intel/ai-reference-models

Issues

• llama2 finetune issue on Xeon

  #190 opened 6 months ago by huiyan2021
  2

• Python 3.11 support (for cloud-data-connector)

  #186 opened 7 months ago by jiridanek
  0

• Distilbert run on CPU

  #181 opened 8 months ago by swamysaranam
  0

• ResNet50 inference model seemed not support FP16

  #173 opened a year ago by chenming22
  4

• Problems with Docker, NUMA, and quickstart script for ResNet50-v1.5 on GPU Max 1100

  #177 opened 10 months ago by WarrenSchultz
  0

• Add wide&deep model support for Tensorflow Serving？

  #82 opened a year ago by 0400H
  3

• Scripts for BERT Large Training Not Found on Master Branch

  #176 opened a year ago by mins2022
  4

• Preprocess imagenet to tf records with multiple threads

  #149 opened 2 years ago by mguo2021
  4

• Error met when running BERT training on multiple nodes

  #94 opened a year ago by Eugene-Mark
  2

• DOCKER variable should be set to "False"

  #144 opened 2 years ago by gshimansky
  2

• Resnet50 v1.5 model is actually v1?

  #155 opened a year ago by xipix
  2

• 403 downloading ResNet50 models

  #175 opened a year ago by WarrenSchultz
  2

• The Bert Large training performance sometimes is wrongly calculated

  #171 opened a year ago by taotod
  1

• The variable "end_training" in Bert_Large training is wrongly used.

  #170 opened a year ago by taotod
  1

• script contains unresolved merge markers

  #169 opened a year ago by xipix
  1

• Can we provide custom epoch value in training_1_epoch.sh file by replacing any value in-place of 1

  #163 opened a year ago by Dirojit
  1

• DLRM Quantization

  #158 opened a year ago by Vasanta1
  1

• Link depreciated

  #152 opened a year ago by 12010486
  2

• VGG-16

  #132 opened 2 years ago by raistefintel
  1

• Build torch-ccl failed

  #131 opened 2 years ago by Fred-cell
  1

• System crash or shutdown in Resnet50 inference

  #113 opened 3 years ago by merazlab
  2

• Support for this notebook on Amazon SageMaker

  #111 opened 3 years ago by mandalrajiv
  4

• Query: Parallel_batches support for CNN and NLP model

  #98 opened 3 years ago by avinashcpandey
  1

• Patches missing for IntelTensorFlow_PerformanceAnalysis

  #96 opened 3 years ago by kaze31
  2

• RNNT training on CPU

  #95 opened 3 years ago by Peach-He
  1

• Several of the data links in benchmarks/.../language translation/.../bert/ are out of date, and the download_glue_data.py script has bugs

  #93 opened 3 years ago by emmacall
  1

• cannot run ssd_resnet34 int8 model with intel-tensorflow 2.5.0

  #91 opened 4 years ago by Zongru-Wen
  1

• Performance issue in /models/recommendation/tensorflow (by P3)

  #90 opened 4 years ago by DLPerf
  2

• How to distinguish between stock TensorFlow and Intel TensorFlow for 2.5.0 version quickly and conveniently.

  #89 opened 4 years ago by zhixingheyi-tian
  5

• Run more docker containters with Inter-optimized-tensorflow on One 8 physical core 16cores Cpu

  #87 opened 4 years ago by siwang2011
  3

• Can not run BERT-Large training successfully on bare metal

  #86 opened 4 years ago by zhixingheyi-tian
  3

• correct_k = correct[:k].view(-1).float().sum(0, keepdim=True) RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.

  #85 opened 4 years ago by arthw
  1

• Inconsistent "permissions" behavior between fp32 vs int8 with Resnet50 model

  #84 opened 4 years ago by brian-a-scott
  3

• How to evaluate the performance number of Bert-Large training

  #83 opened 4 years ago by zhixingheyi-tian
  2

• I had a mistake when I ran tensorflow with multiple nodes

  #81 opened 4 years ago by houyushan
  1

• error running bert following steps on IntelAI/models

  #79 opened 4 years ago by jeyblu
  1

• Need clarification upon Wide&Deep model input shapes

  #78 opened 4 years ago by rkazants
  4

• URL link in Readme is broken

  #77 opened 4 years ago by shailensobhee
  3

• What dataset are these models pretrained on?

  #70 opened 4 years ago by paulgavrikov
  1

• How can I export a optimized wide and deep model?

  #67 opened 4 years ago by lizhen2017
  2

• ResNet50 inference: fail to set device

  #148 opened 2 years ago by mguo2021
  1

• Could you provide the steps for Tensorflow BERT INT8 Inference?

  #107 opened 3 years ago by shuangpe
  1

• imagenet data conversion script returns pthread error

  #88 opened 4 years ago by manjeetbhati
  1

• Possibility of updated MKL docker image on latest 2.4.0

  #71 opened 3 years ago by dcyoung
  3

• Downloading the dataset

  #76 opened 4 years ago by jaidayal
  1

• How to run these w/out docker?

  #75 opened 4 years ago by jaidayal
  4

• INT8 model source

  #73 opened 4 years ago by AlexKoff88
  5

• How does TensorFlow handle the situation of running a training with BF16 on a CPU which does not support it?

  #64 opened 5 years ago by zhao1157
  5

• The latest docker image was not compiled to use AVX2 AVX512F FMA

  #62 opened 5 years ago by zhao1157
  3

• NGC TensorFlow image performs better than Intel-optimized TensorFlow image on Xeon(R) Gold 6242

  #63 opened 5 years ago by zhao1157
  2