I would like to give you some of my experience with AI projects.  

I am thrilled to announce the launch of my new service! As a computer vision and machine learning consultant, I provide end-to-end research and development solutions for cutting-edge artificial intelligence projects. My services encompass custom software implementation, MLOps, and project management, ensuring clients receive top-quality results. If you're looking to enhance your AI capabilities, I'm here to help. Contact me to learn more.

Are you looking for expert analysis of your project, eager for professional feedback, or in need of a comprehensive execution plan? Would you like to gain insights from industry leaders? I offer a 15-minute consultation free of charge to help you achieve your goals.

improved performance, reduced costs, or increased customer satisfaction. 

Are you in search of a partner who aligns with your project requirements? As a freelance data analyst with over 10 years of experience in the industry, I understand that finding the right partner can be challenging.

To help businesses overcome this hurdle, I offer best-in-class analysis tools such as regression analysis, reliability tools, hypothesis tests, and a graph builder feature for scientific data visualization. Additionally, I use predictive modeling to forecast future market conditions, making it easier for businesses to plan and strategize.

I understand that budget limitations can exist, and gaining buy-in for new tools and systems can be burdensome. That's why my services are designed to be user-friendly, with no coding required and built-in content-sensitive help systems. My tools and systems are also designed for non-statisticians, making it easier for businesses to understand and implement them.

With many industry use cases available online, my services are proven to deliver results. Let's partner up to take your project to the next level!

pip install mlc-ai-nightly -f

Day 1:

Introduction to Unity: TVMScript

Introduction to Unity: Relax and PyTorch

TVM BYOC in Practice

Get Started with TVM on Adreno GPU

Introduction to Unity: Metaschedule

How to Bring microTVM to a custom IDE

Day 2:

Community Keynote

PyTorch 2.0: the journey to bringing compiler technologies to the core of PyTorch

Support QNN Dialect for TVM with MediaTek Neuron and Devise the Scheduler for Acceleration

On-Device Training Under 256KB Memory

AMD Tutorial

TVM at TI: Accelerating inference using the C7x/MMA

Adreno GPU: 4x speed-up and upstreaming to TVM mainline

Transfer-Tuning: Reusing Auto-Schedules for Efficient Tensor Program Code Generation

Improvement in the TVM OpenCL codegen to autogenerate optimal convolution kernels for Adreno GPUs

TVM Unity: Pass Infrastructure and BYOC

Renesas Hardware accelerators with Apache TVM

Introduction on 4th Gen Intel Xeon processor and BF16 support with TVM

Hidet: Task Mapping Programming Paradigm for Deep Learning Tensor Programs

Towards Building a Responsible Data Economy

Optimizing SYCL Device Kernels with AKG

Adreno GPU Performance Enhancements using TVM

Improvements to CMSIS-NN integration in TVM

UMA: Universal Modular Accelerator Interface

Day 3:

TVM Unity for Dynamic Models

Empower Tensorflow serving with backend TVM

Enabling Conditional Computing on Hexagon target

Decoupled Model Schedule for Large Deep Learning Model Training

Using TVM to bring Bayesian neural networks to embedded hardware

Efficient Support of TVM Scan OP on RISC-V Vector Extension

Improvements to Ethos-U55 support in TVM including CI on Alif Semiconductor boards

Compiling Dynamic Shapes

TVM Packaging in 2023: delivering TVM to end users

Cross-Platform Training Using Automatic Differentiation on Relax IR

AutoTVM: Reducing tuning space by cross axis filtering

SparseTIR: Composable Abstractions for Sparse Compilation in Deep Learning

Analytical Tensorization and Fusion for Compute-intensive Operators

CUTLASS 3.0: Next Generation Composable and Reusable GPU Linear Algebra Library

Enabling Data Movement and Computation Pipelining in Deep Learning Compiler

Automating DL Compiler Bug Finding with NNSmith


TVM at Tencent

Integrating the Andes RISC-V Processors into TVM

Alpa: A Compiler for Distributed Deep Learning

ACRoBat: Compiler and Runtime Techniques for Efficient Auto-Batching of Dynamic Deep Learning Computations

Channel Folding: a Transform Pass for Optimizing Mobilenets

========================================================================Day 1:

************************ Introduction to Unity: TVMScript

Git remote add orgine  



Anomaly detection 

Use experience. Personalizes.  

Prediction manage society mobility  





Wordtune - AI-powered Writing Companion

tree -v  -I '*.png' -I '*.jpg' --charset utf-8 >list2.txt  

3D object using triangular mesh need vertices 

point cloud underlying surface of some 3D object, faster 

Definition of Done 

User Story complete 

Code\Implementation complete 

Code\Implementation Peer Reviews) approved 

Unit tests complete (if required) 

Testing Notes complete (if required) 

User Story Acceptance criteria defined and verified 

Backend: Python, Redis, Postgres, Celery 

Frontend: React, Redux, TypeScript 

DevOps: Terraform, Kubernetes, GitHub, Docker, AWS 

Data: Python (Data Science), Kafka, Fastapi, MLFlow, AWS SageMaker 

ML: Selcond core, Kubeflow, … 

Sharpness ,Noise,Dynamic range,Tone reproduction , Contrast, Color, Distortion , DSLR lenses, Vignetting, Exposure, Lateral chromatic aberration (LCA), Lens flare, Color, Artifacts  

۱. جهت انتخاب کلمه مورد نظرتان، دو بار روی آن تپ کنید. 

۲. برای انتخاب کل یک پاراگراف، کافیست چهار با روی آن تپ کنید. 

۳. یک انگشت را در ابتدا و انگشت دیگر را در آخر یک محدود گذاشته و کمی نگه دارید. متن میان دو انگشت انتخاب خواهد شد.  

۴. روی ابتدای محدوده ای دلخواه دو بار تپ کرده و بلافاصله با درگ کردن (کشیدن) پین محدوده ی انتخاب شده را گسترش دهید. (انگشت خود را پس از دومین تپ جدا نکنید) 

۵. برای انتخاب کل پاراگراف، به جز استفاده از مورد ۲، می توانید با دو انگشت، یک بار روی آن تپ کنید. 

namely motion estimation, motion smoothing, and image warping. Motion estimation algorithms often use a similarity transform to handle camera translations, rotations, and zooming. The tricky part is getting these algorithms to lock onto the background motion, 

0. video frames captured during fast motion are often blurry. Their appearance can be improved either using deblurring techniques (Section 10.3) or stealing sharper pixels from other frames with less motion or better focus (Matsushita, Ofek, Ge et al. 2006). Exercise 8.3 has you implement and test some of these ideas. 

1. Background subtraction 

2. Motion estimation 

3. Motion smoothing 

4. Image warping. image warping can result in missing borders around the image, which must be cropped, filled using information from other frames, or hallucinated using inpainting techniques (Section 10.5.1). 



Vision stabilization  

There is much recent work on  

Multi-view 3D reconstruction is a central research topic in computer vision that is driven in many different directions 

There are many available methods that can handle the noisy image completion problem 


In the case of surveillance using a fixed camera, there is no desired motion. In the case of most robotic applications, horizontal and vertical motions are desired, but rotation is not. In some cases of ground vehicles where the terrain is known to have many incline changes, or with aerial vehicles undergoing complicated maneuvers where the vehicle’s body is meant to be in varying orientations, rotation might be desired as the robot is meant to be at an angle at times.  

In robotics applications, computational complexity is extremely important due to the need for real-time operation. Also, it is likely that the center of rotation will not lie in the center of the image frame because the camera is rarely mounted at the robot’s center of mass.  



This first assumption is made in many video stabilization algorithms, and is a convenient way to seed the correct features with higher trust values. It is not an unreasonable assumption to make. Depending on the application, there is often a large portion of frames where local motion does not occur. In some situations, such as monitoring of steady traffic, there is no guarantee that local motion will not occur. This situation has not been tested, nor has our algorithm been designed to handle it. The second assumption comes from a combination of common sense, and the experience of many computer vision researchers. It makes sense that an object in the scene which does not move will be recognized more easily and more often. Being recognized consistently and consecutively is considered stable. On the other hand, objects which have local motion are less likely to be recognized as often. They might move through shadows, change orientation, or even move completely out of the scene. These possibilities all lead to a less stable class of features. It is likely that, more often than not, there are more background features than foreground features. Moving objects generally cover a small portion of the screen, which usually yields fewer features. Although uncommon, we did not want to make the assumption that this would occur in every frame. Certain scenes will consist of a large portion of local motion, or an object will move very close to the camera, consuming a much larger portion of the scene than the background. As long as some background features are discovered in each frame, our stabilization algorithm should succeed.  

image processing tips:

"olive" editor remove silence 


How to train model to add new classes?

How to add a new class to an existing classifier in deep learning?

Adding new Class to One Shot Learning trained model

Is it possible to train a neural network as new classes are given?

Merging all several models that detection system for all these tasks.

Answer 1:

There are several ways to add new classes to the trained model, which require just training for the new classes.

Answer 2:

Online learning is a term used to refer to a model which takes a continual or sequential stream of input data while training, in contrast to offline learning (also called batch learning), where the model is pre-trained on a static predefined dataset.

Continual learning (also called incremental, continuous, lifelong learning) refers to a branch of ML working in an online learning context where models are designed to learn new tasks while maintaining performance on historic tasks. It can be applied to multiple problem paradigms (including Class-incremental learning, where each new task presents new class labels for an ever expanding super-classification problem).

Do I need to train my whole model again on all four classes or is there any way I can just train my model on new class?

Naively re-training the model on the updated dataset is indeed a solution. Continual learning seeks to address contexts where access to historic data (i.e. the original 3 classes) is not possible, or when retraining on an increasingly large dataset is impractical (for efficiency, space, privacy etc concerns). Multiple such models using different underlying architectures have been proposed, but almost all examples exclusively deal with image classification problems.

Answer 3:

You could use transfer learning (i.e. use a pre-trained model, then change its last layer to accommodate the new classes, and re-train this slightly modified model, maybe with a lower learning rate) to achieve that, but transfer learning does not necessarily attempt to retain any of the previously acquired information (especially if you don't use very small learning rates, you keep on training and you do not freeze the weights of the convolutional layers), but only to speed up training or when your new dataset is not big enough, by starting from a model that has already learned general features that are supposedly similar to the features needed for your specific task. There is also the related domain adaptation problem.

There are more suitable approaches to perform incremental class learning (which is what you are asking for!), which directly address the catastrophic forgetting problem. For instance, you can take a look at this paper Class-incremental Learning via Deep Model Consolidation, which proposes the Deep Model Consolidation (DMC) approach. There are other continual/incremental learning approaches, many of them are described here or in more detail here.

Answer 4:

by using Continual learning approaches to trained without losing the original classes. It has 3 categories:




Answer 5:

if you access to the dataset then you can download it and add all you new classes when you have " 'N' COCO Classes + 'M' New classes " 

after that you can fine tune model based on new dataset. you do not need all of the dataset just same number of image for all class enough. 

Before start your machine learning project ask these questions and preparation: What is your inference hardware? specify the use case. specify model interface. how would we monitor performance after deployment? how can we approximate post-deployment monitoring before deployment? build a model and iteratively improve it. How to deploy the model at the end? monitor performance after deployment. what is your metric? How do you split your data (training and validation)? 

Preparation ML Project Workflow

Before Training deep learning model

Training deep learning model

Continuous delivery

After Training deep learning model

Deep learning model in production






My Keynote (February 2021)

Machine learning is an application of artificial intelligence (AI) that provides systems the ability to automatically learn and improve from experience without being explicitly programmed 

Advanced and practical 

Summary of the summit




Dreyer's English (learn write English)

#book story

Greek Mythology Explained: A Deeper Look at Classical Greek Lore and Myth


CALTag: High Precision Fiducial Markers for Camera

Diatom Autofocusing in Brightfield Microscopy: a Comparative Study   :implementation variation of the laplacian

Analysis of focus measure operators in shape-from-focus: why laplacian? Blure detection? Iqaf?

Optical flow modeling and computation: A survey

Toward general type 2 fuzzy logic systems based on zSlices


Lost in space

The OA



Movie Serial billons

monk serial movies

Python async

Highly decoupled microservice

Edex RIS-V , Self-car

RISC-V Magazine

Road map

Game: over/under




The EU General Data Protection 

Regulation (GDPR) and Face Images in IoT

The GDPR (General Data Protection Regulation), taking effect in May 2018, introduces strict requirements for personal data protection and the privacy rights of individuals. The EU regulations will set a new global standard for privacy rights and change the way organizations worldwide store and process personal data. The GDPR brings the importance of preserving the privacy of personal information to the forefront, yet the importance of face images within this context is often overlooked. The purpose of this paper is to introduce a solution that helps companies protect face images in IoT devices which record or process image by camera, to strengthen compliance with the GDPR. 

Our Face is our Identity 

Our face is the most fundamental and highly visible element of our identity. People recognize us when they see our face or a photo of our face. 

Recent years have seen exponential increase in the use, storage and dissemination of face images in both private and public sectors - in social networks, corporate databases, IoT, smart-city deployments, digital media, government applications, and nearly every organization’s databases. 


$(aws-okta env stage)

aws s3 cp s3://dataset/archive.tar.gz /Users/

aws s3 ls images | tail -n 100

aws s3 cp staging-images/test.jpg /Users/test.jpg


screen -rD

k get pods


RUN chmod +x /tmp/

Can run docker in terminal and run code line by line

docker run -it --rm debian:stable-slim bash

apt-get update

apt-get installl -y


brew install awscli aws-okta kubectx kubernetes-cli tfenv

touch ~/.aws/config


docker image rm TETSTDFSAFDSADF

docker image ls

docker system prune

docker run -p 5000:5000 nameDocker:latest

docker build . -t nameDocker:latest

docker container stop number-docker-name

docker container ls


Cloud software engineer and consultant focusing on building highly available, scalable and fully automated infrastructure environments on top of Amazon Web Services and Microsoft Azure clouds. My goal is always to make my customers happy in the cloud.


Search google for 3d = tiger - iPhone show AR/VR


brew install youtube-dl


List: Collection bucket : 1 for week 2 for month 3 for future


**•        Per frame operation**

 –        Detection

 –        Classification

 –        Segmentation

 –        Feature extraction

 –        Recognition

**•        Across frames **

–        Tracking

–        Counting

**•        High level**

–        Intention

–        Relations

–        Analyzing




Deep compression

Pruning deep learning

Hash table neural network

Dl compression

Deep compression



Mini PCI-e slot







Advancing Self-Supervised and Semi-Supervised Learning with SimCLR \cite{Chen2020}


first pretraining on a large unlabeled dataset and then fine-tuning on a smaller labeled dataset

pretraining on large unlabeled image datasets, as demonstrated by Exemplar-CNN, Instance Discrimination, CPC, AMDIM, CMC, MoCo and others. 

 “A Simple Framework for Contrastive Learning of Visual Representations”, 85.8\% top-5 accuracy using 1\% of labeled images on the ImageNet dataset

contrastive learning algorithms

linear evaluation protocol (Zhang et al., 2016; Oord et al.,2018; Bachman et al., 2019; Kolesnikov et al., 2019)

unsupervised learning benefits more from bigger models than its supervised counterpart.










Some of optimization algorithms



Swarm Algorithm


1. Ant Colony Optimization (ACO) was inspired by the research on the behavior of ant colonies 

2. Firefly Algorithm based on insects called fireflies 

3. Marriage in Honey Bees Optimization Algorithm (MBO algorithm) is inspired by the process of reproduction of Honey Bee

4. Artificial Bee Colony Algorithm (ABC) is based on the recollection of the Honey Bees

5. Wasp Swarm Algorithm was inspired on the Parasitic wasps

6. Bee Collecting Pollen Algorithm (BCPA) 

7. Termite Algorithm

8. Mosquito swarms Algorithm (MSA)

9. zooplankton swarms Algorithm (ZSA)

10. Bumblebees Swarms Algorithm (BSA)

11. Fish Swarm Algorithm (FSA)

12. Bacteria Foraging Algorithm (BFA)

13. Particle Swarm Optimization (PSO)

14. Cuckoo Search

15. Bat Algorithm (BA)

16. Accelerated PSO

17. Bee System

18. Beehive Algorithm

19. Cat Swarm

20. Consultant-guided search

21. Eagle Strategy

22. Fast Backterial swarming algorithm

23. Good lattice swarm optimization

24. Glowworm swarm optimization

25. Hierarchical swarm model

26. Krill Herd

27. Monkey Search

28. Virtual ant algorithm

29. Virtual bees

30. Weighted Swarm Algorithm

31. Wisdom of Artificial Crowd algorithm 

32. Prey-predator algorithm 

33. Memetic algorithm 

34. Lion Optimization Algorithm 

35. Chicken Swarm Optimization 

36. Ant Lion Optimizer 

37. Compact Particle Swarm Optimization

38. Fruit Fly Optimization Algorithm 

39. marine propeller optimization algorithm  

40. The Whale Optimization Algorithm 

41. virus colony search algorithm 

42. Slime mould optimization algorithm


Ecology Inspired Algorithm


1. Biogeography-based Optimization

2. Invasive Weed Optimization

3. Symbiosis-Inspired Optimization - PS2O

4. Atmosphere Clouds Model

5. Brain Storm Optimization

6. Dolphin echolocation

7. Japanese Tree Frog Calling algorithm

8. Eco-inspired evolutionary algorithm

9. Egyptian Vulture

10. Fish School search

11. Flower Pollination algorithm

12. Gene Expression

13. Great Salmon Run

14. Group Search Optimizer

15. Human Inspired Algorithm

16. Roach Infestation algorithm

17. Queen-bee algorithm

18. Shuffled frog leaping algorithm

19. Forest Optimization Algorithm 

20. coral reefs optimization algorithm 

21. cultural evolution algorithm 

22. Grey Wolf Optimizer 

23. probabilistic pso 

24. omicron aco algorithm 

25. shark smell optimization 

26. social spider algorithm 

27. sosial insects behavior algorithm 

28. sperm whale algorithm 


Evolutionary Optimization


1. Genetic Algorithm

2. Genetic Programming

3. Evolutionary Strategies

4. Differential Evolution

5. Paddy Field Algorithm

6. Queen-bee Evolution

7. Quantum Inspired Social Evolution 


Physic and Chemistry inspired algorithm


1. Big bang-Big Crunch

2. Block hole algorithm

3. Central force optimization

4. Charged System search

5. Electro-magnetism optimization

6. Galaxy based search algorithm

7. Gravitational search

8. Harmony search algorithm

9. Intelligent water drop algorithm

10. River formation algorithm

11. Self-propelled dynamics

12. Simulated Annealing

13. Stachastic diffusion search

14. Spiral optimization

15. Water Cycle algorithm

16. Artificial Physics optimization

17. Binary Gravitational search algorithm

18. Continous quantum ant colony optimization

19. Extended artificial physics optimization

20. Extended Central force optimization

21. Electromagnetism-like heuristic

22. Gravitational Interaction optimization

23. Hysteristetic Optimization algorithm

24. Hybrid quantum-inspired GA

25. Immune gravitational inspired algorithm

26. Improved quantum evolutinary algorithm

27. Linear programming

28. Quantum-inspired bacterial swarming

29. Quantum-inspired evolutionary algorithm

30. Quantum-inspired genetic algorithm

31. Quantum-behaved PSO

32. Unified big bang-chaotic big crunch

33. Vector model of artificial physics

34. Versatile quantum-inspired evolutionary algorithm

35. Space Gravitational Algorithm 

36. Ion Motion Algorithm 

37. Light Ray Optimization Algorithm 

38. Ray Optimization 

39. Photosynthetic Algorithms

40. floorplanning algorithm  

41. Gases Brownian Motion Optimization 

42. gradient-type optimization 

43. mean-variance optimization

44. Mine blast algorithm 

45. moth flame optimization 

46. multi battalion search algorithm 

47. music inspired optimization

48. no free lunch theorems algorithm

49. Optics inspired optimization 

50. runner-root algorithm 

51. sine cosine algorithm

52. pitch tracking algorithm   

53. Stochastic Fractal Search algorithm 

54. stroke volume optimization 

55. Stud krill herd algorithm 

56. The Great Deluge Algorithm 

57. Water Evaporation Optimization 

58. water wave optimization algorithm 

59. Island model algorithm 

60. Steady State model