Model Initialization

[authman]

If possible, could you please share the exact initialization parameters passed into ReXNetV1 in order to create ReXNetV1_2.0? The options (and defaults) are:

• input_ch=16
• final_ch=180
• width_mult=1.0
• depth_mult=1.0
• classes=1000
• use_se=True
• se_ratio=12
• dropout_ratio=0.2
• bn_momentum=0.9

My understanding is that width_mult should be set to 2. However doing so and them attempting to load the provided model weights for the -2.0 model results in many unaligned saved weights vs declared model weights. The paper isn't straightforward in providing guidance in this regard either, but that can be resolved easily, I think, the way ResNet and EfficientNet have convenience methods to build each version of their network, e.g.: https://github.com/pytorch/vision/blob/master/torchvision/models/resnet.py#L232

[authman]

Actually, this is my mistake. Just realized my input_ch was altered. For now, I'll leave the issue up though, should in case it's decided to create the convenience methods. I think they can still serve a purpose :-).

[dyhan0920]

@authman Sorry for your inconvenience. Width_mult and depth_mult are the only tunable hyper-parameters and we provided the pretrained models with respect to width_mult in this version.

Providing convenience methods as those in ResNet would be helpful to use our model. Thanks for the suggestion.