I tried to train my own neural net using my own imagedatabase as described in
http://caffe.berkeleyvision.org/gathered/examples/imagenet.html
However when I want to check the neural net after training on some standard images using the matlab wrapper I get the following output / error:
Done with init
Using GPU Mode
Done with set_mode
Elapsed time is 3.215971 seconds.
Error using caffe
Invalid input size
I used the matlab wrapper before to extract cnn features based on a pretrained model. It worked. So I don't think the input size of my images is the problem (They are converted to the correct size internally by the function "prepare_image").
Has anyone an idea what could be the error?
Found the solution: I was referencing the wrong ".prototxt" file (Its a little bit confusing because the files are quite similar.
So for computing features using the matlab wrapper one needs to reference the following to files in "matcaffe_demo.m":
models/bvlc_reference_caffenet/deploy.prototxt
models/bvlc_reference_caffenet/MyModel_caffenet_train_iter_450000.caffemodel
where "MyModel_caffenet_train_iter_450000.caffemodel" is the only file needed which is created during training.
In the beginning I was accidently referencing
models/bvlc_reference_caffenet/MyModel_train_val.prototxt
which was the ".prototxt" file used for training.
Related
I know Matlab has the function TrainAutoencoder(input, settings) to create and train an autoencoder. The result is capable of running the two functions of "Encode" and "Decode".
But this is only applicable to the case of normal autoencoders. What if you want to have a denoising autoencoder? I searched and found some sample codes, where they used the "Network" function to convert the autoencoder to a normal network and then Train(network, noisyInput, smoothOutput)like a denoising autoencoder.
But there are multiple missing parts:
How to use this new network object to "encode" new data points? it doesn't support the encode().
How to get the "latent" variables to the features, out of this "network'?
I appreciate if anyone could help me resolve this issue.
Thanks,
-Moein
At present (2019a), MATALAB does not permit users to add layers manually in autoencoder. If you want to build up your own, you will have start from the scratch by using layers provided by MATLAB;
In order to to use TrainNetwork(...) to train your model, you will have you find out a way to insert your data into an object called imDatastore. The difficulty for autoencoder's data is that there is NO label, which is required by imDatastore, hence you will have to find out a smart way to avoid it--essentially you are to deal with a so-called OCC (One Class Classification) problem.
https://www.mathworks.com/help/matlab/ref/matlab.io.datastore.imagedatastore.html
Use activations(...) to dump outputs from intermediate (hidden) layers
https://www.mathworks.com/help/deeplearning/ref/activations.html?searchHighlight=activations&s_tid=doc_srchtitle
I swang between using MATLAB and Python (Keras) for deep learning for a couple of weeks, eventually I chose the latter, albeit I am a long-term and loyal user to MATLAB and a rookie to Python. My two cents are that there are too many restrictions in the former regarding deep learning.
Good luck.:-)
If you 'simulation' means prediction/inference, simply use activations(...) to dump outputs from any intermediate (hidden) layers as I mentioned earlier so that you can check them.
Another way is that you construct an identical network but with the encoding part only, copy your trained parameters into it, and feed your simulated signals.
I attempt to compute the mAP of YOLO_v2 and SSD on the VOC2007 test set using VOCevaldet.m, but in both cases I reach lower mAPs than the values reported in the papers.
To produce the detection txt files in VOC format (a file per class), I use the command ./darknet detector valid cfg/voc.data cfg/yolo-voc.cfg weights/yolo-voc.weights for YOLO in darknet, and the python script score_ssd_pascal.py for SSD in Caffe.
What am I missing? Why don't I get the same results as in the papers?
Thanks.
I am using Caffe to extract features with matlab wrapper.I have 5011 images as test data set.I chopped all the layers after 'relu7' in 'deploy.prototxt'. I found out if you take the same image as input of matcaffe_demo.m and matcaffe_batch.m, you will get the different 4096-dim features.
Could someone tell me why?
what is the differences between you extract features from all these images one by one with matcaffe_demo.m and extract features by listing all these images with matcaffe_batch.m?
You can find the answer to this question at caffe github.
Basically, matcaffe_demo is used for classification and it averages results of 10 crops of the input image, while matcaffe_bathc uses only a single input.
Moreover, note that these m-files are no longer available in recent caffe versions.
Does anyone use the matlab wrapper for the caffe framework? Is there a way how to extract an 4096 dimensional feature vector from an image?
I was already following
https://github.com/BVLC/caffe/issues/432
and also tried to remove the last lines in imagenet_deploy.prototxt to remove layers as suggested in another forum on github.
But still when I run "matcaffe_demo(im, 1)" I only get a 1000 dim vector of scores (for the image net classes).
Any help would be appreciated
Kind regards
It seems that you might not be calling the correct prototxt file. If the last layer defined in the prototxt has the top blob of 4096 dimension, there is no way for the output to be 1000 dimension.
To be sure, try creating a bug in the prototxt file and see whether the program crashes. If it doesn't then the program indeed is reading some other prototxt file.
Im using the Gaussian Mixture Model to estimate loglikelihood function(the parameters are estimated by the EM algorithm)Im using Matlab...my data is of the size:17991402*1...17991402 data points of one dimension:
When I run gmdistribution.fit(X,2) I get the desired output
But when I run gmdistribution.fit(X,k) for k>2....the code crashes and I get the error"OUT OF MEMORY"..I have also tried an open source code which again gives me the same problem.Can someone help me out here?..Im basically looking for a code which will allow me to use different number of components on such a large dataset.
Thanks!!!
Is it possible for you to decrease the iteration time? The default is 100.
OPTIONS = statset('MaxIter',50,'Display','final','TolFun',1e-6)
gmdistribution.fit(X,3,OPTIONS)
Or you may consider under-sampling the original data.
A general solution to out of memory problem is described in this document.