New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Author
Label
Projects
Milestones
Assignee
Sort
What is the num_shards, Do I have to define it by myself or use the default?
#783
opened Sep 18, 2020 by
JK-Pair
decreasing input_size gives very low detection accuracy
question
#779
opened Sep 16, 2020 by
hadizand
Error during evaluation: Check failed: cudnnSetTensorNdDescriptor(handle_.get(), elem_type, nd, dims.data(), strides.data()) == CUDNN_STATUS_SUCCESS (9 vs. 0)batch_descriptor: {count: 64 feature_map_count: 64 spatial: 768 768 value_min: 0.000000 value_max: 0.000000 layout: BatchYXDepth} Fatal Python error: Aborted
question
#770
opened Sep 14, 2020 by
Pari-singh
how to fix (terminate called after throwing an instance of 'std::bad_alloc')?
duplicate
#760
opened Sep 11, 2020 by
tongxiaortx
How to hyper parameters tuning for small object (objects < 32x32)
#757
opened Sep 10, 2020 by
JK-Pair
How to load dataset without tfrecords, but with instances.xxx.json ? tfrecords cost too much disk
#752
opened Sep 8, 2020 by
xzswater
always out of memory with telsa v 100 and d7x even with batch size=4
#737
opened Sep 4, 2020 by
vxgu86
How to train EfficientDet for instance Segmentation?
question
#723
opened Sep 2, 2020 by
swapnil3597
Training bounding boxes and segmentation masks simultaneously
#653
opened Aug 4, 2020 by
robert-hardwick
Previous Next
ProTip!
Exclude everything labeled
bug with -label:bug.