MobileNetV3 issues

are there pretained models?

7

I want to have a pretained mode trained on Imagenet? can anyone help me?

TypeError: _hard_swish() missing 1 required positional argument: 'x'

This error occurred when I loaded the model。 h5_model = load_model(weight_file_path, custom_objects={'_hard_swish':_hard_swish, '_relu6':_relu6, '_return_activation':_return_activation, '_conv_block':_conv_block, '_bottleneck':_bottleneck, 'build':build}) h5_to_pb(h5_model,output_dir = output_dir,model_name = output_graph_name)

Cai-YingJie

Hi,

5

LucyGarlapati

What will shortcut do, if stride is 2?

Ur code only add output with input when the stride is 1. How about that the stride is 2?

BlueAnthony

How to change depth multiplier values?

2

Hey in you code depth multiplier value is 1 and width multiplier alpha can be configured and theoretically both seems to be different.If i change the depth multiplier value as...

anilsathyan7

Implementing Semantic Segmentation Head?

9

Firstly, thanks for the implementation of the MobileNetV3! Do you have an interest in implementing the semantic segmentation head described in section 6.4? I am currently planning to implement that,...

fzyzcjy