DeepLearningExamples
deep_navigation
DeepLearningExamples | deep_navigation | |
---|---|---|
7 | 1 | |
12,642 | 4 | |
1.2% | - | |
6.1 | 2.6 | |
about 1 month ago | about 2 months ago | |
Jupyter Notebook | PureBasic | |
- | 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.
DeepLearningExamples
-
A small example from Tacotron2 trained on Brandon "Atrioc" Ewing
GitHub Used: https://github.com/NVIDIA/DeepLearningExamples/tree/master/PyTorch/SpeechSynthesis/Tacotron2
- Retraining Single Shot MultiBox Detector model on a custom data set?
-
Nvidia Scientists Take Top Spots in 2021 Brain Tumor Segmentation Challenge
Disclosure: I used to work on Google Cloud.
I dunno, their A100 results took about 20-30 minutes on 8 x A100s [1]. 8xA100s is like $24/hr on GCP at on-demand rates.
The efficiency was okay but not linear, so if you were more cost constrained you might go with 1xA100 for $3/hr and have ~2.5hr training times.
Getting that performance out of a GPU is more challenging than getting access to the GPUs. All the major cloud providers offer them.
(Nit: GCP deployed the 40 GiB cards rather than the later 80 GiB parts, but let's ignore that).
but it often doesn't matter
[1] https://github.com/NVIDIA/DeepLearningExamples/tree/master/P...
-
Tacotron2 CPU Inferencing
Entrypoint.py file in tacotron2 folder: source code
-
Skyrim Voice Synthesis Mega Tutorial
For those asking about differences to xVASynth, the models trained with xVASynth are the FastPitch models (https://github.com/NVIDIA/DeepLearningExamples/tree/master/PyTorch/SpeechSynthesis/FastPitch). As a quick explainer:
-
Modders develop AI based app for creating new voice lines using neural speech synthesis.
There's another separate tool set from Nvidia that's on GitHub that the creator used to train the models. I'm not going to pretend like I understand it, but you can find it here.
-
[R] Data Movement Is All You Need: A Case Study on Optimizing Transformers
The Nvidia's implementation of BERT has a long way to go (I don't know about the implementations of input independent gradient computations in their backprop). But, there are scaled benchmarks on DGX A100's -https://github.com/NVIDIA/DeepLearningExamples/tree/master/TensorFlow/LanguageModeling/BERT
deep_navigation
-
The right path to ROS
Implement some basic stuff: Do filtering and/or clustering on pointcloud data using PCL. Try room segmentation on a 2D gridmap using OpenCV (hint). Global planner with A* (if you don't want to implement the algorithm check my repo). Local planner using pure pursuit (or some weird stuff like this). Don't forget to check other ROS projects on GitHub and try to read the code a bit.
What are some alternatives?
lidar-harmonization - Code release for Intensity Harmonization for Airborne LiDAR
TTS - :robot: :speech_balloon: Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts)
alpaca_eval - An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
astar_pathfinder_grid_2d - Single header library for path finding on 2D grids with A* algorithm. Includes a stable and a fast path finders.
Megatron-LM - Ongoing research training transformer models at scale
tensorflow-deep-learning - All course materials for the Zero to Mastery Deep Learning with TensorFlow course.
ontogpt - LLM-based ontological extraction tools, including SPIRES
labml - 🔎 Monitor deep learning model training and hardware usage from your mobile phone 📱
llm-search - Querying local documents, powered by LLM
ydata-synthetic - Synthetic data generators for tabular and time-series data
notebooks - Notebooks illustrating the use of Norse, a library for deep-learning with spiking neural networks.
AutoCog - Automaton & Cognition