# Node-red-contrib-tf-model installing problem

Hi,
Im facing with installation problem of : node-red-contrib-tf-model. So, i went throught steps like here : https://www.npmjs.com/package/node-red-contrib-tf-model (skipping the Note section, cause Im working on windows ). So, when running the node-red i have some warning: `

# Welcome to Node-RED

9 Sep 09:13:19 - [info] Node-RED version: v1.1.3
9 Sep 09:13:19 - [info] Node.js version: v14.9.0
9 Sep 09:13:19 - [info] Windows_NT 10.0.18362 x64 LE
Platform node has already been set. Overwriting the platform with [object Object].
Platform node has already been set. Overwriting the platform with [object Object].
9 Sep 09:13:36 - [warn] ------------------------------------------------------
9 Sep 09:13:36 - [warn] [node-red-contrib-tf-model/tf-model] TypeError: Cannot read property 'nonMaxSuppressionV3Impl' of undefined
9 Sep 09:13:36 - [warn] ------------------------------------------------------
9 Sep 09:13:36 - [info] Settings file : \Users\kamil.298374.node-red\settings.js
9 Sep 09:13:36 - [info] Context store : 'default' [module=memory]
9 Sep 09:13:36 - [info] User directory : \Users\kamil.298374.node-red
9 Sep 09:13:36 - [warn] Projects disabled : editorTheme.projects.enabled=false
9 Sep 09:13:36 - [info] Flows file : \Users\kamil.298374.node-red\flows_BLRKEC300608L.json
9 Sep 09:13:36 - [info] Server now running at http://127.0.0.1:1880/
9 Sep 09:13:36 - [warn]

Your flow credentials file is encrypted using a system-generated key.

If the system-generated key is lost for any reason, your credentials
file will not be recoverable, you will have to delete it and re-enter

## You should set your own key using the 'credentialSecret' option in your settings file. Node-RED will then re-encrypt your credentials file using your chosen key the next time you deploy a change.

9 Sep 09:13:36 - [info] Starting flows
cpu backend was already registered. Reusing existing backend factory.
Platform node has already been set. Overwriting the platform with [object Object].
9 Sep 09:13:44 - [error] [tensorflowCoco:7a5ad5a0.8b579c] Error: The specified module could not be found.
\?\C:\Users\XXXX.node-red\node_modules\node-red-contrib-tfjs-coco-ssd\node_modules@tensorflow\tfjs-node\lib\napi-v5\tfjs_binding.node
9 Sep 09:13:44 - [info] Started flows

# ============================ Hi there �. Looks like you are running TensorFlow.js in Node.js. To speed things up dramatically, install our node backend, which binds to TensorFlow C++, by running npm i @tensorflow/tfjs-node, or npm i @tensorflow/tfjs-node-gpu if you have CUDA. Then call require('@tensorflow/tfjs-node'); (-gpu suffix for CUDA) at the start of your program. Visit https://github.com/tensorflow/tfjs-node for more details.

9 Sep 09:14:03 - [error] [cocossd:5f87102c.f40a] Error: 'transpose' not yet implemented or not found in the registry. Did you forget to import the kernel?
9 Sep 09:15:51 - [error] [cocossd:5f87102c.f40a] Error: 'transpose' not yet implemented or not found in the registry. Did you forget to import the kernel?`

Apart of that, Im not able to see the installed tf-model in the pallete. Do you have some prompts for me ?

Why did you skip the node part ? You need to install it correctly.