Hugging Face's logo
GX Kok's picture
1 1

GX Kok

gxkok

AI & ML interests

None yet

Recent Activity

updated a model about 1 month ago
123rf-data/image-tagging-v2-base
updated a model about 1 month ago
123rf-data/image-tagging-v2-base
reacted to rwightman's post with ❤️ 4 months ago
A 'small' MobileNet-V4 update, I just pushed weights for the smallest model I've trained in the series, a 0.5 width multiplier version of the MobileNet-V4 Conv Small. Now you may look at this and say hey, why is this impressive? 64.8% top-1 and 2.2M params? MobileNetV3-Small 0.75, and MobileNet-V2 0.5 are both fewer params (at ~2M) and over 65% top-1, what gives? Well this is where MobileNet-V4 differs from the previous versions of the model family, it trades off (gives up) a little parameter efficiency for some computational efficiency. So, let's look at the speed. On a 4090 w/ torchcompile * 98K img/sec - https://huggingface.co/timm/mobilenetv4_conv_small_050.e3000_r224_in1k * 58K img/sec - https://huggingface.co/timm/mobilenetv3_small_075.lamb_in1k * 37K img/sec - https://huggingface.co/timm/mobilenetv2_050.lamb_in1k And there you go, if you have a need for speed, MNV4 is the better option.
View all activity

Organizations

123rf Data & AI's profile picture

datasets

None public yet