Train YOLOv7 Object Detection on Custom Dataset in Google Colab | 4K

Поділитися
Вставка
  • Опубліковано 12 січ 2025

КОМЕНТАРІ • 79

  • @Augmented_AI
    @Augmented_AI  2 роки тому +1

    💻Source Code - augmentedstartups.info/VisionStore
    Want to Learn YOLOv7 and solve real-world problems?
    🚀Get Notified of the YOLOv7 Course here - lnkd.in/dJ2j9ukU
    ☕ Buy me a Coffee/Chai - augmentedstartups.info/BuyMeCoffee

    • @alghozali5391
      @alghozali5391 Рік тому

      hi bro
      but now
      how to save data set after training and load to running in other colab
      thx for all

  • @jonatapaulino
    @jonatapaulino Рік тому +1

    Once again thanks for the video. This video is serving as a basis for my learning. I noticed that you don't generate the mAP. Can you show me which command lines I could generate the mAP?

  • @jonatapaulino
    @jonatapaulino 2 роки тому +3

    Hello. I really like your videos, they are very informative. I have a doubt. If I already have my model trained, where can I start running my code in colab? That is, I know I don't need to run from the beginning, but I don't know where I can start running from since I already have my weights. Thank you friend.

  • @RENZOFRANCISCOAYALAMENDOZA
    @RENZOFRANCISCOAYALAMENDOZA 2 роки тому +3

    hello sir, in the training step i still getting this error "RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu)", i try several things but can't fix it, help me please :c

    • @Augmented_AI
      @Augmented_AI  2 роки тому

      Please join our WhatsApp group we can help you there chat.whatsapp.com/JTuIB3eEfDRGo0TL4RzqwB

  • @imenselmi9230
    @imenselmi9230 Рік тому

    Can you make video about model inference using NVIDIA triton server and yolo how optimise the model using triton

  • @prasannaravijr1420
    @prasannaravijr1420 Рік тому

    Hi can you tell how to show bounding box and its values for an output of an image

  • @olgamykhaylyuk62
    @olgamykhaylyuk62 Рік тому

    Thanks for the video, really good explained.
    Just one question I cannot train the data, it stop on inialization. Please help
    Epoch gpu_mem box obj cls total labels img_size
    0% 0/293 [00:00

    • @Augmented_AI
      @Augmented_AI  Рік тому

      Please join our WhatsApp group chat.whatsapp.com/JTuIB3eEfDRGo0TL4RzqwB

    • @Augmented_AI
      @Augmented_AI  Рік тому

      We can help you there

  • @nakulmali1413
    @nakulmali1413 2 роки тому +2

    Hi sir first upon thanks for your videos and efforts. Sir i am following your yolov7 playlist. Sir i request you please upload one videos on object detection and measure the actual size of detected object using yolov7

    • @Augmented_AI
      @Augmented_AI  2 роки тому +2

      I'm glad that you have enjoyed my videos and playlist 😁. Yeah that sounds like great idea. I'll add it our project list.

    • @nakulmali1413
      @nakulmali1413 2 роки тому +1

      @@Augmented_AI Thanks sir

    • @Ajitkm8
      @Ajitkm8 2 роки тому

      @@Augmented_AI make a video on shoplifting projects using object detection

  • @danialabyazi6697
    @danialabyazi6697 2 роки тому

    Thank you for the great introduction of YOLOV7 code. Do you know how we can access to detected boundary box information from code?

  • @captainezzy3870
    @captainezzy3870 Рік тому

    thanks sir
    i have a prroblem in 6.2 YOLOv7 Inference on Video. the frames stoped prossing at frame number 22 and i have tried deernt videos. can you help me with that please.

  • @devfordevs
    @devfordevs 2 роки тому +1

    how we convert/export this model to tflite model for using in edge device

    • @Augmented_AI
      @Augmented_AI  2 роки тому

      We show that in yolo+ www.augmentedstartups.com/yolo-plus

  • @arslanahmadbhatti6267
    @arslanahmadbhatti6267 2 роки тому +2

    Can you have a word on camera calibration in yolov5 deepsort

    • @Augmented_AI
      @Augmented_AI  2 роки тому +1

      We can do it but we will work on the yolov7 version

    • @arslanahmadbhatti6267
      @arslanahmadbhatti6267 2 роки тому +1

      @@Augmented_AI can you tell me that why is the output of yolov5+deepsort on cpu is different and on gpu is different

    • @arslanahmadbhatti6267
      @arslanahmadbhatti6267 2 роки тому +1

      I have recently worked on helmet detection basically on yolov5+deepsort to extract the voilators number plates its working perfectly on cpu but on gpu it is giving false ids to objects like motorbike person and also helmet if its present i don't got the point of giving different output on cpu and different on gpu.

    • @arslanahmadbhatti6267
      @arslanahmadbhatti6267 2 роки тому +2

      Very generous of you if you light up my path

  • @maxbunnies
    @maxbunnies 2 роки тому +1

    This is cool 😎 is there anyway I can run this locally with my own gpu on computers I don’t understand google colab

    • @Augmented_AI
      @Augmented_AI  2 роки тому +1

      Yes we show this in both our free and paid yolov7 course. www.augmentedstartups.com/yolo-plus

  • @husseingharakhani8002
    @husseingharakhani8002 2 роки тому

    Thanks for your great videos. I am trying to perform fruit pose estimation. Do you think it is possible to do it with YOLO or other models?

  • @WeeMono93
    @WeeMono93 2 роки тому

    Hi there, Great video with alot of great information! Looking for some help as when i get to checking it on a video, the results flips my video upside down. Is there a way to fix this so the video stays in the correct position?

  • @emmanuelakpaklikwasi4300
    @emmanuelakpaklikwasi4300 2 роки тому +1

    I really like your videos. Nice tutorial! But how do i solve this error ( indices should be either on cpu or on the same device as the indexed tensor (cpu)) on google colab

  • @alghozali5391
    @alghozali5391 Рік тому

    hi bro
    but now
    how to save data set after training and load to running in other colab
    thx for all

  • @nadeemahmad833
    @nadeemahmad833 2 роки тому +1

    getting this same error that you have encountered while using camera section at the end "NameError: name 'torch' is not defined", Can you please tell me how I can resolve it.

    • @Augmented_AI
      @Augmented_AI  2 роки тому

      Please join our WhatsApp group chat.whatsapp.com/KotRg5RlKGdBh2V3ip6yzk

  • @patthachaputthanesmaneerat7623
    @patthachaputthanesmaneerat7623 2 роки тому

    I try to train yolov7 with my custom dataset and run compare with yolov5n (same dataset and epoch). Why a training time per each epoch of v7 is slower than v5 and at the last epoch v5 have mAP higher than v7. Did I do something wrong? Is there a chance it will happen? Thank you

  • @abrarluvrabit
    @abrarluvrabit 2 роки тому

    Can we also do active learning in our coding like out of 20 testing images my system detect 19 correct images but only 1 incorrect detection so how can i tell my system about this 1 incorrect image detection so next time it will not repeat the same mistake again. and how can i do that without training the entire model again?

  • @moahaimen
    @moahaimen 2 роки тому +1

    I need your help I need to emerge Yolov5 or V7 to LSTM to Human action Recognition can you help me?

    • @Augmented_AI
      @Augmented_AI  2 роки тому

      Let's chat on whatsapp www.augmentedstartups.info/whatsapp

  • @faishalichal8934
    @faishalichal8934 2 роки тому

    can i just upload it to roboflow?? because i already labelling in labelimg thanks

  • @rob26r
    @rob26r 2 роки тому

    Any suggestions for me? I detected an object but I want to register or align it automatically. Any thoughts on how I can do this?

  • @AntiEevee
    @AntiEevee 2 роки тому +1

    I dont have coffee! how can i succeed now ;-;

  • @gsayak
    @gsayak Рік тому +1

    Can we not upload our own dataset? instead of using roboflow?

  • @itayhilel2168
    @itayhilel2168 2 роки тому +1

    can you show how to bring yolov7 in to unity?

    • @Augmented_AI
      @Augmented_AI  2 роки тому

      That is a cool tutorial to have! Let me look into it

  • @fahimmahafuzruhad9485
    @fahimmahafuzruhad9485 2 роки тому

    Sir how can we check ta accuracy of our model?

  • @jonatapaulino
    @jonatapaulino 2 роки тому +1

    when I run the training in colab it gives the following error: RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu)

    • @russellseangonzalve4566
      @russellseangonzalve4566 2 роки тому +1

      same, did you already resolve it?

    • @jonatapaulino
      @jonatapaulino 2 роки тому

      @@russellseangonzalve4566 I decided to search the internet. Do you need the solution?

    • @russellseangonzalve4566
      @russellseangonzalve4566 2 роки тому +1

      @@jonatapaulino yes I still need it 😁

    • @kagansenkeser4357
      @kagansenkeser4357 2 роки тому

      @@jonatapaulino hi I need solution ı have the same issue

    • @kagansenkeser4357
      @kagansenkeser4357 2 роки тому

      ​@@russellseangonzalve4566 hi I need solution ı have the same issue

  • @abrarluvrabit
    @abrarluvrabit 2 роки тому +1

    another great video thanks alot Sir for helping us (Students) in the object detection field.
    Can you please also make a video on a Multi-label object dection in a single bounding box. I have a dataset that involves images with bounding boxes which have more than 1 label.
    For example, I have 5 classes (0-4), then an image might have a bounding box with label "2" and another might have a bounding box with two labels "2, 4" ie it belongs to both categories. so how can we show two labels or classes on a single bounding box? please make a video on this or atleast provide some solution in your ans here i will be very thankful to you.

    • @Augmented_AI
      @Augmented_AI  2 роки тому

      We are going yo be covering that in our yolo+ course www.augmentedstartups.com/yolo-plus

  • @IOOOFatihAdjiWidjanarko
    @IOOOFatihAdjiWidjanarko 8 місяців тому

    can anyone help me with the code inference? i tried everything but it doesn't work

  • @jenaiitmandi306
    @jenaiitmandi306 2 роки тому +1

    Sir, Can Yolov7 handle varying image sizes in a dataset ?

    • @Augmented_AI
      @Augmented_AI  2 роки тому +1

      Yes it can. But for any object detection model. It's best to feed your model a dataset of consistent sized images

    • @jenaiitmandi306
      @jenaiitmandi306 2 роки тому

      Sir, now I am implementing Yolov7 on custom dataset and I m getting an error in Dataloader part... I hv arranged d data as described. Can u tell about Cache file ?

    • @Augmented_AI
      @Augmented_AI  2 роки тому +1

      @@jenaiitmandi306 Please join our whatsapp computer vision group chat.whatsapp.com/HuwhV3D7Wbo8qOO7l1doQq we can help you here

    • @jenaiitmandi306
      @jenaiitmandi306 2 роки тому

      @@Augmented_AI Thanks. So kind of u.

    • @sametst1903
      @sametst1903 2 роки тому

      @@Augmented_AI can u resend the whatsapp group link? :)

  • @FalkarSlowmotion
    @FalkarSlowmotion Рік тому

    /content/gdrive/MyDrive/yolov7
    2023-07-12 23:49:57.539025: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
    To enable the following instructions: AVX2 AVX512F FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
    2023-07-12 23:49:58.405597: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
    why on 3.2 Start Training I got this error message ? how can i resolve this problem sir.... thank you

  • @errrbrrr3821
    @errrbrrr3821 2 роки тому

    can it be deployed to raspberry pi?

  • @faezehfereydonian9227
    @faezehfereydonian9227 2 роки тому

    how can use yolov7 as a feature extraction ??

  • @munnabhaii
    @munnabhaii 10 місяців тому

    Hello, is there anyone here has any idea about Chip Defect Detection Based On YoloV7?

  • @NiraUshi
    @NiraUshi 3 місяці тому

    Please share this code

  • @hodlRoarhodlRoar
    @hodlRoarhodlRoar 2 роки тому

    Can you run YOLOV7 on a mobile phone

  • @techkhid4836
    @techkhid4836 2 роки тому

    I keep getting a key error anytime I try to fetch the device key from opt in the video inference

  • @TheRealKitWalker
    @TheRealKitWalker 2 роки тому

    Trash - Not trash reminded me so much of jians pizza no pizza 😜

  • @maheshKumar-iw4qb
    @maheshKumar-iw4qb 2 роки тому

    I need your guide
    Detect the object how to save the local disk how to save the local disk and save the current and date time
    Develop the this type

  • @modeltrainer1246
    @modeltrainer1246 2 роки тому +1

    . i bought your yolo+ course. apparently it's not helping me with this. = multi cam object detection. with only CPU (one server has 4+ cams). GPU not allowed. please do research and give best solution. now a days companies don't want us to use GPU. such a headache. please do it. don't think much. MAKE THIS TUTORIAL.

    • @Augmented_AI
      @Augmented_AI  2 роки тому +1

      Thanks for the suggestion. We have had some requests for multi-cam detection which means that we will be developing it for YOLOv7. Also please add your ideas into the Suggestion box here and we'll incorporate them into the curriculum. doo.vote/251960b

    • @modeltrainer1246
      @modeltrainer1246 2 роки тому

      @@Augmented_AI thanks. please make sure that this it should be specifically for CPU. not jetson nano. not gpu.

  • @russellseangonzalve4566
    @russellseangonzalve4566 2 роки тому

    I cannot train it there's something wrong with the code

  • @UsamaAlDarwashi
    @UsamaAlDarwashi Рік тому

    thaaaaaaaaaaaaaaaaaaaaaaanks

  • @fanzaeldanendra
    @fanzaeldanendra 8 місяців тому

    can't open file '/content/gdrive/MyDrive/yolov7/train.py': [Errno 2] No such file or directory
    i have this error