node-red-contrib-tf-model icon indicating copy to clipboard operation
node-red-contrib-tf-model copied to clipboard

A Node-RED node to load tensorflow model

Results 14 node-red-contrib-tf-model issues
Sort by recently updated
recently updated
newest added

Hello, I am using your method to install @tensorflow/tfjs- [email protected] that,I encountered an installation failure: Unsupported system:cpu-linux-arm64. But I still can't find his installation path, that is, The @tensorflow package...

Hi there, In some environment such as administrated cloud-based NR, saving to disk capability might be limited. Is there a way to retrieve the model and feed it directly to...

Dear @yhwang, Thanks for sharing this interesting node! I would like to _**detect objects**_ (e.g. human body or a car or ...) in images from my IP cameras. I assume...

I have convert my tensorflow model to tensorflow.js model from this https://colab.research.google.com/drive/1aWUWoKUNEfSnDE9RHhBFyHum_XIAKHUd?usp=sharing So I have got model.json and group1-shared1of1.bin from that. So I put model.json into tf.model node but it...

Hello, I have an issue while utilizing your node for loading a .json model. I have also commented on another post but I found the files and I was able...

Hi, will support for SavedModel be added soon? The reason I'm asking is that I tried loading SavedModel with tfjs-node and running into some issues. I'm running node v15.7.0, tfjs-node...

I'm relatively new to Node-Red, but there seems to be standard practice of being able to set the configuration via incoming msg properties. I have a need to set the...

I am having an issue installing on my Jetson Nano. Specifically, I get the following error upon install: `npm WARN [email protected] requires a peer of @tensorflow/tfjs-node@^1.4.0 but none is installed....

Because CUDA depends on the wrong version, I tried to recompile version 1.15, but it will report an error, what to do next ``` jiayq@jiayq-desktop:~/Desktop/tensorflow$ ./configure WARNING: ignoring LD_PRELOAD in...

Would it be possible to use a pre-install script to automatically detect the hardware it is being installed on and then create a custom-binary.json file and then run the npm...