Improving Semantic Segmentation (U-Net) Performance Via Ensemble of Multiple Trained Networks

Improving semantic segmentation (U-Net) performance via ensemble of multiple trained networks.
ResNet34 + Inception V3 + VGG16

Code generated in the video can be downloaded from here:

https://github.com/bnsreenu/python_fo… ​

The dataset used in this video can be downloaded from the link below. This dataset can be used to train and test machine learning algorithms designed for multiclass semantic segmentation. Please read the Readme document for more information.

https://drive.google.com/file/d/1HWtB…

Subscribe: https://www.youtube.com/channel/UC34rW-HtPJulxr5wp2Xa04w/featured

#u-net #deep-learning

What is GEEK

Buddha Community

jQuery Ajax CRUD in ASP.NET Core MVC with Modal Popup

In this article, we’ll discuss how to use jQuery Ajax for ASP.NET Core MVC CRUD Operations using Bootstrap Modal. With jQuery Ajax, we can make HTTP request to controller action methods without reloading the entire page, like a single page application.

To demonstrate CRUD operations – insert, update, delete and retrieve, the project will be dealing with details of a normal bank transaction. GitHub repository for this demo project : https://bit.ly/33KTJAu.

Sub-topics discussed :

• Form design for insert and update operation.
• Display forms in modal popup dialog.
• Form post using jQuery Ajax.
• Implement MVC CRUD operations with jQuery Ajax.
• Loading spinner in .NET Core MVC.
• Prevent direct access to MVC action method.

Create ASP.NET Core MVC Project

In Visual Studio 2019, Go to File > New > Project (Ctrl + Shift + N).

From new project window, Select Asp.Net Core Web Application_._

Once you provide the project name and location. Select Web Application(Model-View-Controller) and uncheck HTTPS Configuration. Above steps will create a brand new ASP.NET Core MVC project.

Setup a Database

Let’s create a database for this application using Entity Framework Core. For that we’ve to install corresponding NuGet Packages. Right click on project from solution explorer, select Manage NuGet Packages_,_ From browse tab, install following 3 packages.

Now let’s define DB model class file – /Models/TransactionModel.cs.

public class TransactionModel
{
    [Key]
    public int TransactionId { get; set; }

    [Column(TypeName ="nvarchar(12)")]
    [DisplayName("Account Number")]
    [Required(ErrorMessage ="This Field is required.")]
    [MaxLength(12,ErrorMessage ="Maximum 12 characters only")]
    public string AccountNumber { get; set; }

    [Column(TypeName ="nvarchar(100)")]
    [DisplayName("Beneficiary Name")]
    [Required(ErrorMessage = "This Field is required.")]
    public string BeneficiaryName { get; set; }

    [Column(TypeName ="nvarchar(100)")]
    [DisplayName("Bank Name")]
    [Required(ErrorMessage = "This Field is required.")]
    public string BankName { get; set; }

    [Column(TypeName ="nvarchar(11)")]
    [DisplayName("SWIFT Code")]
    [Required(ErrorMessage = "This Field is required.")]
    [MaxLength(11)]
    public string SWIFTCode { get; set; }

    [DisplayName("Amount")]
    [Required(ErrorMessage = "This Field is required.")]
    public int Amount { get; set; }

    [DisplayFormat(DataFormatString = "{0:MM/dd/yyyy}")]
    public DateTime Date { get; set; }
}

C#Copy

Here we’ve defined model properties for the transaction with proper validation. Now let’s define  DbContextclass for EF Core.

#asp.net core article #asp.net core #add loading spinner in asp.net core #asp.net core crud without reloading #asp.net core jquery ajax form #asp.net core modal dialog #asp.net core mvc crud using jquery ajax #asp.net core mvc with jquery and ajax #asp.net core popup window #bootstrap modal popup in asp.net core mvc. bootstrap modal popup in asp.net core #delete and viewall in asp.net core #jquery ajax - insert #jquery ajax form post #modal popup dialog in asp.net core #no direct access action method #update #validation in modal popup

PyTorch Unsupervised Sentiment Discovery

** DEPRECATED **

This repo has been deprecated. Please visit Megatron-LM for our up to date Large-scale unsupervised pretraining and finetuning code.

If you would still like to use this codebase, see our tagged releases and install required software/dependencies that was available publicly at that date.

PyTorch Unsupervised Sentiment Discovery

This codebase contains pretrained binary sentiment and multimodel emotion classification models as well as code to reproduce results from our series of large scale pretraining + transfer NLP papers: Large Scale Language Modeling: Converging on 40GB of Text in Four Hours and Practical Text Classification With Large Pre-Trained Language Models. This effort was born out of a desire to reproduce, analyze, and scale the Generating Reviews and Discovering Sentiment paper from OpenAI.

The techniques used in this repository are general purpose and our easy to use command line interface can be used to train state of the art classification models on your own difficult classification datasets.

This codebase supports mixed precision training as well as distributed, multi-gpu, multi-node training for language models (support is provided based on the NVIDIA APEx project). In addition to training language models, this codebase can be used to easily transfer and finetune trained models on custom text classification datasets.

For example, a Transformer language model for unsupervised modeling of large text datasets, such as the amazon-review dataset, is implemented in PyTorch. We also support other tokenization methods, such as character or sentencepiece tokenization, and language models using various recurrent architectures.

The learned language model can be transferred to other natural language processing (NLP) tasks where it is used to featurize text samples. The featurizations provide a strong initialization point for discriminative language tasks, and allow for competitive task performance given only a few labeled samples. For example, we consider finetuning our models on the difficult task of multimodal emotion classification based on a subset of the plutchik wheel of emotions.

Created by Robert Plutchik, this wheel is used to illustrate different emotions in a compelling and nuanced way. He suggested that there are 8 primary bipolar emotions (joy versus sadness, anger versus fear, trust versus disgust, and surprise versus anticipation) with different levels of emotional intensity. For our classification task we utilize tweets from the SemEval2018 Task 1E-c emotion classification dataset to perform multilabel classification of anger, anticipation, disgust, fear, joy, sadness, surprise, and trust. This is a difficult task that suffers from real world classification problems such as class imbalance and labeler disagreement.

On the full SemEval emotion classification dataset we find that finetuning our model on the data achieves competitive state of the art performance with no additional domain-specific feature engineering.

Setup

Install

Install the sentiment_discovery package with python3 setup.py install in order to run the modules/scripts within this repo.

Python Requirements

At this time we only support python3.

• numpy
• pytorch (>= 0.4.1)
• pandas
• scikit-learn
• matplotlib
• unidecode
• sentencepiece
• seaborn
• emoji

Pretrained models

We've included our sentencepiece tokenizer model and vocab as a zip file:

• sentencepiece tokenizer [1MB]

We've included a transformer language model base as well as a 4096-d mlstm language model base. For examples on how to use these models please see our finetuning and transfer sections. Even though these models were trained with FP16 they can be used in FP32 training/inference.

• FP16 Transformer LM [311MB]
• FP16 mLSTM LM [169MB]

We've also included classifiers trained on a subset of SemEval emotions corresponding to the 8 plutchik emotions (anger, anticipation, disgust, fear, joy, sadness, surprise, and trust):

• Finetuned Plutchik Transformer [673MN]
• Finetuned Plutchik mLSTM [433MB]

Lastly, we've also included already trained classification models for SST and IMDB binary sentiment classification:

• Finetuned SST Transformer [621MB]
• Transferred SST mLSTM [325MB]
• Transferred IMDB mLSTM [325MB]

To use classification models that reproduce results from our original large batch language modeling paper please use the following commit hash and set of models.

We did not include pretrained models leveraging ELMo. To reproduce our papers' results with ELMo, please see our available resources.

Each file has a dictionary containing a PyTorch state_dict consisting of a language model (lm_encoder keys) trained on Amazon reviews and a classifier (classifier key) as well as accompanying args necessary to run a model with that state_dict.

Data Downloads

In the ./data folder we've provided processed copies of the Binary Stanford Sentiment Treebank (Binary SST), IMDB Movie Review, and the SemEval2018 Tweet Emotion datasets as part of this repository. In order to train on the amazon dataset please download the "aggressively deduplicated data" version from Julian McAuley's original site. Access requests to the dataset should be approved instantly. While using the dataset make sure to load it with the --loose-json flag.

Usage

In addition to providing easily reusable code of the core functionalities (models, distributed, fp16, etc.) of this work, we also provide scripts to perform the high-level functionalities of the original paper:

• sentiment classification of input text
• unsupervised reconstruction/language modeling of a corpus of text (+ script for launching distributed workers)
• transfer of learned language model to perform sentiment analysis on a specified corpus
• sampling from language model to generate text (possibly of fixed sentiment) + heatmap visualization of sentiment in text

Classifying text

Classify an input csv/json using one of our pretrained models or your own. Performs classification on Binary SST by default. Output classification probabilities are saved to a .npy file

python3 run_classifier.py --load_model ama_sst.pt                               # classify Binary SST
python3 run_classifier.py --load_model ama_sst_16.pt --fp16                     # run classification in fp16
python3 run_classifier.py --load_model ama_sst.pt --text-key <text-column> --data <path.csv>     # classify your own dataset

See here for more documentation.

Training Language Models (+ Distributed/FP16 Training)

Train a language model on a csv/json corpus. By default we train a weight-normalized, 4096-d mLSTM, with a 64-d character embedding. This is the first step of a 2-step process to training your own sentiment classifier. Saves model to lang_model.pt by default.

python3 pretrain.py                                                               #train a large model on imdb
python3 pretrain.py --model LSTM --nhid 512                                       #train a small LSTM instead
python3 pretrain.py --fp16 --dynamic-loss-scale                                   #train a model with fp16
python3 -m multiproc pretrain.py                                                  #distributed model training
python3 pretrain.py --data ./data/amazon/reviews.json --lazy --loose-json \       #train a model on amazon data
  --text-key reviewText --label-key overall --optim Adam --split 1000,1,1 
python3 pretrain.py --tokenizer-type SentencePieceTokenizer --vocab-size 32000 \  #train a model with our sentencepiece tokenization
  --tokenizer-type bpe --tokenizer-path ama_32k_tokenizer.model 
python3 pretrain.py --tokenizer-type SentencePieceTokenizer --vocab-size 32000 \  #train a transformer model with our sentencepiece tokenization
  --tokenizer-type bpe --tokenizer-path ama_32k_tokenizer.model --model transformer \
  --decoder-layers 12 --decoder-embed-dim 768 --decoder-ffn-embed-dim 3072 \
  --decoder-learned-pos --decoder-attention-heads 8
bash ./experiments/train_mlstm_singlenode.sh                                      #run our mLSTM training script on 1 DGX-1V
bash ./experiments/train_transformer_singlenode.sh                                #run our transformer training script on 1 DGX-1V 

For more documentation of our language modeling functionality look here

In order to learn about our language modeling experiments and reproduce results see the training reproduction section in analysis.

For information about how we achieve numerical stability with FP16 training see our fp16 training analysis.

Sentiment Transfer

Given a trained language model, this script will featurize text from train, val, and test csv/json's. It then uses sklearn logistic regression to fit a classifier to predict sentiment from these features. Lastly it performs feature selection to try and fit a regression model to the top n most relevant neurons (features). By default only one neuron is used for this second regression.

python3 transfer.py --load mlstm.pt                                 #performs transfer to SST, saves results to `<model>_transfer/` directory
python3 transfer.py --load mlstm.pt --neurons 5                     #use 5 neurons for the second regression
python3 transfer.py --load mlstm.pt --fp16                          #run model in fp16 for featurization step
bash ./experiments/run_sk_sst.sh                                    #run transfer learning with mlstm on imdb dataset
bash ./experiments/run_sk_imdb.sh                                   #run transfer learning with mlstm on sst dataset

Additional documentation of the command line arguments available for transfer can be found here

Classifier Finetuning

Given a trained language model and classification dataset, this script will build a classifier that leverages the trained language model as a text feature encoder. The difference between this script and transfer.py is that the model training is performed end to end: the loss from the classifier is backpropagated into the language model encoder as well. This script allows one to build more complex classification models, metrics, and loss functions than transfer.py. This script supports building arbitrary multilable, multilayer, and multihead perceptron classifiers. Additionally it allows using language modeling as an auxiliary task loss during training and multihead variance as an auxiliary loss during training. Lastly this script supports automatically selecting classification thresholds from validation performance. To measure validation performance this script includes more complex metrics including: f1-score, mathew correlation coefficient, jaccard index, recall, precision, and accuracy.

python3 finetune_classifier.py --load mlstm.pt --lr 2e-5 --aux-lm-loss --aux-lm-loss-weight .02   #finetune mLSTM model on sst (default dataset) with auxiliary loss
python3 finetune_classifier.py --load mlstm.pt --automatic-thresholding --threshold-metric f1     #finetune mLSTM model on sst and automatically select classification thresholds based on the validation f1 score
python3 finetune_classifier.py --tokenizer-type SentencePieceTokenizer --vocab-size 32000 \       #finetune transformer with sentencepiece on SST
  --tokenizer-type bpe tokenizer-path ama_32k_tokenizer.model --model transformer --lr 2e-5 \
  --decoder-layers 12 --decoder-embed-dim 768 --decoder-ffn-embed-dim 3072 \
  --decoder-learned-pos --decoder-attention-heads 8 --load transformer.pt --use-final-embed
python3 finetune_classifier.py --automatic-thresholding --non-binary-cols l1 l2 l3 --lr 2e-5\     #finetune multilayer classifier with 3 classes and 4 heads per class on some custom dataset and automatically select classfication thresholds
  --classifier-hidden-layers 2048 1024 3 --heads-per-class 4 --aux-head-variance-loss-weight 1.   #`aux-head-variance-loss-weight` is an auxiliary loss to increase the variance between each of the 4 head's weights
  --data <custom_train>.csv --val <custom_val>.csv --test <custom_test>.csv --load mlstm.pt
bash ./experiments/se_transformer_multihead.sh                                                    #finetune a multihead transformer on 8 semeval categories

See how to reproduce our finetuning experiments in the finetuning reproduction section of analysis.

Additional documentation of the command line arguments available for finetune_classifier.py can be found here

Analysis

• Why Unsupervised Language Modeling?
  • Difficulties of Supervised Natural Language
  • Data Robustness
  • Model/Optimization Robustness
• Reproducing Results
  • Training
    • Transformer Training Setup
    • mLSTM Training Setup
  • FP16 Training
  • Large Model Training
  • Sentiment Transfer
  • Finetuning Classifiers
  • ELMo Comparison
• Data Parallel Scalability
  • PyTorch + GIL
• Open Questions

Acknowledgement

A special thanks to our amazing summer intern Neel Kant for all the work he did with transformers, tokenization, and pretraining+finetuning classification models.

A special thanks to @csarofeen and @Michael Carilli for their help developing and documenting our RNN interface, Distributed Data Parallel model, and fp16 optimizer. The latest versions of these utilities can be found at the APEx github page.

Thanks to @guillitte for providing a lightweight pytorch port of openai's sentiment-neuron repo.

This project uses the amazon review dataset collected by J. McAuley

Thanks

Want to help out? Open up an issue with questions/suggestions or pull requests ranging from minor fixes to new functionality.

May your learning be Deep and Unsupervised.

---

Download details:

Author: NVIDIA
Source: https://github.com/NVIDIA/sentiment-discovery

License: View license

#pytorch 

Improving Semantic Segmentation (U-Net) Performance Via Ensemble of Multiple Trained Networks

Improving semantic segmentation (U-Net) performance via ensemble of multiple trained networks.
ResNet34 + Inception V3 + VGG16

Code generated in the video can be downloaded from here:

https://github.com/bnsreenu/python_fo… ​

The dataset used in this video can be downloaded from the link below. This dataset can be used to train and test machine learning algorithms designed for multiclass semantic segmentation. Please read the Readme document for more information.

https://drive.google.com/file/d/1HWtB…

Subscribe: https://www.youtube.com/channel/UC34rW-HtPJulxr5wp2Xa04w/featured

#u-net #deep-learning

ARM64 Performance in .NET 5

The .NET team has significantly improved performance with .NET 5, both generally and for ARM64. You can check out the general improvements in the excellent and detailed Performance Improvements in .NET 5 blog by Stephen. In this post, I will describe the performance improvements we made specifically for ARM64 and show the positive impact on the benchmarks we use. I will also share some of the additional opportunities for performance improvements that we have identified and plan to address in a future release.

While we have been working on ARM64 support in RyuJIT for over five years, most of the work that was done was to ensure that we generate functionally correct ARM64 code. We spent very little time in evaluating the performance of the code RyuJIT produced for ARM64. As part of .NET 5, our focus was to perform investigation in this area and find out any obvious issues in RyuJIT that would improve the ARM64 code quality (CQ). Since Microsoft VC++ team already has support for Windows ARM64, we consulted with them to understand the CQ issues that they encountered when doing a similar exercise.

#.net core #.net internals #c# #dot.net #performance #.net #arm #arm64 #performance #ryujit

.NET Certification Training | .NET Online Training

The .NET Certification training is primarily designed for student(s)/fresher(s) who want to make a career in .NET technologies. In this course, you will learn .NET concepts, OOPs concepts, C# language, SQL Server, HTML, CSS, Bootstrap and ASP.NET MVC and how to use visual studio 2019 for .NET development.

#dotnet online training #dot net training #net course #net training