google-research/pix2seq

Issues

• How to perform multi-task training?

  #33 opened 2 years ago by JulioZhao97
  2

• scale factor b

  #54 opened 10 months ago by zhangdan8962
  0

• missing code for captioning task using bit diffusion

  #52 opened a year ago by bruce2233
  1

• All 3 colabs do not work out of the box

  #34 opened 2 years ago by shamitb
  6

• How to use it for more tasks, such as ocr GAN, etc ?

  #53 opened a year ago by gg22mm
  0

• how to use this to generate image captioning

  #21 opened 2 years ago by tingchihc
  1

• Convert mask to polygon

  #45 opened a year ago by zkyseu
  2

• About sequence formulation for instance segmentation

  #16 opened 2 years ago by volgachen
  3

• TypeError: 'int' object is not subscriptable

  #23 opened 2 years ago by M-Amrollahi
  8

• missing code for panoptic segmentation

  #50 opened a year ago by abred
  0

• 'ImageFont' object has no attribute 'getsize'

  #48 opened a year ago by JJJYmmm
  0

• RIN training with float16/bfloat16

  #47 opened a year ago by nicolas-dufour
  2

• RIN results on CIFAR

  #35 opened a year ago by nicolas-dufour
  6

• multitask object detection result is wrong!

  #41 opened a year ago by jiejie1993
  2

• Model weights for pix2seq-D (panoptic segmentation)?

  #46 opened a year ago by dbbert
  0

• Tensorflow2.0 installed by pip does not supprt GPU!

  #44 opened a year ago by yangmin666
  0

• How to prepare coco data in tfrecord format?

  #43 opened a year ago by yangmin666
  1

• How much time needed in the VOS task?

  #37 opened 2 years ago by isksjsksk
  2

• Trouble training RIN on CIFAR-10

  #42 opened a year ago by leon-w
  1

• coco images downloading

  #2 opened 3 years ago by Epiphqny
  5

• ValueError: coco_object_detection not registered!

  #40 opened a year ago by mimichu
  2

• Generate different inference results

  #39 opened 2 years ago by zkyseu
  2

• How to finetune on wider_face? & VOC fine-tuning colab error

  #38 opened 2 years ago by ArecaNon
  0

• How to get inference on multiple images batchwise in one go?

  #36 opened 2 years ago by sachin-rock-gh
  0

• training gets stuck

  #1 opened 3 years ago by hust-nj
  9

• Typo in the README

  #32 opened 2 years ago by JackCai1206
  1

• Cannot reproduce BLEU-4 score of 34.3 in Table 1 for image captioning task

  #31 opened 2 years ago by tj-zhu
  6

• Input Sequence Box Augmentation

  #30 opened 2 years ago by ShijieVVu
  2

• Distance Measurement

  #27 opened 2 years ago by hesamira
  3

• Visualization of Attention map

  #29 opened 2 years ago by willxxy
  0

• Question about inference

  #14 opened 2 years ago by ejlee95
  5

• Problem with installing packages

  #25 opened 2 years ago by M-Amrollahi
  0

• Video and webcam

  #24 opened 2 years ago by hesamira
  1

• Versions of libraries in the requirements.txt

  #22 opened 2 years ago by xwjabc
  1

• About ViT-B

  #20 opened 2 years ago by jihaonew
  2

• Hi ,i get the error msg like this :

  #19 opened 2 years ago by ross-Hr
  8

• The `response_seq_class_m` is used for the input sequence (why do the code randomly change the label of the Input Sequence),

  #18 opened 2 years ago by huimlight
  2

• Inconsistency between paper and code

  #10 opened 3 years ago by zyc573823770
  3

• Input multiple sequences per image

  #17 opened 2 years ago by qihao067
  1

• Training from scratch on local MSCOCO data on A100

  #6 opened 3 years ago by dipendra009
  4

• anybody knows how to train the custom datasets?

  #12 opened 2 years ago by Isaiah1013
  1

• Question about inference

  #15 opened 2 years ago by SY-Xuan
  2

• Coco-pretrained model

  #13 opened 2 years ago by ejlee95
  0

• Training Hangs forever

  #9 opened 3 years ago by shikunyu8
  1

• checksum error for downloaded data

  #7 opened 3 years ago by dipendra009
  1

• speed too slow

  #5 opened 3 years ago by lucasjinreal
  5

• typo in readme

  #4 opened 3 years ago by alexlib
  1

• Training from scratch

  #3 opened 3 years ago by logicwong
  2