Issues
- 0
PredCLS and SGCLS
#64 opened by wuzhiwei2001 - 0
The downloaded dataset contains some corrupted images, causing errors during evaluation. How can this be resolved?
#63 opened by wuzhiwei2001 - 12
Model not getting trained on single GPU
#32 opened by aryanmangal769 - 2
Unable to train on a single GPU - ChildFailedError( torch.distributed.elastic.multiprocessing.errors.ChildFailedError
#55 opened by ikram-md - 4
- 3
Inference code for Open Images?
#61 opened by ZihaoZheng98 - 1
关于openimages的数据处理问题
#58 opened by liaowang0125 - 1
Training failed on custom data set
#60 opened by ikram-md - 1
- 1
How to use the resulting weight file for evaluation
#52 opened by 48215 - 2
- 4
RuntimeError: CUDA error: device-side assert triggered CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.
#39 opened by YubeiZheng - 1
- 3
demo
#57 opened by Gezelligheid-debug - 2
- 5
1
#53 opened by 3237522375 - 1
请问如何将inference.py得到的场景图保存成一个json文件呢
#48 opened by M1091027 - 1
I can only get the relationships between entities, how can I get the scene graph?
#54 opened by AlphaGoooo - 2
name 'train_stats' is not defined
#41 opened by G200005 - 3
About OpenV6
#51 opened by xhonghu - 1
checkpoint should be updated with enhanced version
#45 opened by long8v - 3
Evaluation
#44 opened by Gezelligheid-debug - 2
- 1
Error during training in bbox.pyx : ValueError: Buffer dtype mismatch, expected 'DTYPE_t' but got 'double'
#47 opened by aelayouch - 1
about Predcls
#43 opened by xhonghu - 2
Some questions about evaluation
#38 opened by xhonghu - 0
convert the reltr model to onnx forma
#42 opened by hekkang - 7
About evaluate_rel_batch() function
#40 opened by xfufu0724 - 4
- 1
Can ur work train on VidOR?
#37 opened by Mortyzhou-Shef-BIT - 6
How to Calcualte PredCLS and SGCls ?
#20 opened by mohammedessamtga - 1
The problem of RelTR Demo.ipynb
#30 opened by rourou-droid - 2
about output
#31 opened by zhujiaxiao - 2
The problem of training time
#28 opened by Yassin-fan - 2
annotation files
#24 opened by Turkishvein - 1
About training strategy
#36 opened by Vincent-luo - 1
Evaluation on VRD dataset
#33 opened by 1799336361 - 1
- 1
Memory Utilization Issue
#26 opened by karanvora2599 - 3
demo问题
#27 opened by Zhangwt100 - 0
Number of classes of relations in VG
#29 opened by bowen-upenn - 9
cannot start training
#23 opened by Turkishvein - 3
Train and Test for custom images
#14 opened by Chenghao-Ding - 2
rel_logits vs pred_logits
#22 opened by william-han-hri - 1
- 4
Some details about Open Image v6.
#21 opened by JacobYuan7 - 3
- 2
- 3
Evaluation on Colab failing
#17 opened by IamShubhamGupto - 2
Unable to download checkpoint from drive
#16 opened by IamShubhamGupto