-
Trying to train Flownet2S using following command.
python main.py --model FlowNet2S --save_flow --training_dataset MpiSintelClean --training_dataset_root /home/meghanabasavaraj/Desktop/Meghana/Flow…
-
Hello,
I was trying to run Inference code of the FlowNet2.0 using the FlowNet2C pretrained model you provided on the MPI-Sintel dataset using following command (from PyCharm): /data/users/milan/fl…
-
The command I used for inference step.
`python main.py --crop_size 384 512 --inference --model FlowNet2C --save_flow --inference_dataset MpiSintelClean --inference_dataset_root /home/tushar/data/…
-
Did you benchmark on Sintel? The official repository puts the files into subfiles alley, bamboo etc ...
Either I am not using it correctly or the mpisintel.py loader doesn't take that into account. …
bkvie updated
6 years ago
-
Provided by ChuanweiZhou
Dataset: FlyingChairs path:/data3/FlyingChairs/FlyingChairs size: 1.1T
keywords: optical flow estimation
homepage: https://lmb.informatik.uni-freiburg.de/resources/datase…
-
When I try to run flownet2 with this input
python main.py --batch_size 8 --model FlowNet2C --optimizer=Adam --optimizer_lr=1e-4 --loss=MultiScale --loss_norm=L1 \
--loss_numScales=5 --loss_startSc…
-
I can't download the MPI-Sintel flow datasets from the official website. Could everyone share the dataset by google drive?
-
Hi, I have trained the FlowNet2C model and want to test it but I meet the following errors.
Here is the command I am excuting.
```
python main.py --inference --model FlowNet2C --save_flow --inf…
-
Hi, I‘m not clear why in a single epoch, the train_loader just didn't stop to perform validation process.
I set the batch size as 8, and epoch size to be 80. Then I assume each epoch will have 10 ite…
-
I am getting this error. I said protobuf is both too old and too new. I am not sure what the error is.
[log.txt](https://github.com/lmb-freiburg/flownet2/files/1468447/log.txt)