SincNet
cnnimageretrieval-pytorch
| SincNet | cnnimageretrieval-pytorch | |
|---|---|---|
| 3 | 1 | |
| 1,097 | 1,375 | |
| - | - | |
| 0.0 | 3.2 | |
| about 3 years ago | almost 2 years ago | |
| Python | Python | |
| MIT License | 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.
SincNet
- Does this SincNet (neural architecture) contain a discriminator?
-
TypeError: layer_norm(): argument 'input' (position 1) must be Tensor, not SincNet.
the sincnet class is taken from here: https://github.com/mravanelli/SincNet/blob/master/dnn_models.py
-
[R][P] Announcing audax, a audio ML/DL framework in Jax
Code for https://arxiv.org/abs/1808.00158 found: https://github.com/mravanelli/SincNet
cnnimageretrieval-pytorch
-
[R] Any Content Based Image Retrieval Pretrained Models?
https://github.com/filipradenovic/cnnimageretrieval-pytorch is still probably the best one that is public.
What are some alternatives?
pyannote-audio - Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding
dnn_from_scratch - A high level deep learning library for Convolutional Neural Networks,GANs and more, made from scratch(numpy/cupy implementation).
speechbrain - A PyTorch-based Speech Toolkit
TorchGA - Train PyTorch Models using the Genetic Algorithm with PyGAD
Image-Forgery-Detection-CNN - Image forgery detection using convolutional neural networks. Group 10's final project for TU Delft's course CS4180 Deep Learning 2019.
stereo-image-generation - This repository contains code to generate stereo (Side by side) image from a single image.
ruptures - ruptures: change point detection in Python
DOLG-pytorch - Unofficial PyTorch Implementation of "DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Features"
UHV-OTS-Speech - A data annotation pipeline to generate high-quality, large-scale speech datasets with machine pre-labeling and fully manual auditing.
style-transfer-app - An asynchronous dual application (web + Telegram bot) for stylization images.
EasyOCR - Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.