hszhao / ICNet

ICNet for Real-Time Semantic Segmentation on High-Resolution Images, ECCV2018
https://hszhao.github.io/projects/icnet
605 stars 199 forks source link

Code available? #1

Open ThomasLengeling opened 7 years ago

ThomasLengeling commented 7 years ago

Hi Hengshuang,

I am wondering if by any chance your code is available for test? Thank you

hszhao commented 7 years ago

Yeah, will be available no later than the end of May, possibly after nips ddl. Thanks.

weitaoatvison commented 7 years ago

Hi, I am confused about the tricks you made the ICNET to achieve at 30FPS on PSPNET50. In your paper you introduced the details of compression method you choose. But In Section 6.1, you said "When directly compressing PSPNet50 following our previously described procedure, 170ms inference time is yielded with mIoU reducing to 67.9% as shown in Table 3. They indicate that only model compression has almost no chance to achieve realtime performance under the condition of keeping decent segmentation quality. In what follows, we take the model compressed PSPNet50, which is reasonably accelerated, as our baseline system for comparison." So, I am confused if the speedup of the ICNET is come from the compressed PSPNet50 model you take and not come from the compression method you take?

StuvX commented 7 years ago

My understanding is that the speedup is largely from an optimisation of model depth balanced against image resolution - so parallel inference is run using: 1: full resolution through 4 layer model, 2: 1/2 resolution through 8 layer model, and 3: 1/4 resolution through 16 layer model. The inference is combined to produce the output in ~30 ms.

ysh329 commented 7 years ago

mark

johnsonice commented 7 years ago

mark, looking forward for it.

soeaver commented 7 years ago

mark

world4jason commented 7 years ago

still waiting for u lol

marshallixp commented 7 years ago

mark

tobschmidt commented 7 years ago

any update?

hszhao commented 7 years ago

Dear all, thanks for the patience, the evaluation code is ready now.

mehulmodihb commented 6 years ago

HI, can you please let me know how to implement same feature on iOS/Android mobile application for background subtraction.