NRauschmayr commented on a change in pull request #14179: Fix READMEs for examples URL: https://github.com/apache/incubator-mxnet/pull/14179#discussion_r257406974
########## File path: example/gluon/mnist/README.md ########## @@ -0,0 +1,37 @@ +# MNIST classification example + +This script shows a simple example how to do image classification with Gluon. +The model is trained on MNIST digits image dataset and the goal is to classify the digits ```0-9```. The model has the following layout: +``` +net = nn.Sequential() +with net.name_scope(): + net.add(nn.Dense(128, activation='relu')) + net.add(nn.Dense(64, activation='relu')) + net.add(nn.Dense(10)) +``` + +The script provides the following commandline arguments: + + +``` +MXNet Gluon MNIST Example + +optional arguments: + -h, --help show this help message and exit + --batch-size BATCH_SIZE + batch size for training and testing (default: 100) + --epochs EPOCHS number of epochs to train (default: 10) + --lr LR learning rate (default: 0.1) + --momentum MOMENTUM SGD momentum (default: 0.9) + --cuda Train on GPU with CUDA + --log-interval N how many batches to wait before logging training + status +``` + +After one epoch we get the following output vector for the given test image: + +<img src="test_image.png" width="250" height="250"> Review comment: I moved all images to dmlc/web-data ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
