apple/ml-cvnets

Issues

• [MLX Backend] CVNets

  #108 opened 2 months ago by cvnad1
  1

• update to newest coremltools

  #107 opened 5 months ago by imerish
  0

• wget https://docs-assets.developer.apple.com/ml-research/models/cvnets-v2/examples/vit/classification/vit_base.pt

  #106 opened 6 months ago by tutu96177
  0

• Main_train Error

  #105 opened 7 months ago by rokkamaravind321
  3

• ERROR - total_loss not present in the dictionary. Available keys are: []. Exiting!!!

  #104 opened 9 months ago by 111hyq111
  0

• How to load MobileViT for my project

  #69 opened 2 years ago by Sehaba95
  5

• Inconsistent Results for MobileVIT v1 Models

  #68 opened 2 years ago by hzphzp
  5

• 'nan' loss when training 'ByteFormer' using ImageNet

  #103 opened a year ago by minguinho26
  0

• Normalization Params

  #102 opened a year ago by i-vee
  0

• How to solve this problem:ModuleNotFoundError: No module named 'cvnets.models.classification.'

  #101 opened a year ago by acrlife
  5

• Questions about the file bytes length of ByteFormer

  #100 opened a year ago by DanJun6737
  3

• AttributeError: 'NoneType' object has no attribute 'size'

  #99 opened a year ago by Tranbaber
  2

• bug in coco_ssd.py

  #76 opened a year ago by MLRadfys
  2

• Question: Do you have removed the support for video classification?

  #89 opened a year ago by MasterHM-ml
  2

• Not possible to test ByteFormer

  #80 opened a year ago by zangobot
  5

• crash if different number of classess within `train/test` set

  #90 opened a year ago by mjamroz
  6

• ModuleNotFoundError: No module named 'main_train'

  #97 opened a year ago by Tranbaber
  0

• ModuleNotFoundError: No module named 'main_train'

  #98 opened a year ago by Tranbaber
  0

• How to convert segmentation model results into VNInstanceMaskObservation?

  #93 opened a year ago by darwinharianto
  4

• VIT-tiny weights and config dont match?

  #92 opened a year ago by nemcekova
  1

• Using vision transformers for different image resolutions

  #95 opened a year ago by Oussamab21
  1

• ModuleNotFoundError: No module named 'main_train'

  #94 opened a year ago by prsbsvrn
  2

• The license of pretrained weights

  #88 opened a year ago by alzaia
  0

• Size mismatch error when loading a pretrained model

  #87 opened a year ago by jackywangtj66
  1

• Segmentation model conversion size mismatch

  #86 opened a year ago by darwinharianto
  1

• [Feature Request] Docker container

  #84 opened a year ago by saad-palapa
  0

• Cross Attention Computation in LinearSelfAttention()

  #81 opened a year ago by goutamyg
  0

• ByteFormer code and pre-trained models

  #77 opened a year ago by zangobot
  2

• Runtime error on single GPU Linux environment training

  #79 opened a year ago by darwinharianto
  1

• cannot run conversion example

  #78 opened a year ago by darwinharianto
  2

• add apple's new model: FastViT

  #73 opened 2 years ago by rotem154154
  4

• Training SSDLite-MobileViTv2-2.0 object detection model

  #75 opened 2 years ago by MLRadfys
  1

• Converting foundation models to coreml

  #71 opened 2 years ago by lukasugar
  0

• how to use the model to eval the imagenet1K

  #74 opened 2 years ago by neverstoplearn
  0

• Training process of Mask R-CNN crashes when workers parameter is greater than 0

  #67 opened 2 years ago by cywinski
  2

• ImageNet-22k Pre-trained Models

  #72 opened 2 years ago by goutamyg
  0

• MobileViT (version 1) pre-training dataset

  #56 opened 2 years ago by YHYeooooong
  4

• train_2017.txt in coco_preprocess

  #70 opened 2 years ago by siangyang
  2

• there is a code defect need to fix

  #63 opened 2 years ago by Light-Reflection
  1

• classification mobilevit_v2 model，where can I find softmax activation layer？

  #66 opened 2 years ago by chenying99
  3

• Size mismatch for ssd_heads when using the pretrained model

  #62 opened 2 years ago by QiqLiang
  6

• Get different accuracy on different GPU

  #59 opened 2 years ago by jimmylin0979
  4

• Model stability problem

  #54 opened 2 years ago by Xinjie-Wei
  3

• module 'torchvision.transforms' has no attribute 'RandAugment'

  #61 opened 2 years ago by liamsun2019
  2

• May I ask which version of imagenet are you using?

  #60 opened 2 years ago by Eggydan
  2

• choose warm up iterations problem

  #52 opened 2 years ago by Xinjie-Wei
  2

• Confusion matrix is None. Check code Error

  #53 opened 2 years ago by HaoWuSR
  1

• ERROR - Nan encountered in the loss.

  #55 opened 2 years ago by blossom-lv
  1

• Use extra coco dataset for segmentation

  #57 opened 2 years ago by zhangzjn
  1

• About Dataset collate fn

  #58 opened 2 years ago by YHYeooooong
  2