---
title: Machine Learning Models
slug: manufacturing-connect-edge/machine-learning-models
docTags: 
createdAt: 2022-05-13T19:02:44.000Z
---

The Analytics module allows you to execute your Machine Learning (ML) models “run time”. You can feed live data to the model and get live output from it.

:::hint{type="info"}
**Note**: To work with ML models in Analytics, your computer has to meet certain [requirements](https://www.tensorflow.org/install/gpu). If it does not, the ML-specific processors will not be available for flow building.
:::

# Create a Machine Learning Model for Upload

To upload a model to Analytics, you need a SavedModel format from [TensorFlow](https://www.tensorflow.org/guide/saved_model). Once you have created and saved a model, you must compress and zip it prior to uploading it to Analytics. SavedModel is a directory containing serialized signatures and the state needed to run them, including variable values and vocabularies. The SavedModel (`saved_model.pb`) file stores the TensorFlow model and a set of named signatures, each identifying a function that accepts tensor inputs and produces tensor outputs. SavedModels may contain multiple variants of the model.

Once your ML model is ready, proceed as follows:

1. Upload the model. See [Upload a Model](docId:2yyfQysFPMVKg6z8BB2Xb) for details. 
2. Create an analytics flow where the function processor is based on your model. 
   - TensorFlow processor for time-series data. See [Create an Analytics Flow](docId\:lwduYgQAPeDv9gmRcAmQR) for details. 
   - TensorFlow Images processor for images. See [Create an Analytics Flow](docId\:lwduYgQAPeDv9gmRcAmQR) and [TensorFlow Images Processor](docId:44XpmPYhVGuB0pEL2gyC4) for details. 
3. (Optional) Add the Tengo Script processor to modify the model output. See [Tengo Script](docId\:rHuPXOOLtmWy8QUV8Lutc) for details. 
4. Visualize the ML-based output in the [Flows Manager](docId\:q4JyT-_6f9wEAqu53lw3b) or through [Applications](docId\:UPKtM_T_EFgGSsljZ6e7S).  

# Access Analytics Models UI

**To access Analytics Models:**

1. Log in to Manufacturing Connect Edge.
2. From the Navigation panel, navigate to **Analytics **> **Models**.
   The *Models *pane appears.
   ::Image[]{src="https://api.archbee.com/api/optimize/SSUUxKZUk9bFTEPNn_6Zo/BBgSXWW2NGVeKj2mmSAfL_modelslp.png" size="80" width="969" height="565" caption="Analytics Models pane" position="center" showCaption="true"}

# Next Steps

- [Upload a Model](docId:2yyfQysFPMVKg6z8BB2Xb) 
- [Obtain Field Values from a Model](docId\:Dm4HCksO2l0IaZ4XQGrKh) 
- [Model Types](docId:-kN-es3FY4N9IZkQJvjhj)