![Dr. Priyanto Hidayatullah](/img/default-banner.jpg)
- 75
- 134 422
Dr. Priyanto Hidayatullah
เข้าร่วมเมื่อ 23 ธ.ค. 2008
Penulis Buku Sakti Deep Learning
Chapter 08-05 - Face Mask Detection
In this video, we will perform face mask detection using a model from the previous training. Detection is carried out on images, videos and webcams.
⬇️ Facemask image and Video
drive.google.com/drive/u/2/folders/1fPmSkXYgcD-T5z3xt-LQPVg0ngneSldE
#yolov7 #yolov7course #objectdetection #customobjectdetection #yolocourse
⬇️ Facemask image and Video
drive.google.com/drive/u/2/folders/1fPmSkXYgcD-T5z3xt-LQPVg0ngneSldE
#yolov7 #yolov7course #objectdetection #customobjectdetection #yolocourse
มุมมอง: 26
วีดีโอ
Chapter 08-04 - How to continue an unfinished training
มุมมอง 21หลายเดือนก่อน
In this video, we'll guide you through the process of resuming training from where you left off. You’ll learn how to save and load model checkpoints, update training scripts to start from the latest checkpoint, and ensure continuity in your training progress. #yolov7 #yolov7course #objectdetection #customobjectdetection #yolocourse
Chapter 08-03 - Perform training and see the accuracy graph using Tensorboard
มุมมอง 55หลายเดือนก่อน
In this video, we’ll guide you through the steps to train your deep learning model and monitor its performance with TensorBoard. You’ll learn how to set up your training script, log relevant metrics, and launch TensorBoard to visualize the accuracy and loss graphs in real-time. ⬇️ YOLOv7 Argument for Training drive.google.com/file/d/1By8JmxVWJUbjNNxSVHn_4fE61ONcL00d/view?usp=drive_link #yolov7 ...
Chapter 08-02 - Make Configuration File
มุมมอง 16หลายเดือนก่อน
In this video, i will explain how to create a configuration file containing dataset paths and class names #yolov7 #yolov7course #objectdetection #customobjectdetection #yolocourse
Chapter 08-01 - Preparing dataset and splitting the dataset automatically
มุมมอง 24หลายเดือนก่อน
In this video, we'll guide you through the essential steps of organizing your dataset and splitting it into training, validation, and testing sets. You’ll learn how to structure your data directories and use scripts to automate the splitting process. ⬇️ Facemask Dataset: drive.google.com/drive/folders/1dOG5Ic7sFCXoFLjoS-Rd6MuXULFEzaQm #yolov7 #yolov7course #objectdetection #customobjectdetectio...
Chapter 07-03 - YOLOv7 Object Detection on video and webcam (GPU Mode)
มุมมอง 50หลายเดือนก่อน
In this video, we'll guide you through the process of executing YOLOv7 for real-time object detection on video files and live webcam streams. You’ll learn how to specify the video input source or webcam device and run the detection script to visualize results in real-time. ⬇️ Sample Video for detection drive.google.com/file/d/1pg04n7WWRgiw2qL2Cc9cXhV4x8wlHiQ7/view?usp=drive_link #yolov7 #yolov7...
Chapter 07-02 - YOLOv7 Object Detection on image (GPU Mode)
มุมมอง 26หลายเดือนก่อน
In this video, we'll guide you through the process of running YOLOv7 on a batch of images, detecting objects, and exporting the detection results into a text file. #yolov7 #yolov7course #objectdetection #customobjectdetection #yolocourse
Chapter 07-01 - Intro Object Detection
มุมมอง 32หลายเดือนก่อน
In this video, we’ll explain the various command-line arguments and parameters you can use to customize and optimize your object detection tasks with YOLOv7. You’ll learn how to specify the input source, adjust confidence thresholds, set the device for computation (CPU or GPU), and configure other important settings. ⬇️ YOLOv7 Argument for Detection drive.google.com/file/d/1K1YCFimTCOECxu7aDwmb...
Chapter 06-02 - Install YOLOv7 in GPU Mode
มุมมอง 69หลายเดือนก่อน
In this video, we’ll guide you through the complete process of setting up YOLOv7 to leverage the power of your GPU for faster and more efficient object detection. You’ll learn how to configure your environment and install the necessary dependencies. We’ll also show you how to download the YOLOv7 source code and run a basic script to verify your setup. Perfect for developers looking to maximize ...
Chapter 06-01 - Install YOLOv7 in CPU Mode
มุมมอง 43หลายเดือนก่อน
In this video, we’ll guide you through the entire process of setting up YOLOv7 without requiring a GPU. You’ll learn how to configure your environment, install the necessary dependencies, and download the YOLOv7 source code. We’ll also walk you through running a basic YOLOv7 script to ensure everything is working correctly. Perfect for those who don't have access to a GPU or are just getting st...
Chapter 05-02 - Install CUDA
มุมมอง 51หลายเดือนก่อน
In this video, we’ll guide you through the entire process of downloading and installing CUDA, NVIDIA's parallel computing platform and programming model. You’ll learn how to check your system compatibility, download the correct version of CUDA for your GPU, and install it on your operating system. #yolov7 #yolov7course #objectdetection #customobjectdetection #yolocourse
Chapter 05-03 - Install cuDNN
มุมมอง 92หลายเดือนก่อน
In this video, we'll walk you through the process of downloading and installing cuDNN, the NVIDIA CUDA Deep Neural Network library, which is essential for accelerating deep learning frameworks on NVIDIA GPUs. You’ll learn how to check compatibility, download the correct version of cuDNN, and integrate it with your CUDA installation. #yolov7 #yolov7course #objectdetection #customobjectdetection ...
Chapter 05-01 - Install GPU Driver
มุมมอง 37หลายเดือนก่อน
In this video, we'll walk you through the process of downloading and installing the latest GPU drivers for your system, ensuring optimal performance for gaming, deep learning, and other GPU-intensive tasks. You’ll learn how to identify your GPU model, find the correct driver, and properly install it on your operating system. #yolov7 #yolov7course #objectdetection #customobjectdetection #yolocourse
Chapter 04-04 - Dataset Splitting
มุมมอง 37หลายเดือนก่อน
In this video, we will explain dataset splitting in object detection. #yolov7 #yolov7course #objectdetection #customobjectdetection #yolocourse
Chapter 04-03 - Dataset Annotation using LabelImg
มุมมอง 103หลายเดือนก่อน
In this video, we will explain how to install Labelimg and annotate datasets using Labelimg. ⬇️ Face Mask Dataset www.kaggle.com/datasets/andrewmvd/face-mask-detection #yolov7 #yolov7course #objectdetection #customobjectdetection #yolocourse
Chapter 04-02 - Understanding YOLO dataset annotation format
มุมมอง 49หลายเดือนก่อน
Chapter 04-02 - Understanding YOLO dataset annotation format
Chapter 03-01 - How To Install Anaconda
มุมมอง 52หลายเดือนก่อน
Chapter 03-01 - How To Install Anaconda
Chapter 02-03 - YOLOv7 architecture detailed explanation
มุมมอง 141หลายเดือนก่อน
Chapter 02-03 - YOLOv7 architecture detailed explanation
Chapter 02-02 - Convolutional Neural Networks summary
มุมมอง 56หลายเดือนก่อน
Chapter 02-02 - Convolutional Neural Networks summary
Chapter 02-01 - Understanding Deep Learning
มุมมอง 43หลายเดือนก่อน
Chapter 02-01 - Understanding Deep Learning
Chapter 01-03 - How to run your first Deep Learning program using YOLOv7 in less than 3 minutes
มุมมอง 57หลายเดือนก่อน
Chapter 01-03 - How to run your first Deep Learning program using YOLOv7 in less than 3 minutes
Chapter 01-01 - How to Install Python and Download YOLOv7 Source Code
มุมมอง 105หลายเดือนก่อน
Chapter 01-01 - How to Install Python and Download YOLOv7 Source Code
YOLOv10 Comparison with Latest YOLO models
มุมมอง 1.7Kหลายเดือนก่อน
YOLOv10 Comparison with Latest YOLO models
YOLOv8 vs YOLOv9 Comparison - The Real Battle
มุมมอง 2.4K3 หลายเดือนก่อน
YOLOv8 vs YOLOv9 Comparison - The Real Battle
Hello, AttributeError: 'tensorrt_bindings.tensorrt.ICudaEngine' object has no attribute 'num_bindings' What is solution this problem ?
hello Professor ! thankyou for the detailed explanation it helped a lot. We are using this model for an interdisciplinary project that also requires explaining this models behaviour using explainability techniques like EigenCam and GradCam. Sir can you please suggest some layers in this Architecture that we can target to get better Predictions...?
Permisi pak , ijin bertanya apakah ada jurnal referensi yang bisa menjadi sitasi pak ?
YOLOv8 memang belum ada jurnalnya sampai sekarang
Penjelasannya mudah dipahami, terima kasih pak
alhamdulillah, sama-sama
Which better to detect static photo v5 or v8 also to detect video ??
Both models were authored by the same team. They claimed yolov8 is better for both cases. However some users said they experienced yolov5 was better for their dataset. At the end, you have to check it by yourself to your dataset. I suggest, start with yolov8.
im going to buy the course right now,does this work on yolov9 and yolov10?
Needs a lot of modification
@@Dr.Priyanto.Hidayatullah will you update the course content in the future or i shouldn’t buy now?
@@chihebnouri5541 At the moment, this course is specialized for YOLOv8
menarik ini, dari semua model kayanya v5 itu paling stabil ya
Beberapa orang bilang seperti itu. Tapi beda video bisa beda hasilnya.
ada kelas khusus penggunaan apple silicon? untuk trianing YOLO
Kalau khusus Apple, di kelas kami belum ada. Tapi pengguna Apple bisa menggunakan Google colab. Kami sediakan file untuk dieksekusi di google colabnya (yolov7 dan YOLOv8). Bisa di searching di udemy YOLOv8, lalu cari yang instruktur nya saya.
V8 better pak, butuh yang lebih akurat di robot
Iya YOLOv8 lebih akurat. Namun di kasus tertentu, yolov9 lebih akurat. Kalau ingin lebih akurat lagi, harus dilakukan modifikasi. Bisa arsitektur, hyperparameter, atau tambah data.
Hi Dr. do you have courses on how to improve yolov5?
Hi marcoz. Unfortunately no. YOLOv8 is the sequel of YOLOv5. Authored by the same team. Has many similarities. Has better performance than YOLOV5. Supposed you want to switch to YOLOv8 and want to improve the performance, this course is definitely for you.
@@Dr.Priyanto.Hidayatullah Hi Dr. for some reason I am getting much better accuracy with yolov5 than yolov8. would be really nice if you make a course about yolov5 too
Could you please show the YOLOv9-seg architecture also? Thank you so much ~~~
That would be making another video :D But thank you for asking
Hey, I am trying to make a conveyor belt tear detection model. Based on your comparison, which version would you recommend: YOLOv8, YOLOv9, or YOLOv10?
I have answered your question in another video
@@Dr.Priyanto.Hidayatullah YOLOv10 in your case. You would want the faster response.
@@Canna_Science_and_Technology yes
Great video! I am trying to make a conveyor belt tear detection model. Based on your comparison, which version would you recommend: YOLOv8, YOLOv9, or YOLOv10?
For accuracy, choose between YOLOv8 / v9. For speed, YOLOv10
@@Dr.Priyanto.Hidayatullah thanks!
@@Dr.Priyanto.Hidayatullah Hello sir, i tried both yolov8 and yolov9 for conveyor belt tear with a dataset of 1300 images(75%training, 13%valid, 12%test), but i am getting low accuracy, around 57%precision, 34% recall, 32%mAP50 after training for 65 epochs. How can i increase it?
@@ramyeonmokja there are many way how to improve accuracy. 1. Is the accuracy still increasing as the training goes? If yes continue the training, you need more epoch 2. Do hyperparameter tuning 3. Modify the architecture so it suit you study case. 4. Add drop out if necessary 5. Increase first layer resolution And many more
Izin bertanya. Apakah dalam implementasinya, Yolov8 bisa dikombinasikan dengan arsitektur lain?
Menurut saya bisa. Pas mengerjakannya harus sabar dan telaten
@@Dr.Priyanto.Hidayatullah Apakah ada harga promo untuk mengikuti kelasnya di Udemy Prof?
@@dosenswasta www.udemy.com/course/yolo-performance-improvement-masterclass/?couponCode=C00946B7B921C18E4ED9 Ini saya buatkan. Kuponnya tinggal berlaku 2-3 HARI lagi saja.
Mohon diperhatikan, kupon ini untuk kursus peningkatan performa YOLOv8 yang memang membahas cukup dalam tentang arsitektur YOLOv8 dan modifikasinya
Saya ingin bergabung di kelasnya Pak. Mohon petunjuknya jika ada kelas tatap muka online untuk kelas ini.
Silakan bergabung pak. Namun mohon maaf, belum ada fasilitas temu muka online dari udemy. Tapi bapak bisa bertanya via QA section
Halo Pak Doktor. Mohon masukanya. Untuk mendeteksi multi class objek apakah Yolov8 atau Yolov9 ini bisa lebih baik dibandngkan Yolov4 atau Yolov5?
Berdasarkan papernya, seperti itu pak. Hasil eksperimen kami juga seperti itu
It seems like you are working with confidence above 0.2 I don't know if the footage is 720p or 1080p, can you please share the resolution? I would like to test the performance of the nano versions of each model by using a 1080p and 2k images.
Object detection in this video uses a confidence threshold of 0.25. The resolution is 1080p.
Thanks for neat, but impactful explanation
You're welcome!
Hello, I am interested in the masterclass, but I don't see any information about whether the videos have Spanish subtitles
what is mean by iou parameter ? can u explain.. thank u
IoU parameter is Intersection over Union (IoU) threshold. IoU is the ratio of the overlapping area between the predicted bounding box and the ground truth bounding box. The detection result is said to be correct, if it has an IoU value greater than or equal to this threshold.
thank you i havent read the docs hehe im sorry before that, i face a problem with modified model the result cant be get.. can you explain why my experiment get 0 on map value ?
@@yudisdwi1050 most probably, the problem is in the model.
Hello Dr. I've been trying to pay for the "YOLOv8 Performance Improvement Masterclass" course for a week but I can't make the transfer. I use a visa card. I am from Senegal. please I would like you to help me get the content. I really need it in my current job. and I hope it will be of great help to me.
Hi! Try to find the solution here support.udemy.com/hc/en-us/articles/360000165907-Payment-Methods-on-Udemy I hope it helps
You might want to try using different devices (laptop/mobile phone).
Dr Priyanto. I like the content on your channel. In some of your courses do you address the topic of "fine tuning" with YOLO? Which of your courses would you recommend? Also, I would like to cordially suggest including automatically generated subtitles in Spanish in your courses. Thank you so much
Thank you. Yes we do recommend bit.ly/Improve-YOLOv8 Regarding the subtitle, we Will consider it.
GitHub link please
Where is the difference between the YOLOv8 object detection architecture and classification architecture?
Based on architecture file github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/models/v8/yolov8-cls.yaml In the classification, there is no SPPF block in the backbone. After that in the head, there is only a classify block
May I ask why the feature map with higher height x width specializes detecting small objects? Does it have something to do with the channel? (9:42)
Not with the channel, but with the resolution.
Enrollment link: bit.ly/YOLOv7_v8_v9_Course
Where is the enrollment link sir ?
It is in the description. Or you can use this one bit.ly/YOLOv7_v8_v9_Course
Apa itu berpengaruh kepada akurasi? Atau hanya nice to have aja?
Pertama, mobil dianggap Cell phone itu sudah suatu yg fatal. Yang kedua, kalaupun kelasnya benar (ada kasus lain), akurasinya lumayan bedanya.
Dr. Priyanto Hidayatullah, Subscribed because your content is fantastic!
Thank you for your kind words. Thank God
Good video. Yolov10 processes faster but is more imprecise. Yolov8 and Yolov9 seem similar. I think Yolov8 is a little better with distant objects.
You have an accurate conclusion 👍
Nice, Can you please tell me how I will create the loss curve of yolov10, yolov9, and yolov8 for comparison on a single graph?.
That would probably a long tutorial 😬
Good explaination Sir. Can I get the link to the collab notebook, kindly share as I will have clarity in regards to numbers of doubts. Thank you!
The colab is available if you enroll to the course 🙏 bit.ly/Improve-YOLOv8
@@Dr.Priyanto.Hidayatullah yes sir surely! Kinly share a discount link if you have any. I am so willing to learn from your courses.:)
@@healingherselfdaily5650 here you go: www.udemy.com/course/yolo-performance-improvement-masterclass/?couponCode=C00946B7B921C18E4ED9
it's time limited btw. Grab it fast!
hello , thank you for your video , i just would like to know how can i change in yolov8 model like the momentum and other hyperparameters .pls
You can write as arguments when you do the training. The hyperparameter is nlisted here docs.ultralytics.com/usage/cfg/#train-settings
@@Dr.Priyanto.Hidayatullah Thank you so much, and wht about if want to change in the architecture of the model inside , like the numbre of layers and ect..
@@ikramessafi9560 then the best option is you enroll to my course. We can discuss deeper there: bit.ly/Improve-YOLOv8
Dear Sir, Which activation function is used in YOLOv9? Which attention module is used in YOLOv9?
SiLU activation function
SiLU activation function
@@Dr.Priyanto.Hidayatullah Thank you sir. What about attention module?
@@businessjournal339 i have to check the code.
@@businessjournal339 I have check the source code and the paper, i'm not sure there is an attention module in YOLOv9. In fact, there is someone who wants to add attention module to YOLOv9 github.com/WongKinYiu/yolov9/issues/454
Thank you Dr. Priyanto Hidayatullah. Excelent tutorial.
Thank you. Thank God..
is this an explanation of how feature extraction from yolov8 works?
in one POV, yes
Can you provide architecture diagram of the YOLOv9 ?
You can downlooad it from here: stunningvisionai.com/article/yolov9-architecture
penjelasan yang jelas dan sangat bermanfaat pak! namun saya mengalami error di bagian deteksi video menggunakan yolov8n.engine. Detail errornya AttributeError: 'tensorrt_bindings.tensorrt.ICudaEngine' object has no attribute 'num_bindings'. Kira-kira itu errornya kenapa ya pak dan bagaimana solusinya?
did you resolve this error?
Hi sir, Thank you so much for this explanation but could you please explain what exactly is this 'max output channel'?
is it possible for yolo to train data whose channels>3 ?
do u have a video to explain how to install tensorrt ? i cant make it in my local computer. But colab is working well.
Not yet. We are working on something else at the moment
if you know tell me pleaseeeeeeeee, is there a specific activation functions list used just with yolov9 or not? and how can i change the type of activation function in the model, i am training it on custom dataset
For a list of activation functions that can be used, you can see the following link pytorch.org/docs/stable/nn.html#non-linear-activations-weighted-sum-nonlinearity You can change it in common.py file. github.com/WongKinYiu/yolov9/blob/main/models/common.py
Nice work doctor really appreciated
Thank you, alhamdulilah
@Dr. Priyanto Hidayatullah, Sir how can i test this code with my video? or any other video is this possible? Pls help me.
Upload your video by following the tutorial. Change the video path accordingly
Sir, i tried but it shows me error for the road folder. How can i solve this?
@@hridoydev8730 have you follow the tutorial 100% and working? If yes, then just change the video file name with yours
Sir please share architecture diagram .
I really appreciate your explanation. However, What about the Multi-Level Auxiliary Information branch as mentioned in the paper?
That would be another level of explanation. We need another video for it
Hello, Nice test!, currently I have a project with an RTX 3060 and an AMD R7 5700X processor, would it be advisable to change it for an Intel? Additionally, I'm having trouble running the inference model with TensorRT.
No, IMO you don't have to. Tensorrt is related to the GPU. Your GPU is ok. You might want to check my tutorial in this channel on how to use tensorrt. Hope it helps
thank you for your explained ❤❤❤❤
Kursus bapak yg dalam bahasa indonesia bisa dicheck out dimana ya pak?
Kursusnya dalam bahasa Inggris semua. Kalau mau yg berbahasa Indonesia, kita ada workshop. Biasanya sebulan sekali. Coba hubungi 081214617878 untuk workshop berikutnya
Couldn’t you get up to 500 fps on yolov8 nano with deepsparse?