interdigitalinc / festa Goto Github PK

Hi. Thanks for sharing your code.
I run FESTA on my GTX 1080TI and change epoch from 500 to 100.
After training, i run the test.sh, but there is the error i cannot solve:

Traceback (most recent call last):
  File "/root/.pycharm_helpers/pydev/pydevd.py", line 1483, in _exec
    pydev_imports.execfile(file, globals, locals)  # execute the script
  File "/root/.pycharm_helpers/pydev/_pydev_imps/_pydev_execfile.py", line 18, in execfile
    exec(compile(contents+"\n", file, 'exec'), glob, loc)
  File "/root/FESTA/train.py", line 467, in <module>
    main()
  File "/root/FESTA/train.py", line 430, in main
    net.load_state_dict(checkpoint['state_dict'])
KeyError: 'state_dict'

I have debugged this code, i found there is no dict which named 'state_dict' in model.best.t7.
I am expecting your kindly Reply.

Hi, how is the point cloud visualization in the paper done, it looks very 3D stereoscopic.

Thank you so much for sharing you code ..
May I ask you please about the difference between the result on your paper and the previous works like PointPWC-Net, HPLFlowNet, PV-RAFT ? and how do get a different results for these works while they are not mentioned in their original papers? Is there a specific way to calculate these values?

Thanks in advance and hope you can see and answer my question..

Hi,
Thanks for this wonderful project! Can you share the pre-trained model on Flyingthings3D?
Besides, I only use the geometry information to train FESTA on FlyingThings3D, it cannot achieve the EPE of 0.1253.
Final test results on FlyingThings3D:
mean test loss: 0.024688
mean test epe_3d: 0.134604
mean test acc_3d: 0.363211
mean test 3d_2_sum: 0.686857
mean test mask_sum: 0.160795
mean test epe_3d end: 0.133733
mean test acc_3d end: 0.363290
mean test 3d_2_sum end: 0.687539
mean test mask_sum end: 0.160651
Final test results on KITTI without fine tuning:
mean test loss: 0.028747
mean test epe_3d: 0.153715
mean test acc_3d: 0.197930
mean test 3d_2_sum: 0.579847
mean test mask_sum: 0.071703
mean test epe_3d end: 0.152873
mean test acc_3d end: 0.197633
mean test 3d_2_sum end: 0.580544
mean test mask_sum end: 0.070945.
The results are worse than the results listed in Table2. I wonder if some parameters need to be adjusted！