Duo Li

Results 47 comments of Duo Li

Param and MAdd

Thanks but I'm not sure what 960x960 means.

Param and MAdd

I have tried to add one block here, as pointed out by @Rookielike, but still can not reach the params and FLOPs.

Param and MAdd

@zhoudaquan I have put my model definition in https://github.com/d-li14/mobilenext.pytorch for your checking, The FLOPs is 275M now, as also shown by others.

Param and MAdd

@zhoudaquan still confusing... https://github.com/d-li14/mobilenext.pytorch/blob/master/mobilenext.py#L48, we should change inp to oup?

Param and MAdd

@zhoudaquan but changing the above line to ```python hidden_dim = _make_divisible(round(oup // reduction_ratio), 16) ``` gives 370M flops.

Param and MAdd

so any difference between these two writing?

Question about the prototxt

@chuanqi305 I‘m also interested in `show_tensor.py` but have no clue about it. Could you please share with us? thx.

Input size issue

Also confused about this issue. Is there any update? @chuanqi305 @biycyr

Fix COCO configuration

Thanks for your modification. But I wonder that how you deal with COCO dataset? The url https://s3.amazonaws.com/amdegroot-datasets/instances_trainval35k.json.zip given in `data/scripts/COCO2014.sh` works well? Or is there any link to download **correct...

Fix COCO configuration

Thanks @ddonatien , but as far as I'm concerned, as stated in #123, just replacing instances_trainval_35k.json with valminusminival2014.json seems not reasonable.