EfficientNet Trained on ImageNet with RandAugment

Identify the main object in an image

Released in 2019, this model utilizes the techniques of RandAugment data augmentation on the EfficientNet architectures to effectively perform image classification.

Number of models: 2

Training Set Information

ImageNet Large Scale Visual Recognition Challenge 2012 classification dataset, consisting of 1.2 million training images, with 1,000 classes of objects.

Performance

The models achieve the following accuracies on the original ImageNet validation set.

Examples

Download Example Notebook

Open in Wolfram Cloud

Resource retrieval

Get the pre-trained net:

In[1]:=

Out[1]=

NetModel parameters

This model consists of a family of individual nets, each identified by a specific parameter combination. Inspect the available parameters:

In[2]:=

$NetModel["EfficientNet Trained on ImageNet with RandAugment", \ "ParametersInformation"]$

Out[2]=

Pick a non-default net by specifying the parameters:

In[3]:=

Out[3]=

Pick a non-default uninitialized net:

In[4]:=

Out[4]=

Basic usage

Classify an image:

In[5]:=

(* Evaluate this cell to get the example input *) CloudGet["https://www.wolframcloud.com/obj/073a1403-557f-439a-af50-c40fa95ae664"]

Out[5]=

The prediction is an Entity object, which can be queried:

In[6]:=

Out[6]=

Get a list of available properties of the predicted Entity:

In[7]:=

Out[7]=

Obtain the probabilities of the 10 most likely entities predicted by the net:

In[8]:=

(* Evaluate this cell to get the example input *) CloudGet["https://www.wolframcloud.com/obj/0c14ef93-75d7-4dda-b9fa-cf616056cac5"]

Out[8]=

An object outside the list of the ImageNet classes will be misidentified:

In[9]:=

(* Evaluate this cell to get the example input *) CloudGet["https://www.wolframcloud.com/obj/51af2229-5046-4c9a-8ee5-252b80f9bc4c"]

Out[9]=

Obtain the list of names of all available classes:

In[10]:=

EntityValue[
NetExtract[
NetModel["EfficientNet Trained on ImageNet with RandAugment"], "Output"][["Labels"]], "Name"]

Out[10]=

Feature extraction

Remove the last two layers of the trained net so that the net produces a vector representation of an image:

In[11]:=

Out[11]=

Get a set of images:

In[12]:=

(* Evaluate this cell to get the example input *) CloudGet["https://www.wolframcloud.com/obj/d23620ff-d336-4b21-9a53-de01a354a1d1"]

Visualize the features of a set of images:

In[13]:=

Out[13]=

Visualize convolutional weights

Extract the weights of the first convolutional layer in the trained net:

In[14]:=

Out[14]=

In[15]:=

$weights = NetExtract[ NetModel[ "EfficientNet Trained on ImageNet with RandAugment"], \ {"stem_conv", "Weights"}];$

Show the dimensions of the weights:

In[16]:=

Out[16]=

Visualize the weights as a list of 48 images of size 3x3:

In[17]:=

Out[17]=

Transfer learning

Use the pre-trained model to build a classifier for telling apart images of motorcycles and bicycles. Create a test set and a training set:

In[18]:=

(* Evaluate this cell to get the example input *) CloudGet["https://www.wolframcloud.com/obj/de6cc77a-c36c-459e-8830-008177a6d5d3"]

In[19]:=

(* Evaluate this cell to get the example input *) CloudGet["https://www.wolframcloud.com/obj/3e7470e3-dccb-421a-adc6-e537afc3bf02"]

Remove the linear layer from the pre-trained net:

In[20]:=

Out[20]=

Create a new net composed of the pre-trained net followed by a linear layer and a softmax layer:

In[21]:=

newNet = NetChain[<|"pretrainedNet" -> tempNet, "linearNew" -> LinearLayer[], "softmax" -> SoftmaxLayer[]|>, "Output" -> NetDecoder[{"Class", {"bicycle", "motorcycle"}}]]

Out[21]=

Train on the dataset, freezing all the weights except for those in the "linearNew" layer (use TargetDevice -> "GPU" for training on a GPU):

In[22]:=

$trainedNet = NetTrain[newNet, trainSet, LearningRateMultipliers -> {"linearNew" -> 1, _ -> 0}]$

Out[22]=

Perfect accuracy is obtained on the test set:

In[23]:=

Out[23]=

Net information

Inspect the number of parameters of all arrays in the net:

In[24]:=

$Information[ NetModel["EfficientNet Trained on ImageNet with RandAugment"], \ "ArraysElementCounts"]$

Out[24]=

Obtain the total number of parameters:

In[25]:=

$Information[ NetModel["EfficientNet Trained on ImageNet with RandAugment"], \ "ArraysTotalElementCount"]$

Out[25]=

Obtain the layer type counts:

In[26]:=

$Information[ NetModel["EfficientNet Trained on ImageNet with RandAugment"], \ "LayerTypeCounts"]$

Out[26]=

Export to MXNet

Export the net into a format that can be opened in MXNet:

In[27]:=

Out[27]=

Export also creates a net.params file containing parameters:

In[28]:=

Out[28]=

Get the size of the parameter file:

In[29]:=

Out[29]=

Construction Notebook

Download Construction Notebook

Open in Wolfram Cloud

Requirements

Wolfram Language 12.1 (March 2020) or above

Resource History

Date Created: 12 January 2021

Reference

E. Cubuk, B. Zoph, J. Shlens, Q. Le, "RandAugment: Practical Automated Data Augmentation with a Reduced Search Space," arXiv:1909.13719 (2019)
M. Tan, Q. Le, "EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks," arXiv:1905.11946 (2019)
Available from:
- https://github.com/tensorflow/tensorflow/blob/v2.3.1/tensorflow/python/keras/applications/efficientnet.py
- https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet