Deep Learning, NLP, NMT, AI, ML
Get Notified about vaccine availability in your location on email & sms ✉️! Vaccinator Octocat tracks & sends personalised vaccine info everday. Go get your shot ! 💉 Techstack There are two components in this app, First the webapp on which users can register & a second script that sends notification daily. python MongoDB APScheduler hosted on GCP GitHub https://github.com/mayukhpankaj/vaccinater
Read more
gcp-inspector Tool to check publicly accessible GCP bucket. What it does Checks whether the GCP bucket from the list is publicly accessible or not. Provides colored description in the cli.After creating a new project and enabling billing for it, open Cloud Shell and ensure that it points to the project you just created. Prerequisites GCP account with project. Create a GCP account with project enabled Install gsutil tool from the documentation or use pip. Run “gsutil config” to configure shell. […]
Read more
audio-tagging Audio Classification, Tagging & Sound Event Detection in PyTorch Progress: [x] Fine-tune on audio classification [ ] Fine-tune on audio tagging [ ] Fine-tune on sound event detection [x] Add tagging metrics [ ] Add Tutorial [x] Add Augmentation Notebook [ ] Add more schedulers [ ] Add FSDKaggle2019 dataset [ ] Add MTT dataset [ ] Add DESED Model Zoo AudioSet Pretrained Models Model Task mAP (%) Sample Rate (kHz) Window Length Num Mels Fmax Weights CNN14 Tagging […]
Read more
scamminator Blocking a scammer is not enough. It is time to fight back. Wouldn’t be great if there was a tool that uses Artificial Intelligence to reply to a scammer on your behalf and waste their time? This is exactly what scamminator does. Scammers have a limited amount of time available and every second wasted trying to scam an Artificial Intelligence is a second not used to scam a real person. How does it works? scamminator has three components: Telegram […]
Read more
DiscordOauth2Join Protect discord server invite links! Setup I will not help setting up the discord application, but just python. First, install the requirements. $ python3 -m pip install -r requirements.txt Once that’s finished, you can go ahead and make a config file, by doing: $ python3 main.py $ nano config.json Then you can go ahead and change the needed stuff in there. MARKED WITH “CHANGE THIS” And the last thing you have to do, is running the server. $ python3 […]
Read more
Introduction Have you ever solved a Machine Learning problem in just one go? Solving a problem using machine learning isn’t straightforward. It involves various steps to come up with an accurate solution. The process/steps to be followed for solving an ml problem is known as ML Pipeline/ML Cycle. ML Pipeline/ ML Cycle (Credits: https://medium.com/analytics-vidhya/machine-learning-development-life-cycle-dfe88c44222e) As shown in the figure, the Machine Learning pipeline consists of different steps like: Understand Problem Statement, Hypothesis Generation, Exploratory Data Analysis, Data Preprocessing, Feature Engineering, […]
Read more
Neural-Semi-Supervised-Learning-for-Text-Classification Neural Semi supervised Learning for Text Classification Under Large Scale Pretraining. Download Models and Dataset Datasets and Models are found in the follwing list. Download 3.4M IMDB movie reviews. Save the data at [REVIEWS_PATH].You can download the dataset HERE. Download the vanilla RoBERTa-large model released by HuggingFace. Save the model at [VANILLA_ROBERTA_LARGE_PATH].You can download the model HERE. Download in-domain pretrained models in the paper and save the model at [PRETRAIN_MODELS]. We provide three following models.You can download HERE. init-roberta-base: […]
Read more
Khiva Khiva is an open-source library of efficient algorithms to analyse time series in GPU and CPU. It can be used to extract insights from one or a group of time series. The large number of available methods allow us to understand the nature of each time series. Based on the results of this analysis, users can reduce dimensionality, find out recurrent motifs or discords, understand the seasonality or trend from a given time series, forecasting and detect anomalies. Khiva […]
Read more
3D_adapt_auto_driving This paper has been accpeted by Conference on Computer Vision and Pattern Recognition (CVPR) 2020. Train in Germany, Test in The USA: Making 3D Object Detectors Generalize by Yan Wang*, Xiangyu Chen*, Yurong You, Li Erran, Bharath Hariharan, Mark Campbell, Kilian Q. Weinberger, Wei-Lun Chao* Dependencies Usage Prepare Datasets (Jupyter notebook) We develop our method on these datasets: Configure dataset_path in config_path.py. Raw datasets will be organized as the following structure: dataset_path/ | kitti/ # KITTI object detection 3D […]
Read more
Image2Reverb Image2Reverb: Cross-Modal Reverb Impulse Response SynthesisNikhil Singh, Jeff Mentch, Jerry Ng, Matthew Beveridge, Iddo Drori Code for the ICCV 2021 paper [arXiv]. Image2Reverb is a method for generating audio impulse responses, to simulate the acoustic reverberation of a given environment, from a 2D image of it. Dependencies Model/Data: PyTorch>=1.7.0 PyTorch Lightning torchvision torchaudio librosa PyRoomAcoustics PIL Eval/Preprocessing: PySoundfile SciPy Scikit-Learn python-acoustics google-images-download matplotlib Resources Model Checkpoint Code Acknowlegdements We borrow and adapt code snippets from GANSynth (and this PyTorch […]
Read more