Keras - Image Classification with two classes Tensorflow Python - python

i want to classify two classes with CNN.
first class are objects(car, building, and so go an)
secound class are NoObjects(for example Background without objects)
So, the question is, how can I realize this? I want to have many objects images for the CNN. I saw a example with Cat and Dog.. But I have only images for one class. The other class are the background. It is possible to create a background class??
I´m very new in CNN..

It seems that you're talking about semantic segmentation, where you have a variable N number of classes to localize (in this case N=1) plus the background class. There's a lot of literature and baseline models out there that can help you out. I recommend these two since they're the most popular ones:
Pretrained models: Tensorflow's model zoo
Datasets: Specifically COCO

Related

Create a model from images dataset

I have a set of images of abstract art classified by artist I want to create a model and generate images by giving the name of an artist. I came across this dataset:
https://github.com/camillegontier/DELAUNAY_dataset/issues
With Stable Diffusion and all that is happening now in early 2023, I want to know your opinion on how to train this dataset and generate new images via the artist's name or by making mixes
For example if I want to make a work in the style of Vasarely or a Mix between Vasarely & Yves Klein ...
I have bases in python, I know https://huggingface.co/, kuggle, stable diffusion but I don't know what is the easiest to achieve this goal
Thanks
I want to generate a new image based on my model

CNN on python with Keras

I made a simple CNN that classifies dogs and cats and I want this CNN to detect images that aren't cats or dogs and this must be a third different class. How to implement this? should I use R-CNN or something else?
P.S I use Keras for CNN
What you want to do is called "transfer learning" using the learned weights of a net to solve a new problem.
Please note that this is very hard and acts under many constraints i.e. using a CNN that can detect cars to detect trucks is simpler than using a CNN trained to detect people to also detect cats.
In any case you would use your pre-trained model, load the weights and continue to train it with new data and examples.
Whether this is faster or indeed even better than simply training a new model on all desired classes depends on the actual implementation and problem.
Tl:Dr
Transfer learning is hard! Unless you know what you are doing or have a specific reason, just train a new model on all classes.
You can train that almost with the same architecture (of course it depends on this architecture, if it is already bad then it will not be useful on more classes too. I would suggest to use the state of the art model architecture for dogs and cats classification) but you will also need the dogs and cats dataset in addition to this third class dataset. Unfortunately, it is not possible to use pre-trained for making predictions between all 3 classes by only training on the third class later.
So, cut to short, you will need to have all three datasets and train the model from scratch if you want to make predictions between these three classes otherwise use the pre-trained and after training it on third class it can predict if some image belongs to this third class of not.
You should train with new_category by add one more category, it contains images that are not in 2 category before. I mean
--cat_dir
-*.jpg
--dog_dir
-*.jpg
--not_at_all_dir
-*.jpg
so.. total categories you will train are 3 categories.
(categories or classes whatever it is)
then add the output of final dense fullyconnected (3 categories)

Is it possible to train model from multiple datasets for each class?

I'm pretty new to object detection. I'm using tensorflow object detection API and I'm now collecting datasets for my project
and model_main.py to train my model.
I have found and transformed two quite large datasets of cars and traffic lights with annotations. And made two tfrecords from them.
Now I want to train a pretrained model however, I'm just curious will it work? When it is possible that an image for example "001.jpg" will have of course some annotated bounding boxes of cars (it is from the car dataset) but if there is a traffic light as well it wouldn't be annotated -> will it lead to bad learning rate? (there can be many of theese "problematic" images) How should I improve this? Is there any workaround? (I really don't want to annotate the images again)
If its stupid question I'm sorry, thanks for any response - some links with this problematic would be the best !
Thanks !
The short answer is yes, it might be problematic, but with some effort you can make it possible.
If you have two urban datasets, and in one you only have annotations for traffic lights, and in the second you only have annotations for cars, then each instance of car in the first dataset will be learned as false example, and each instance of traffic light in the second dataset will be learned as false example.
The two possible outcomes I can think of are:
The model will not converge, since it tries to learn opposite things.
The model will converge, but will be domain specific. This means that the model will only detect traffic lights on images from the domain of the first dataset, and cars on the second.
In fact I tried doing so myself in a different setup, and got this outcome.
In order to be able to learn your objective of learning traffic lights and cars no matter which dataset they come from, you'll need to modify your loss function. You need to tell the loss function from which dataset each image comes from, and then only compute the loss on the corresponding classes (/zero out the loss on the classes do not correspond to it). So returning to our example, you only compute loss and backpropagate traffic lights on the first dataset, and cars on the second.
For completeness I will add that if resources are available, then the better option is to annotate all the classes on all datasets in order to avoid the suggested modification, since by only backpropagating certain classes, you do not enjoy using actual false examples for other classes.

Using machine learning to detect images based on single learning image

I have a use case where I have about 300 images out of 300 different items. I need machine learning to detect an item about once a minute.
I've been using Keras with Sequential to detect images but I'm wondering what I should take into consideration when I have 300 labels and only one image per label for learning.
So in short:
1) Can you do machine learning image detection with one learning image per label?
2) Are there any special things I take into consideration?
If this were a special case -- say, one class in 100 was represented by a single training image -- then you might get away with it. However, a unique image per class is asking for trouble.
A neural network learns by iterative correction, figuring out what features and combinations are important, and which are not, in discriminating the classes from one another. Training starts by a chaotic process that has some similarities to research: look at the available data, form hypotheses, and test then against the real world.
In a NN, the "hypotheses" are the various kernels it develops. Each kernel is a pattern to recognize something important to the discrimination process. If you lack enough examples for the model to generalize and discriminate for each class, then you run the risk (actually, you have the likelihood) of the model making a conclusion that is valid for the one input image, but not others in the same class.
For instance, one acquaintance of mine did the canonical cat-or-dog model, using his own photos, showing the pets of his own household and those of a couple of friends. The model trained well, identified cats and dogs with 100% accuracy on the test data, and he brought it into work ...
... where it failed, having an accuracy of about 65% (random guessing is 50%). He did some analysis and found the problem: his friends have indoor cats, but their preferred dog photos were out of doors. Very simply, the model had learned to identify not cats vs dogs, but rather couches and kitchen cabinets vs outdoor foliage. One of the main filters was of large, textured, green areas. Yes, a dog is a large, textured, green being. :-)
The only way your one-shot training would work is if each of your training images was specifically designed to include exactly those features that differentiate this class from the other 299, and no other visual information. Unfortunately, to identify what features those might be, and to provide canonical training photos, you'd have to know in advance what patterns the model needed to pick.
This entirely defeats the use case of deep learning and model training.
If you were to only train on that image once, it probably wouldn't be able to detect it yet. If you train it more, it will probably over fit and only recognize that one image. If that is what you are trying to do then you should make an algorithm to search the screen for that image (it will be more efficient).
1) You'll probably have problems with the generalization of your models because the lack of training set. In other words, your model will not "learn" about that class.
2) It's good to have a better training set in order to create a better model.

Train Python Object Detection Model Strait Object's Images

as the title states, is there a way to build a object detection model (with a library pytorch or tensorflow) that trains straight from the objects picture. Here's an example. This is the inputted image.
(A Clash Royale Battle Scene)
And say that I wanted it to detect a troop (Let's say the valkyrie with orange hair). I could train it with how you'd normally train it (put a box around it) and do a bunch of examples, but is there a way that I could just give it the valkyrie image (below)
And train it on that. For my situation, this will be much easier. Also I know that I said tensorflow before, but if possible I'd like not to use it as I have a 32bit system. Any help is greatly appreciated.

Categories