conv_large.e600_r384_in1k

Image Classification • Updated Sep 2 • 1.07k • 2

Note 83.39 @ 448x448, 82.95 @ 384x384
timm/mobilenetv4_hybrid_medium.e200_r256_in12k_ft_in1k

Image Classification • Updated Sep 2 • 1.86k
timm/mobilenetv4_conv_large.e500_r256_in1k

Image Classification • Updated Sep 2 • 1.66k • 1

Note 82.67 @ 320x320, 81.86 @ 256x256
timm/mobilenetv4_hybrid_medium.ix_e550_r256_in1k

Image Classification • Updated Sep 2 • 466 • 1

Note 82.49 @ 320x320, 81.45 @ 256x256
timm/mobilenetv4_hybrid_medium.e500_r224_in1k

Image Classification • Updated Sep 2 • 1.22k

Note 81.28 @ 256x256, 80.44 @ 224x224
timm/mobilenetv4_conv_medium.e500_r256_in1k

Image Classification • Updated Sep 2 • 8.02k

Note 80.86 @ 320x320, 79.93 @ 256x256
timm/mobilenetv4_conv_blur_medium.e500_r224_in1k

Image Classification • Updated Sep 2 • 918 • 1

Note 80.14 @ 256x256, 79.44 @ 224x224. This is a customization with blur pooling for downsample convs after the stem.
timm/mobilenetv4_conv_medium.e500_r224_in1k

Image Classification • Updated Sep 2 • 2.77k

Note 79.81 @ 256x256, 79.1 @ 224x224
timm/mobilenetv4_conv_small.e2400_r224_in1k

Image Classification • Updated Sep 2 • 13k • 7

Note 74.62 @ 256x256, 73.76 @ 224x224
timm/mobilenetv4_conv_small.e1200_r224_in1k

Image Classification • Updated Sep 2 • 2.31k • 2

Note 74.29 @ 256x256, 73.45 @ 224x224
timm/mobilenetv4_conv_small_050.e3000_r224_in1k

Image Classification • Updated Sep 22 • 916 • 4
MobileNetV4 -- Universal Models for the Mobile Ecosystem

Paper • 2404.10518 • Published Apr 16 • 2