timm/mobilenetv4_hybrid_large.ix_e600_r384_in1k
Image Classification
•
Updated
•
113
•
2
MobileNetV4 pretrained weights
Weights for MobileNet-V4 pretrained in timm
Note 84.36 @ 448x448, 83.99 @ 384x384
timm/mobilenetv4_hybrid_large.e600_r384_in1k
Image Classification • Updated • 592 • 1Note 84.27 @ 448x448, 83.8 @ 384x384
timm/mobilenetv4_hybrid_medium.ix_e550_r384_in1k
Image Classification • Updated • 36 • 1Note 83.39 @ 448x448, 82.97 @ 384x384
timm/mobilenetv4_conv_large.e600_r384_in1k
Image Classification • Updated • 520 • 1Note 83.39 @ 448x448, 82.95 @ 384x384
timm/mobilenetv4_conv_large.e500_r256_in1k
Image Classification • Updated • 700Note 82.67 @ 320x320, 81.86 @ 256x256
timm/mobilenetv4_hybrid_medium.ix_e550_r256_in1k
Image Classification • Updated • 65 • 1Note 82.49 @ 320x320, 81.45 @ 256x256
timm/mobilenetv4_hybrid_medium.e500_r224_in1k
Image Classification • Updated • 520Note 81.28 @ 256x256, 80.44 @ 224x224
timm/mobilenetv4_conv_medium.e500_r256_in1k
Image Classification • Updated • 672Note 80.86 @ 320x320, 79.93 @ 256x256
timm/mobilenetv4_conv_blur_medium.e500_r224_in1k
Image Classification • Updated • 254 • 1Note 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 • 300Note 79.81 @ 256x256, 79.1 @ 224x224
timm/mobilenetv4_conv_small.e2400_r224_in1k
Image Classification • Updated • 1.99k • 1Note 74.62 @ 256x256, 73.76 @ 224x224
timm/mobilenetv4_conv_small.e1200_r224_in1k
Image Classification • Updated • 1.62k • 2Note 74.29 @ 256x256, 73.45 @ 224x224
-
MobileNetV4 -- Universal Models for the Mobile Ecosystem
Paper • 2404.10518 • Published • 2