siddagra
siddagra
ids are supposed to start from 1 and increase sequentially. Many dataloaders and libraries for COCO will give errors and not work with this haphazard id indexing.
Enabling mixed precision using: ``` python3 train_net.py --config-file configs/sparse_inst_r50vd_dcn_giam_aug.yaml --num-gpus 1 SOLVER.AMP.ENABLED True ``` causes error: ``` Traceback (most recent call last): File "train_net.py", line 180, in launch( File "/home/siddharth/.local/lib/python3.8/site-packages/detectron2/engine/launch.py",...
How much memory does this use while inferencing? It is trying to allocate 12GB and there is no option for changing batch sizes in these scripts either (test_net.py and demo.py)....
I am having an issue... Whether I use `src` or `dst` coords.. `image-` or otherwise, It often detects junctions as `dst` instead of the endpoints. How do I specifically get...
Just a request if you perhaps have any advice of how to improve performance on two line recognition. I am working on a dataset of 2000 images only, it has...
None of the codes working, all give errors: RuntimeError: output with shape [1, 28, 28] doesn't match the broadcast shape [3, 28, 28] IndexError: invalid index of a 0-dim tensor....
I have a relatively small dataset of a different format (license plates) and it often gets license plate format wrong. I was wondering if there was a way to train...
This error shows up often because many different mods have non-unicode characters. I am unsure why this is even required and why you cannot just replace it with some completely...
Dataset seems to be missing. Completely empty with no code. Any way to retrieve the dataset for training?
I use Control+Shift+P command to then minify directory, js directory minifies fine, but not CSS?