OpenGVLab/unmasked_teacher

Issues

• Features extraction and preparation of new video dataset

  #51 opened 14 days ago by mustafahalimeh
  0

• An example showing how to do fine running

  #20 opened a year ago by mustafahalimeh
  2

• 'pos_embed' key not found in downloadable checkpoints.

  #6 opened a year ago by zyoNoob
  3

• The link to the ckpt file failed

  #50 opened 2 months ago by yangshiqi2002
  2

• unable to reproduce zero-shot results

  #49 opened 3 months ago by pritamqu
  8

• [Model Evaluation] Encountering IndexError When Running run_umt_pretraining.py on a New Dataset

  #48 opened 3 months ago by kaizhuanren
  2

• cannot download checkpoints

  #47 opened 3 months ago by ShristiDasBiswas
  1

• 模型是否有中文支持

  #45 opened 3 months ago by normanShan0917
  1

• conda env conflict

  #29 opened 7 months ago by pengzhansun
  4

• Error "NoSuchBucket" When Attempting to Download Model

  #46 opened 3 months ago by kaizhuanren
  1

• About Loading Weights to text Encoder

  #44 opened 4 months ago by sushil579
  1

• 权重的读取是否有问题？

  #10 opened a year ago by gyftsy
  7

• Some questions about pretraining

  #43 opened 4 months ago by Chuan-shanjia
  3

• 下游任务训练

  #42 opened 5 months ago by miumiuc
  2

• problems about zero_evaluation

  #41 opened 6 months ago by Karine-Huang
  3

• config_dp01lr2w1e12_trimmed30.py

  #40 opened 7 months ago by tqosu
  2

• 关于下游任务

  #39 opened 7 months ago by MortironX
  1

• pre-training script and checkpoint of ssv2

  #38 opened 7 months ago by wjj-w
  1

• missing msvd_qa_answer_list.json

  #30 opened 10 months ago by tmliang
  2

• Model with resolution of 384 and clip size of 16

  #31 opened 7 months ago by mr17m
  1

• onnx model export for vision encoder and text encoder model to get embedding

  #34 opened 9 months ago by 1093842024
  2

• UMT-VIT module

  #36 opened 7 months ago by JackeyZhang1001
  3

• Missing files for SSv2

  #37 opened 7 months ago by ninatu
  2

• GPU resources to reproduce results

  #35 opened 9 months ago by wufeim
  2

• Could you provide an example of running action recognition?

  #33 opened 9 months ago by vba34520
  1

• single_modality pip install raise AssertionError: Unable to pre-compile ops without torch installed. Please install torch before attempting to pre-compile ops.

  #32 opened 9 months ago by vba34520
  2

• video-text retrieval，请教在DiDeMo数据集复现结果的问题

  #28 opened 10 months ago by SuperHalo
  4

• 关于下游任务的问题

  #24 opened a year ago by qq1332427275
  1

• What loss is used during stage-1 pre-training - "l2" or MSE loss

  #25 opened a year ago by atawari
  3

• Wrong encoder width in bert_large

  #27 opened a year ago by HyeongminLEE
  1

• Question about test video number of didemo retrieval

  #23 opened a year ago by allonsy07
  3

• Some json files are missing

  #22 opened a year ago by cmh1027
  11

• Wrong Checkpoint in Model Zoo (Multimodal)

  #26 opened a year ago by HyeongminLEE
  4

• 请教一下指标复现上出现的一些问题

  #13 opened a year ago by Noobb123
  5

• video-text retrieval MSVD数据集划分

  #12 opened a year ago by SuperHalo
  10

• out of memory

  #19 opened a year ago by JackSparrow3
  2

• Question about training MSVD.

  #14 opened a year ago by ikodoh
  10

• Question about sparse sampling

  #17 opened a year ago by yuu2704
  2

• Problem with downloading Video Question Answering ActivityNet-QA ckpt

  #15 opened a year ago by nonomanlurker
  1

• QR-Code can`t be used

  #16 opened a year ago by hayleeXinyi
  1

• Inference cost

  #11 opened a year ago by tengyu-liu
  2

• Retrieval dataset process approach

  #9 opened a year ago by Seolen
  1

• 对应的交流群还有么？目前给的链接已经失效

  #8 opened a year ago by gyftsy
  3

• multi-modal Video-Text Retrieval demo

  #7 opened a year ago by sportzhang
  1

• Include code

  #2 opened a year ago by nathankaha
  2

• Images at different resolutions compared with training size

  #5 opened a year ago by littlespray
  1

• CLIP as teacher

  #3 opened a year ago by farewellthree
  1

• Clarity on retrieval results

  #1 opened a year ago by ffnc1020
  2