Daniel Klevebring

Any workaround available? My base image is `tensorflow/tensorflow:2.4.0-gpu` which weighs 2.35 GB compressed.

Hello! I have an idea on how to implement this that I wanted to check with you, if this is still on the table. The idea I have (a poc...

@maciejkula pinging here since it's and old thread and this might be missed otherwise :)

I love this plugin but this is driving me absolutely bananas. I would love to see a fix. Thanks!

+1 on improving the error message :D

Is anything happening to this issue? We're interested in styling our KR deployment.

Same question here: Are the model weights MIT licensed, or does that refer to the code only?

FYI, I added a method like so: ``` bool MQTT::publish(const char* topic, const char* payload, bool retain) { return publish(topic, (uint8_t*)payload, strlen(payload), retain, QOS0, NULL); } ``` With this, I...

#77 should fix this. @raenrfm @hirotakaster