Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 5 years ago.
Improve this question
I am trying to train a HAAR Cascade for car detection from a Drone.
Because of the viewing angle of the drone, I need to detect the car from many angles, So I need to train the classifier for that.
I have many 3d car models of the cars I want to detect, Can I use them to train the classifier instead of getting images from the internet ?
The car may be not moving, so I can't use motion as a parameter.
there are many questions here.
First, to train for many angles seems to be not really optimal for me, maybe you could check some more simple approaches like in this paper about car detection
https://www.tnt.uni-hannover.de/papers/data/977/scia2013_baumann.pdf
Second, yes, you can train on synthetic data, but there will be no noise as in real life and your classifier could be much less effective finally on real data. But usually to generate synthetic DB is fast, so why not to try.
Related
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed last year.
Improve this question
I want to create a model that can predict who has speak with different word.
In this case i try to use feature
Mfcc
Melspectogram
Tempo
Chroma stft
Spectral Centroid
Spectral Bandwidth
Tempo
And for train that i am use RandomforestRegressor
It's possible to create model like that?
For the sound processing and feature extraction part, librosa is definitely going to provide you all you need.
For the machine learning part however, speaker identification (also called "voice recognition") is a relatively complex task. You probably will get more success using techniques from deep learning. You can certainly try to use random forests if you like, but you'll probably get a lower accuracy and will have to spend more time doing feature engineering. In fact, it will be a good exercise for you to compare the results you can get with the various techniques.
For an example tutorial on speaker identification using Keras, see e.g. this article.
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 2 years ago.
Improve this question
I have seen it on Shutterstock or on many websites. if you upload an image with automatically generate suggested tags.
That's commonly done using (Deep) Artificial Neural Networks (NNs).
The idea is that you feed an image into a trained NN model and it will predict a classification of the entire image, detect objects present in the image, or even label regions inside the image. There's a lot of freedom in what can be achieved. Since good models are not easy to obtain (without large amounts of data and intense training resources), there exist pretrained models that can be finetuned by the user in order to make it work on your own particular dataset (unfortunately, these models are often somewhat overfit to the dataset they have been trained on such that finetuning is necessary most of the time). I think this link will point you further into the direction how these automatically suggested tags can be generated.
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 4 years ago.
Improve this question
While reading the great book by F. Chollet, I'm experimenting with Keras / Tensorflow, on a simple Sequential model that I train on simulated images, which come from a physical analytical model.
Having full control of the simulations, I wrote a generator which produces an infinite stream of data and label batches, which I use with fit_generator in Keras. The data so generated are never identical, plus I can add some random noise to each image.
Now I'm wondering: is it a problem if the model never sees the same input data from one epoch to the next?
Can I assume my problems in getting the loss down are not due to the fact that the data are "infinite" (so I only have to concentrate on hyper parameters tuning)?
Please feel free if you have any advice for dealing with DL on simulated data.
A well trained network will pick up on patterns in the data, prioritizing new data over old. If your data comes from a constant distribution this doesn't matter, but if that distribution is changing over time it should adapt (slowly) to the more recent distribution.
The fact that the data is never identical does not matter. Most trained networks use some form of data augmentation (e.g. for image processsing, it is common for images to be randomly cropped, rotated, resized, and have color manipulations applied etc, so each example is never identical even if it comes from the same base image).
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 5 years ago.
Improve this question
I search a lot but I cannot find anything to show that how can I generate data for continuous dataset such as breastCancer? All documents are about images or text classifications.
Can you please help me construct neural network?
CNNs are useful for datasets where the features have strong temporal or spatial correlation. For instance, in the case of images, the value of a pixel is highly correlated to the neighboring pixels. If you randomly permute the pixels, then this correlation goes away, and convolution no longer makes sense.
For the breast cancer dataset, you have only 10 attributes which are not spatially correlated in this way. Unlike the previous image example, you can randomly permute these 10 features and no information is lost. Therefore, CNNs are not directly useful for this problem domain.
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 5 years ago.
Improve this question
I'm attempting a text classification task, where I have training data of around 500 restaurant reviews that are labelled across 12 categories. I spent longer than I should have implementing TF.IDF and cosine similarity for the classification of test data, only to get some very poor results (0.4 F-measure). With time not on my side now, I need to implement something significantly more effective that doesn't have a steep learning curve. I am considering using the TF.IDF values in conjunction with Naive Bayes. Does this sound sensible? I know if I can get my data in the right format, I can do this with Scikit learn. Is there anything else you recommend I consider?
Thank you.
You should try to use fasttext: https://pypi.python.org/pypi/fasttext . It can be used to classify text like this:
(don't forget to download a pretrained model here https://s3-us-west-1.amazonaws.com/fasttext-vectors/wiki.en.zip by changing the language if it's not english)
import fasttext
model = fasttext.load_model('wiki.en.bin') # the name of the pretrained model
classifier = fasttext.supervised('train.txt', 'model', label_prefix='__label__')
result = classifier.test('test.txt')
print ('P#1:', result.precision)
print ('R#1:', result.recall)
print ('Number of examples:', result.nexamples)
Every line in your training and test sets should be like this:
__label__classname Your restaurant review blah blah blah