I've created a project in Azure Custom Vision (Object Detection, General Compact, Tier S0). I uploaded about 70 images, 35 images per tag then started training my model.
Checked tags in the Iterations screen after training (Quick Training) was done. For my surprise, only 7 images were tested per tag.
Tried to run Advanced Training for 1 hour. Nothing has changed. Only 7 images per tag were tested.
Am I doing something wrong?
Is there a way to use all images for object detection training so it can give me a better accuracy?
Thanks,
+ftex
What you are seeing in the test interface after the training is only a part of the total images because these metrics are calculated using k-fold cross validation.
You are not doing something wrong. It would not be logic to test all the images because it would mean testing with your training images.
To have a better accuracy, there's no magic: add more images, relevant to your use-case
https://learn.microsoft.com/en-us/azure/cognitive-services/custom-vision-service/getting-started-build-a-classifier#evaluate-the-classifier
Related
I’m currently working on object detection using yolov5. I trained a model with a custom dataset which has 3 classes = [‘Car’,‘Motorcycle’,‘Person’]
I have many questions related to yolov5.
All the custom images are labelled using Roboflow.
question1 : As you can see from the table that my dataset has mix of images with different sizes. Will this be a problem in training? And also assume that i’ve trained the model and got ‘best.pt’. Will that model work efficiently in any dimensions of images/videos.
question 2:
Is this directory model correct for training. Even i have ‘test’ directory but it seems that the directory is not at all used. The images in the ‘test’ folder is useless. ( I know that i’m asking dumb questions, please bare with me.)
Is it ok if place all my images like this
And should i need a ‘test’ folder?
question3: What is the ‘imgsz’ in detect.py? Is it downsampling the input source?
I’ve spent more than 3 weeks in yolo. I love it but i find some parts difficult to grasp. kindly provide suggestion for this questions. Thanks in advance.
"question1 : As you can see from the table that my dataset has mix of images with different sizes. Will this be a problem in training? And also assume that i’ve trained the model and got ‘best.pt’. Will that model work efficiently in any dimensions of images/videos."
As long as you've resized/normalized all of your images to be the same square size, then you should be fine. YOLO trains on square images. You can use a platform like Roboflow to process your images so they not only come out in the right structure (for your images and annotation files) but also resize them while generating your dataset so they are all the same size. http://roboflow.com/ - you just need to make a public workspace to upload your images to and you can use the platform free. Here's a video that covers custom training with YOLOv5: https://www.youtube.com/watch?v=x0ThXHbtqCQ
Roboflow's python package can also be used to extract your images programmatically: https://docs.roboflow.com/python
"Is this directory model correct for training. Even i have ‘test’ directory but it seems that the directory is not at all used. The images in the ‘test’ folder is useless. ( I know that i’m asking dumb questions, please bare with me.)"
Yes that directory model is correct from training. Its what I have whenever I run YOLOv5 training too.
You do need a test folder if you want to run inference against the test folder images to learn more about your model's performance.
The 'imgsz' parameter in detect.py is for setting the height/width of the images for inference. You set it at the value you used for --img when you ran train.py.
For example: Resized images to 640 by 640 when generating your images for training? Use (640, 640) for the 'imgsz' parameter (that is the default value). And that would also mean you set --img to 640 when you ran train.py
detect.py parameters (YOLOv5 Github repo)
train.py parameters (YOLOv5 Github repo)
YOLOv5's Github: Tips for Best Training Results https://github.com/ultralytics/yolov5/wiki/Tips-for-Best-Training-Results
Roboflow's Model Production Tips: https://docs.roboflow.com/model-tips
I am implementing YOLOv3 and have trained the model on my custom class ( which is tomato). I have used the darknet model 53 weights ( https://pjreddie.com/media/files/darknet53.conv.74) to start my training as per the instructions provided by many sites on training and object detection using YOLOv3 . I thought it was not necessary to list down the steps.
One of my object images used for training is shown below ( with bounding boxes using LabelImg):
The txt file for the above image for the bounding boxes contains the following coordinates , as created using labellmg:
0 0.152807 0.696655 0.300640 0.557093
0 0.468728 0.705306 0.341862 0.539792
0 0.819652 0.695213 0.337242 0.543829
0 0.317164 0.271626 0.324449 0.501730
Now when I use the same image for testing to determine the accuracy of detection, it is unable to detect all the tomatoes and moreover the bounding boxes are way off from the objects as shown below:
I am not sure what is going on.
I have cloned the git
https://github.com/AlexeyAB/darknet and did a local make and trained the model on the custom object. Nothing fancy.
The pictures above were taken from my phone. I have trained the darknet using a combination of downloaded images and custom tomato pictures I had taken from my phone. I have 290 images for training.
Maybe your model can't generalize well. Maybe your are training too much, which can cause over-fitting or even your dataset is small.
You can try testing on a never seen data (a new tomato picture) and sees if it does well.
Double-check your config files, if something is incorrect there, like you are using a yolov4 cfg in a yolov3 model.
And I recommend that you read this article in which can help you understand better how neural networks works:
https://towardsdatascience.com/understand-neural-networks-model-generalization-7baddf1c48ca
Im trying to use the Faster R-CNN Algorithm for vehicle detection using keras.
I have a dataset containing different folders with every folder containing multiple images. I've managed to transform the annotation files for the images into a CSV file for training process. the annotation files contain extra information about region to be ignored in the images during the training (black zones in the attached image). The image show the bounding boxes for the vehicles along with the ignored zones in the image in a test example based on the information obtained from the annotation file for this image.
Is there a way to specify the specific zones to focus on or to ignore while during training of the algorithm?
The loss function is modified to not penalize predictions inside these ignore annotation areas as false positives during training.
This phrase is of bellow article (Sec.3.2), a good way but I don't know how to do it.
Vandersteegen, Maarten, Kristof Van Beeck, and Toon Goedemé. "Super accurate low latency object detection on a surveillance UAV." 2019 16th International Conference on Machine Vision Applications (MVA). IEEE, 2019.
I am trying to train a classification network. For my classification purpose, I don't have any publicly available data set. For deep ConvNets, large number of training data is needed. It is really time consuming to create such a large data set. Is there any way to generate large number of images from few images?
For example, 1000 images from a few 20 images for training.
If someone knows the answer, kindly help me.
Thanking you in advance.
You can use image augmentation for generating more images (for example flipping the image)
https://pytorch.org/docs/stable/torchvision/transforms.html
I am trying to implement YOLOv2 on my custom dataset. Is there any minimum number of images required for each class?
There is no minimum images per class for training. Of course the lower number you have, the model will converge slowly and the accuracy will be low.
What important, according to Alexey's (popular forked darknet and the creator of YOLO v4) how to improve object detection is :
For each object which you want to detect - there must be at least 1
similar object in the Training dataset with about the same: shape,
side of object, relative size, angle of rotation, tilt, illumination.
So desirable that your training dataset include images with objects at
diffrent: scales, rotations, lightings, from different sides, on
different backgrounds - you should preferably have 2000 different
images for each class or more, and you should train 2000*classes
iterations or more
https://github.com/AlexeyAB/darknet
So I think you should have minimum 2000 images per class if you want to get the optimum accuracy. But 1000 per class is not bad also. Even with hundreds of images per class you can still get decent (not optimum) result. Just collect as many images as you can.
It depends.
There is an objective minimum of one image per class. That may work with some accuracy, in principle, if using data-augmentation strategies and fine-tuning a pretrained YOLO network.
The objective reality, however, is that you may need as many as 1000 images per class, depending on your problem.