salman-h-khan/PL-ZSD_Release

Issues

• Question about vocabulary_w2v.txt and word_w2v.txt

  #29 opened 2 years ago by JKZhan
  0

• How was the file word_w2v.txt generated?

  #28 opened 3 years ago by xkhnhms
  0

• How to predict objects of a custom category?

  #27 opened 3 years ago by xkhnhms
  0

• How to generate embeddings for COCO classes with multiple words?

  #26 opened 3 years ago by Na-Z
  0

• The predicted scores are all zero.Have you seen this problem？

  #16 opened 5 years ago by CaiQiuYu
  4

• Train or test with cpu

  #25 opened 3 years ago by xiaofeng-c
  0

• One query regarding docker image

  #24 opened 3 years ago by SUSHIL1312
  0

• How to generate a word_w2v.txt file？

  #11 opened 5 years ago by bassyess
  5

• Generate vocabulary file for Pascal VOC dataset

  #23 opened 3 years ago by Rahn80643
  0

• Problem in running gzsd.py file

  #22 opened 3 years ago by SUSHIL1312
  1

• How to generate resnet50_csv_50_focal_seen_w2v.h5?Hoping to get your reply!

  #12 opened 5 years ago by ZhangTh2
  4

• evaluation of accuracy

  #19 opened 4 years ago by aoko-sys
  1

• Custom dataset

  #21 opened 4 years ago by manyaafonso
  0

• Error while running gzsd.py

  #20 opened 4 years ago by SodaCoder
  0

• Error when run testing code: IndexError: list index out of range

  #17 opened 5 years ago by SilonR
  3

• Error when run training code: tensorflow/core/grappler/optimizers/dependency_optimizer.cc:666] Iteration = 0, topological sort failed with message: The graph couldn't be sorted in topological order.

  #18 opened 5 years ago by EasitMickly
  0

• Error when loading weights, I want to train it on another dataset, and the num_classes is not 65

  #14 opened 5 years ago by Johumliu
  1

• for GZSD,when training,classification (Concatenate) (None, None, 65) ? why not (None, None, 80) ??

  #15 opened 5 years ago by lixiangamy
  2

• The num_classes during training and testing

  #10 opened 5 years ago by weiyaowu-md
  1

• A warning during training

  #9 opened 5 years ago by TessGreymane
  1

• train/val curve

  #13 opened 5 years ago by lsq357
  1

• Have you tried applying the politary loss function to the traditional classification problem instead of the zero shot object classification problem? I would like to know whether the effect will be better or not.

  #5 opened 5 years ago by Bigwode
  1

• Can you share train code? I want to know how to train this model. Thank you!

  #6 opened 5 years ago by TessGreymane
  2

• Some questions about the test process on unseen object detection.

  #8 opened 5 years ago by interstate50
  1

• I have some questiions about the training process. Hoping to get your reply

  #7 opened 5 years ago
  1

• can not find keras_resnet.models

  #3 opened 5 years ago by yangdb
  1

• train code?

  #2 opened 5 years ago by asdfqwer2015
  1

• can you share the training code

  #4 opened 5 years ago by TessGreymane
  2