-
Hi, thanks for the nice work. I have some concerns.
1) The graph is constructed in the mini-batch, if some images in mini-batch do not have neighbors with same labels, then the graph is useless.
…
-
Hi
I am following [1], I am running the following command, I am not able to reproduce RTE results and really appreciate any suggestions to try. thanks.
```
python3 cli.py --method pet --pattern_…
-
In the `prepro.sh`, there are some scripts used in `defaultPreprocessor` which I cant find in this repo. To reproduce the results in paper, preprocess procedure is very important. And could you guys …
-
**Describe**
I am using MiniLM, but I find that the last FFN of MiniLM is not supervised by any signals.
I am wondering whether this matters or not?
-
# Experiments design
Follow discussion [here](https://docs.google.com/document/d/110tlidAcpiNteKnA27tR5KPS_VahNqYKqCeJlu1MWww/edit#heading=h.wmf5tyes1tfk)
## pointers to code and datasets
### …
-
Thanks for your good work and open source code!
When I read the paper and code, I have a question. As far as I know, in the CSPN series of papers, the algorithm first obtains an initial depth image…
-
hi，hologerry， thanks for open source the code, I just wonder does use a detector trained on object detection dataset to generate proposal can get a better result than selective search, as detector is …
-
### The problem
Since a few versions (I don’t know if it was Home Assistant Operating System, Home Assistant Core or Home Assistant Supervisor) it takes 10-20 seconds before a log is shown.
It is re…
-
Hi,
I wonder why you set the `epoch_length=7330` in DistributedGroupSemiBalanceSampler? If the prameters like`gpu_nums, samples_per_gpu，dataset length` change，the number of iterations in one epoch w…
-
Can you please provide some information about how the supervised model and the untrained encoder are trained in the paper? My assumption is that the supervised model is trained on both `pretext group …