Closed ilous12 closed 4 years ago
@ilous12 Here is the description: https://github.com/XiaoMi/mace-models/tree/master/deeplab-v3-plus
Part of the model (sub_7 ~ ResizeBilinear_2) is converted for MACE.
Thanks for reply. Deeplab had 21 label and I tried to run your model. But I got invalid result. Is It working valid? I only saw background label.
@llhe Do you know why the output shapes are 1,65,65,21 rather than 1,513,513,21?
@hoonkai We use "ResizeBilinear_2" node which has such a shape (1,65,65,21) as output.
@lydoc But if the output layer is 65x65x21, how should the 512x512 mask bitmap be built? Or is the result meant to be a 64x64 mask bitmap?
@hoonkai You can resize the output size to 512 * 512.
Hi. nice work
I will try to run my own deeplabv3plus model on mace framework. So I want to know what was model changes for mace.
I saw your description about deeplabv3plus model
I understood original deeplab v3 plus was below.
What do you fix for mace framework? Can you tell me about that? or your training code.
if you use "transform_graph", please share me command.