Discussions

• 1 You must be logged in to vote

  #️⃣

  Tiny EfficentNet

  snarb asked Feb 26, 2023 in General · Unanswered

  

  

  1
• 2 You must be logged in to vote

  #️⃣

  efficientnetv2_rw_t training input size

  hyxcl asked Feb 22, 2023 in General · Unanswered

  

  

  2
• 1 You must be logged in to vote

  #️⃣

  Hyperparameters to reproduce ConvNeXt-atto/femto/pico/nano

  yuweihao asked Feb 13, 2023 in General · Answered

  

  

  2
• 2 You must be logged in to vote

  #️⃣

  Status Quo on object detection / instance segmentation

  cnut1648 asked Feb 20, 2023 in General · Unanswered

  

  

  0
• 1 You must be logged in to vote

  #️⃣

  Is there a mae model in the timm library that can be used?

  ross-Hr asked Feb 16, 2023 in General · Unanswered

  

  

  0
• 1 You must be logged in to vote

  🙏

  Does initializing the position embedding to pure zeros for ViT make it worse?

  enhancement New feature or request

  Phuoc-Hoan-Le asked Feb 11, 2023 in Q&A · Unanswered

  

  

  0
• 1 You must be logged in to vote

  🙏

  About Normalization in the PatchEmbed for Swin Transformer

  enhancement New feature or request

  Phuoc-Hoan-Le asked Feb 10, 2023 in Q&A · Unanswered

  

  

  2
• 1 You must be logged in to vote

  #️⃣

  What is the difference between INTEGER_ACCURATE in jpeg decoding and the default option in reader_tfds?

  zw615 asked Feb 9, 2023 in General · Unanswered

  

  

  0
• 1 You must be logged in to vote

  🙏

  About new release

  mostafij-rahman asked Feb 9, 2023 in Q&A · Unanswered

  

  

  0
• 1 You must be logged in to vote

  🙏

  distributed_train on 0.8.x

  drexalt asked Feb 6, 2023 in Q&A · Answered

  

  

  3
• 1 You must be logged in to vote

  #️⃣

  Are DaVit models available in the timm model library?

  chr1sba asked Feb 5, 2023 in General · Answered

  

  

  2
• 1 You must be logged in to vote

  #️⃣

  Poor Training speed of DistributedDataParallel on A40*8

  Doraemonzm asked Feb 5, 2023 in General · Answered

  

  

  1
• 1 You must be logged in to vote

  #️⃣

  Timm models work with any size of input images?

  bekhzod-olimov asked Feb 3, 2023 in General · Answered

  

  

  1
• 1 You must be logged in to vote

  🙏

  Input size of an image

  bekhzod-olimov asked Feb 2, 2023 in Q&A · Answered

  

  

  2
• 1 You must be logged in to vote

  🙏

  Using WebDataset on TPU + Google Cloud Storage

  zw615 asked Jan 13, 2023 in Q&A · Answered

  

  

  2
• 2 You must be logged in to vote

  💡

  Should we modify tracked buffer in this norm layer to support symbolic tracing?

  super-dainiu asked Jan 9, 2023 in Ideas · Unanswered

  

  

  

  

  3
• 2 You must be logged in to vote

  🙏

  Thoughts on padding images of different sizes for VisionTransformer?

  priyamtejaswin asked Dec 31, 2022 in Q&A · Unanswered

  

  

  

  

  2
• 1 You must be logged in to vote

  🙏

  Having issues with loading ViT_16_384 weights

  Divs1159 asked Jan 6, 2023 in Q&A · Unanswered

  

  

  2
• 2 You must be logged in to vote

  🙏

  Regnet training hparams

  pamolchanov asked Jan 4, 2023 in Q&A · Answered

  

  

  

  

  2
• 1 You must be logged in to vote

  #️⃣

  Using instancenorm with resnest

  jaideep11061982 asked Dec 25, 2022 in General · Unanswered

  

  

  1
• 1 You must be logged in to vote

  🙏

  What batch size number other than 1024 have you tried when training a DeiT or ViT model?

  Phuoc-Hoan-Le asked Dec 29, 2022 in Q&A · Unanswered

  

  

  0
• 1 You must be logged in to vote

  🙏

  Any place I can find the exact training method/configuration used for the pretrained models?

  rezafuru asked Dec 23, 2022 in Q&A · Answered

  

  

  3
• 1 You must be logged in to vote

  🙏

  How to use the new EVA models? (create_model reports Unknown model)

  BingliangLi asked Dec 23, 2022 in Q&A · Answered

  

  

  2
• 1 You must be logged in to vote

  🙏

  Where to find training config for trained models?

  main-2983 asked Dec 2, 2022 in Q&A · Unanswered

  

  

  

  

  2
• 1 You must be logged in to vote

  🙏

  What are the commands for training MaxViT-T to 83.6%?

  enhancement New feature or request

  xuesongnie asked Dec 10, 2022 in Q&A · Unanswered

  

  

  1