belval / mobilenetv3 Goto Github PK

The number of the last block channel of mobilenetv3 in the paper is reduced by a factor of 2, and atrous conv is used

Have you ever tried to train on Cityscapes dataset and compare the accuracy with paper?

Collecting tensorflow-gpu==1.15.0 (from -r requirements.txt (line 35))
Could not find a version that satisfies the requirement tensorflow-gpu==1.15.0 (from -r requirements.txt (line 35)) (from versions: 0.12.1, 1.0.0, 1.0.1, 1.1.0, 1.2.0, 1.2.1, 1.3.0, 1.4.0, 1.4.1, 1.5.0,
1.5.1, 1.6.0, 1.7.0, 1.7.1, 1.8.0, 1.9.0, 1.10.0, 1.10.1, 1.11.0, 1.12.0, 1.12.2, 1.12.3, 1.13.1, 1.13.2, 1.14.0, 2.0.0a0, 2.0.0b0, 2.0.0b1)
No matching distribution found for tensorflow-gpu==1.15.0 (from -r requirements.txt (line 35))

Reverting to tensorflow-gpu==1.14 helps run the command 'pip install -r requirements.txt'