jerryji1993/DNABERT

Issues

• Using DNABert to predict expression

  #125 opened a month ago by saninta0212
  0

• Understand the attention design

  #124 opened a month ago by HelloWorldLTY
  0

• The highest possible pytorch which can run DNABERT?

  #123 opened 2 months ago by HelloWorldLTY
  1

• Which model to use for genomic variants analysis?

  #122 opened 3 months ago by nc1m
  1

• training with different k-mer

  #81 opened 2 years ago by berkuva
  3

• Creating a dataset needs very long time

  #121 opened 3 months ago by HelloWorldLTY
  1

• Request for Detailed Information on Training the Tokenizer

  #117 opened 8 months ago by a-green-hand-jack
  1

• Installation Issues.

  #120 opened 6 months ago by CodelyUnicorn
  0

• what is the masking ratio

  #119 opened 6 months ago by abhidipbhattacharyya
  0

• Release pretraining data?

  #118 opened 6 months ago by leannmlindsey
  0

• Importing error of Transformers

  #103 opened a year ago by Rofidagamal
  4

• Unable to get motif image

  #115 opened 8 months ago by wangyb97
  3

• pre-training perplexity

  #74 opened 3 years ago by gianfilippo
  1

• Pre-train

  #83 opened 2 years ago by morningsun77
  1

• DNATokenizer

  #77 opened 2 years ago by ChengkuiZhao
  3

• the seq longer than 512

  #113 opened a year ago by SSHH007
  0

• install packages using pip

  #112 opened a year ago by lingfengxu
  2

• Shape of atten.npy

  #111 opened a year ago by salehsereshkiucr
  0

• benchmark for the time and computation cost during the fine-tuning

  #110 opened a year ago by Shicheng-Guo
  0

• Pretraining error

  #109 opened a year ago by liu3zhenlab
  0

• attention maps generated in pre-training stage or fine-turning stage

  #108 opened a year ago by Shicheng-Guo
  0

• Finetuning Issue with Example Data

  #78 opened 2 years ago by mosala777
  4

• Trained on mouse?

  #82 opened 2 years ago by gdolsten
  1

• How can I create my own processor?

  #101 opened 2 years ago by dominiclopez391
  1

• AssertionError in kmer2seq for motif search

  #105 opened a year ago by Vejni
  0

• How to get the high attention regions of a given sequence.

  #104 opened a year ago by ytye2010
  0

• There is a bug about attention mask in source code

  #102 opened 2 years ago by Jason941
  0

• How Can I track model loss and accuracy of each epoch during fine-tuning, to make sure model is stable?

  #99 opened 2 years ago by XuanrZhang
  0

• early_stop not being triggered?

  #98 opened 2 years ago by jackievaleri
  0

• Changing max_seq_length does not update max_length in config.json

  #97 opened 2 years ago by jackievaleri
  0

• How to divide our own dataset into test, dev and train data and assign them labels for fine tuning process

  #96 opened 2 years ago by smruti241
  2

• Is there an implementation in huggingface?

  #88 opened 2 years ago by yyou1996
  1

• provided example does not use GPU

  #95 opened 2 years ago by ekg
  1

• Long training time and overfitting when reproducing your example

  #73 opened 3 years ago by warm-ice0x00
  1

• Readme section 5.2

  #89 opened 2 years ago by mepster
  4

• Can you use the pre-trained BERT models, but add novel tokens to the vocabulary?

  #94 opened 2 years ago by mepster
  0

• comparing DNABERT to where it was forked from transformers

  #93 opened 2 years ago by mepster
  0

• Transformers not recognized in test run

  #92 opened 2 years ago by leannmlindsey
  0

• cannot import name 'BertForLongSequenceClassification'

  #84 opened 2 years ago by vedashreebhandare
  4

• Reverse complement of a sequence

  #91 opened 2 years ago by ariannap88
  0

• How to use `--task_name dnasplice`?

  #90 opened 2 years ago by ajoudaki
  0

• Your masking of 6 consecutive tokens lets MLM pre-training trivially learn from the adjacent tokens

  #86 opened 2 years ago by rcasero
  0

• Steps required for pre-training completion

  #85 opened 2 years ago by smruti241
  0

• Intermdiate layers output

  #80 opened 2 years ago by FAhtisham
  0

• Add custom tokens to DNATokenizer

  #79 opened 2 years ago by WENHUAN22
  0

• Adding a license?

  #76 opened 2 years ago by ksarmentrout
  1

• Long DNA seqs embeddings

  #72 opened 3 years ago by rominaappierdo
  0

• Getting the last hidden state of the encoder

  #71 opened 3 years ago by bill-95
  1

• DNA BERT : MISMATCH in the saved fine_tuned model and the model loaded after fine tuning

  #70 opened 3 years ago by FAhtisham
  0

• error

  #69 opened 3 years ago by Moy4e
  0