fyu / dilation

Dilated Convolution for Semantic Image Segmentation

Home Page:https://www.vis.xyz/pub/dilation

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Runtime measurement

Timo-hab opened this issue · comments

Hi Fisher

I have measured the runtime of dilation10 with the pretrained model by following command:

/home/timo/caffe/build/tools/caffe time -gpu 0 -model /home/timo/dilation/models/dilation10_cityscapes_deploy.prototxt -iterations 10

For the measurement I use a Titan X and I get an average forward pass of 1058ms.
The input shape of the dilation10_cityscapes_deploy.prototxt is:

input: "data"
input_shape {
  dim: 1
  dim: 3
  dim: 1396
  dim: 1396
}

In the Cityscapes benchmark it says the runtime is 4s. So the question is, how did you measured it? Makes my measurement the results better as they are?

Btw. if I change the input_shape to:

input: "data"
input_shape {
  dim: 1
  dim: 3
  dim: 500
  dim: 500
}

I get a runtime of only 53 ms!
On FCN8s I get despite the same setting 134ms, although the model should be faster if compare the runtime on cityscapes benchmark.
https://www.cityscapes-dataset.com/benchmarks/#pixel-level-results

Best,
Timo

I think the reason for that is the sliding window and the label margin of 186.
For a image of 500x500 px, the input shape have to be 686x686. Therefore my comparison to FCN-8s was not right.