facebookresearch/detr

Issues

• I think there are some errors in the posted code

  #619 opened a year ago by nothing7744
  6

• GFLOPs instead of GFLOPS?

  #626 opened 10 months ago by zzowenzz
  0

• Average Precision of each class for best epoch and then it's mean

  #616 opened a year ago by FedwickErwode
  1

• Get Image masks coordinates.

  #625 opened a year ago by coolmattpanther
  0

• when the trained model is used for inference this import error comes: RuntimeError: Failed to import transformers.models.detr.modeling_detr because of the following error (look up to see its traceback): cannot import name 'experimental_functions_run_eagerly' from 'tensorflow.python.eager.def_function' (C:\Anaconda\lib\site-packages\tensorflow\python\eager\def_function.py)

  #623 opened a year ago by amit-parmar
  0

• Queries for images with low number of objects

  #620 opened a year ago by dokeefemain
  2

• Map metrics anomalies after backbone replacement

  #622 opened a year ago by arnozxn
  0

• RuntimeError: Error(s) in loading state_dict for DETRsegm:

  #621 opened a year ago by Brion112233
  2

• Why need to freeze for segmentation task after training the normal box model?

  #572 opened 2 years ago by jeong-tae
  1

• Sigmoid in bounding boxes prediction?

  #587 opened 2 years ago by ahorlbeck
  2

• the mAP is chage

  #617 opened a year ago by WenLinLliu
  0

• ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: -9) local_rank: 6 (pid: 257736) of binary: /home/public/anaconda3/envs/DL/bin/python

  #615 opened a year ago by llla123123123
  0

• box_cxcywh_to_xyxy

  #614 opened a year ago by nothing7744
  0

• Very low performance for segmentation task.

  #613 opened a year ago by lianzheng-research
  0

• using vit as image backbone

  #599 opened a year ago by FightingFighting
  1

• Why positional encoding is added to different role in encoder and decoder.

  #607 opened a year ago by Kamichanw
  1

• Process finished with exit code 137 (interrupted by signal 9: SIGKILL)Please read & provide the following

  #612 opened a year ago by 1799604432
  0

• In the paper, it is mentioned that visualizing the last layer of attention graph, how is this operation done?

  #593 opened a year ago by notfacezhi
  4

• I do not understand what the mask meaning in "samlpes"

  #611 opened a year ago by goodstudent9
  0

• Question about object queries.

  #604 opened a year ago by AjibolaPy
  4

• How to finetune DETR for semantic segmentation task?

  #610 opened a year ago by lianzheng-research
  0

• continue training with chekckpoint

  #609 opened a year ago by wiemrebhi
  0

• I have some problem about object query.

  #596 opened a year ago by Zhong-Zi-Zeng
  8

• 🐛 Bug: Architecture diagram in README.md renders incorrectly when using dark mode

  #608 opened a year ago by guillaume-troadec
  0

• I know the problem is caused by COCO label.json file, but have no clue how to solve it

  #577 opened 2 years ago by frabob2017
  1

• Why Resnet features multiplied by 0.1 in Colab notebook demo?

  #592 opened a year ago by MLDeS
  2

• I want to train the DETR model on a CPU. How can I make it possible on a small computer, 8gb RAM

  #605 opened a year ago by Bestine
  3

• if object query is random, as shown in code, how to evaluate to get a steady result?

  #597 opened a year ago by RedBlack888
  1

• What is the object query ?

  #588 opened 2 years ago by hitbuyi
  3

• what exact command you run:FutureWarning: The module torch.distributed.launch is deprecated

  #578 opened 2 years ago by 123456hxh
  2

• continuously growing memory

  #602 opened a year ago by anonymoussss
  0

• DETRsegm to torchscript

  #595 opened a year ago by Mona77
  1

• How to train with a custom dataset on mac m2?

  #601 opened a year ago by solotreeinkh
  0

• Keyerror: image_id (training detr on custom dataset

  #600 opened a year ago by chdms12
  0

• unable to download annoations from the main readme.md

  #598 opened a year ago by solotreeinkh
  0

• first decoder_layer input different with paper

  #580 opened 2 years ago by ehdrndd
  2

• using --resume, I encounter a strange problem.

  #582 opened 2 years ago by frabob2017
  3

• What does the different loss curves while training mean?

  #594 opened a year ago by Ashwin-Dhakal
  1

• DETR in raspberry pi?

  #591 opened a year ago by abhinavgogadey
  0

• Why different criteria for loss calculation and Hungarian matching

  #590 opened a year ago by MLDeS
  0

• Big misunderstanding on DETR

  #589 opened 2 years ago by Alan-D-Chen
  0

• How can I use DETR to detect rotated bbox

  #586 opened 2 years ago by spcrobocar
  1

• Error in loading weights from Model Zoo

  #583 opened 2 years ago by insafim
  0

• Convert model to TorchScript

  #581 opened 2 years ago by yingh16
  0

• It looks that DETR training time is longer than YOLO，

  #579 opened 2 years ago by frabob2017
  2

• [CRASH!] System crash/reboot on RTX 4090

  #575 opened 2 years ago by rajatmodi62
  2

• How to train with many objects

  #570 opened 2 years ago by mcondor10
  2

• max_size do not work in RandomResize()

  #574 opened 2 years ago by ZhouZhuo2022
  0

• How to convert DETR into a detection frame that can detect rotation?

  #573 opened 2 years ago by acheman
  0

• Bounding Boxes do not seem correct

  #571 opened 2 years ago by Ogusch
  0