textgenrnn
donkeycar
textgenrnn | donkeycar | |
---|---|---|
7 | 5 | |
4,943 | 3,011 | |
- | 1.3% | |
0.0 | 5.7 | |
almost 2 years ago | 5 days ago | |
Python | Python | |
GNU General Public License v3.0 or later | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
textgenrnn
-
Modern alternative to textgenrnn?
Try this: 1) (Not sure if that's necessary.) Uninstall textgenrnn: pip3 uninstall textgenrnn. 2) Install it using one of this commands: * pip3 install git+git://github.com/minimaxir/textgenrnn.git * pip3 install git+https://github.com/minimaxir/textgenrnn.git (Try the first one, but if it'll raise an error, try the second one.) That's discussion about this "multi_gpu_model not found" error: https://github.com/minimaxir/textgenrnn/issues/222.
-
How do you get a Python IDE to execute Python code?
Thanks! PyCharm seems to work well enough. However, I'm not sure how to run an existing project. I successfully imported this github release: https://github.com/minimaxir/textgenrnn But I don't see any "main" file that can be executed. If I run the "setup.py" file, it complains that there is "no command to be executed." Also, import commands seem to fail, even though I literally have the files in the project that I'm trying to import. :/ I don't know how I'm supposed to run commands defined in the project if they can't be imported into a script.
-
I trained a neural network on every town and village name in England and then made a website that lets you generate them
This is an utterly fantastic question but I actually don't understand much about neural nets at all, and am just using a prebuilt python library is basically text based neural nets for idiots (https://github.com/minimaxir/textgenrnn) Happy to share data though if you want to find this out and would know how?
-
The Office - an episode generated by NN
Python package: Textgenrnn
-
makeitmetal.net - A metal band name generator using Python/Tensorflow
I started off with the model from textgenrnn, which is an RNN with LSTM layers. I'm not an expert on deep learning or different model architectures, and textgenrnn is a great starting point because you can use pretrained weights as a starting point for your model. I tweaked the model architecture slightly to allow multiple context labels, but most of the work on this project was porting the model to TensorFlow.js so it could run in the browser once I'd trained it in Python.
-
What's wrong with my import?
Is it installed? https://github.com/minimaxir/textgenrnn#usage
donkeycar
-
embedded ML graduation project ideas
The donkey car community is also a good ressource, but based around the Raspberry Pi and a lot more complex: https://www.donkeycar.com/
-
Considering buying this - very mixed reviews on Amazon - what's your experience?
I got it when it first came out. It was backlogged for a really long time. I'm not sure if they changed it but you need to use SageMaker to train it. I prefer training on my own gpu. I was going to use it for DIY Robocars but then covid hit. Build a Donkeycar instead. https://www.donkeycar.com/
- GitHub - autorope/donkeycar: Open source hardware and software platform to build a small scale self driving car.
- Donkeycar: A Python self driving library
What are some alternatives?
gpt-2-simple - Python package to easily retrain OpenAI's GPT-2 text-generating model on new texts
surrortg-sdk - Surrogate python sdk for controlling devices on surrogate.tv
deepface - A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python
Gravis - Gravis is an open-source robot with the goal of having advanced features at a low cost
d2l-en - Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.
ActionAI - Real-Time Spatio-Temporally Localized Activity Detection by Tracking Body Keypoints
Spectrum - Spectrum is an AI that uses machine learning to generate Rap song lyrics
minifi-jetson-nano - MiNiFi Agent Configuration and Scripts for NVidia Jetson Nano device
DeepAA - make ASCII Art by Deep Learning
afeka-mtg-detector
autokeras - AutoML library for deep learning
Lego-generator