We are hiring ! See our job offers.
Revision e1467a79dc6580ae009d827b5e6f274faff3b339 authored by liqunfu on 27 March 2020, 21:42:04 UTC, committed by GitHub on 27 March 2020, 21:42:04 UTC
2 parents c7bc93f + a2055f6
Raw File
# CNTK Examples: Image/FeatureExtraction

## Overview

|Data:     |A small toy data set of food items in a fridge (grocery).
|Purpose   |Demonstrate how to evaluate and write out different layers of a trained model using Python.
|Network   |Pre-trained ResNet_18 model.
|Training  |None, only evaluation of different layers of the model.

## Running the example

### Getting the data

We use the `grocery` toy data set ([Examples/Image/DataSets/Grocery](../DataSets/Grocery)) and a pre-trained ResNet_18 model [PretrainedModels/ResNet18_ImageNet_CNTK.model](../../../PretrainedModels). To download both run 

`python install_data_and_model.py`

### Details

Run `python FeatureExtraction.py` to generate the output of a specific layer. Please refer to the comments in the Python code directly for how to choose different layers for evaluation.
back to top