1

I am using DeepLabv3+ and I am running some tests. For my first run I used an output_stride=16 and atrous_rates=[6, 12, 18] and in the 2nd run I used output_stride=8 and atrous_rates=[12,24, 36]. Then I used tensorboard to see the results and I could notice that the heatmaps look larger and one "unit" is 4x bigger than the run with output_stride=16. enter image description here

output_stride=16

enter image description here

output_stride=8 I would like to know what is the reason behing this behaviour and the consequences on my mIOU metric.

regards

vftw
  • 1,547
  • 3
  • 22
  • 51

1 Answers1

0

According to the paper Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation (3.1 DeeplabV3+ as an encoder), output_stride simply means the ratio between image input size and feature map output size (before global pooling). So change output_stride will change the output result.

just copy form link.

Mohammad Shokouhi Gol
  • 349
  • 2
  • 18