Closed meteorshowers closed 4 years ago
Moreover, I test your model with normal convolution,100ms on titanxp is the runtime right?
You can refer to the Table 1 in our paper for the performance without deformable conv.
May I know your test settings (e.g., resolution)? Our inference time is measured by inference.py
with --count_time
activated.
Thanks 360*1280 I do not use the deformable conv.
Are you using our code inference.py
?
no
why do not eval on the 1/8 resolution with stereonet config? It would be faseter
There is a trade-off between accuracy and speed. If speed is a priority, you can use the StereoNet-AA model.
If anyone test the inference time on titanxp, tell me, thanks
We have uploaded our timing scripts, you should use them to measure the inference time.
118.24091136 gflops 3.175282 M double check parameter 3.175282 M time 114.790651798 ms input 360*1260 device titian xp I think v100 may 1.5 times faster than titianxp, it is normal
118.24091136 gflops 3.175282 M double check parameter 3.175282 M time 114.790651798 ms input 360*1260 device titian xp I think v100 may 1.5 times faster than titianxp, it is normal
您好,能否支援一份不带dconv的代码?
can you share me the code without @@deformable
can you provide the performace without deformable conv?
can you share me the code without deformable,thank you! @meteorshowers
can you provide the performace without deformable conv?