-
Thank you for your excellent work !
my python = 3.5 , my pytorch = 0.4.1 , my cuda = 9.0
when I used the imagenetvid datasets to train the ATOM, and I run the "python
run_training.py bbreg atom_…
klyjb updated
5 years ago
-
I have been troubled by the randomness of `ImageNetVID`, and finally found the reason. In some versions of python, e.g. python 3.5, the cache files in JSON format will be unorderly loaded. This won't …
-
Hello, thank you for your excellent work.
my python = 3.5 , my pytorch = 0.4.1 , my cuda = 9.0
I have successfully started training ATOM on the imagenetvid dataset, as shown below:
**[train: 5, 5 …
klyjb updated
5 years ago
-
What is the right way to parallelize the evaluation?
I took the default launcher.py script and made some changes for passing in additional arguments like ckpt and model_path.
```
import subproc…
-
after 2 epochs training, when end to end train-and-test comes to this phrase, it stops at this point and doesn't continue, no error reported, the program is still running, but stucks here.
-
When I train dff by your tutorial，it only run epoch 0 and end without any checkpoints.
It seems that there comes to a problem when the training process wanna do checkpoints.
Here is the training log…
-
The version of mxnet is v0.10.0
I managed to run the demo, but when I try to train, an error occurs:
```
Namespace(cfg='experiments/fgfa_rfcn/cfgs/resnet_v1_101_flownet_imagenet_vid_rfcn_end2end_…
-
I compiled mxnet with custom operator_cxx files and run demo
`sudo python ./demo.py`
and it prints out
/usr/lib/python2.7/dist-packages/matplotlib/font_manager.py:273: UserWarning: Matplotlib…
-
Hi Orpine,
Thank you for solving the previous issues. When I train deep feature flow with r-fcn on imagenet dataset, I encounter this problem. could you please give a favor? waiting online.......…