search

Tramac / Lightweight-Segmentation

Lightweight models for real-time semantic segmentation(include mobilenetv1-v3, shufflenetv1-v2, igcv3, efficientnet).
Apache License 2.0
352 stars 77 forks source link

mobilenetv3 backbone #16

Open pawopawo opened 4 years ago

pawopawo commented 4 years ago

Thanks for your excellent work !

I print the shapes of c2 and c4 from here, [1, 112, 64, 128] and [1, 960, 64, 128] respectively. image

As shown above, c2 should be 1/8 of the input, shape should be [1, 40, 128, 256]. c4 should be 1/16 of the input picture, and shape should be [1, 160, 64, 128]

In addition, layer3_setting and layer4_setting are inconsistent with those in the paper: image

Is my understanding wrong? hope for help