• Automation framework: CK
  
• Development repository: ck-ml
  
• Source: GitHub
  
• Available command lines:
  
  • ck run program:image-classification-resnet-50-mxnet --cmd_key=train (META)
    
  • ck run program:image-classification-resnet-50-mxnet --cmd_key=train-and-profile (META)
    
  • ck run program:image-classification-resnet-50-mxnet --cmd_key=train-and-profile-fp32 (META)
    
• Support for host OS: any
  
• Support for target OS: any
  
• Tags: image-classification,mxnet-image-classification
  
• How to get the stable version via the client:
  
  pip install cbench
  cb download program:image-classification-resnet-50-mxnet --version=3.0.0 --all
  ck run program:image-classification-resnet-50-mxnet
• How to get the development version:
  
  pip install ck
  ck pull repo:ck-ml
  ck run program:image-classification-resnet-50-mxnet
  

ImageClassification-Inception-MXNet

This folder contains the MXNet implementation of the inception-v3 model.

Prepare Dataset

The original directory of MXNet image classification contains scripts for all MNIST, cifar10 and imagenet datasets. In our benchmark, we use only the imagenet1K dataset.

To use our benchmark, first prepare the dataset according to the following steps:

1, Download and decompress the imagenet1K 2012 dataset. Note that you need to sign up for an account at image-net.org to download the dataset. After decompressing, your dataset directory should look like this:

$ DATA_DIR=.... # put your directory here
$ ls $DATA_DIR
n01440764/
n01443537/
n01484850/
...

2, Generate the data format of RecordIO:

python dataset/im2rec.py --list True --recursive True imagenet1k $DATA_DIR
python dataset/im2rec.py --resize 480 --quality 95 --num-thread 16 imagenet1k $DATA_DIR

You should have a file named imagenet1k_train.rec generated, the size of this file is about 137G.

Run Training

We choose the following hyper-parameters for the inception-v3 models:

Learning rate: 0.1 for 30 epochs, 0.01 for 30 epochs, 0.001 for 40 epochs\ momentum: 0.9\ weight decay: 0.0001\ optimizer: sgd

We leave other hyper parameters as default.

Change the --data-train option in scripts/inception-imagenet.sh, then start the training by:

cd scripts
bash inception-imagenet.sh

Change the --batch-size option in scripts/inception-imagenet.sh if you want to use a different mini-batch size.

• 3.0.0 (2021-04-12)
• 1.0.0 (2019-10-08)

• .cm/desc.json (3 bytes)
• .cm/info.json (321 bytes)
• .cm/meta.json (1999 bytes)
• README.md (1687 bytes)
• source/symbols/__init__.py (0 bytes)
• source/symbols/resnet.py (9630 bytes)
• source/train_imagenet.py (2279 bytes)