I have a huge amount of points data set. so i want to find min and max values from these points set. now i am using normal for loop for this purpose nice it is working but i want to know posibility to use opencv library since i wish to use this library. so plese any one help me. thanks
There are several options. Using OpenCV for this may give you an easy way to use SSE or other partially par
http://docs.opencv.org/search.html?q=minMax&check_keywords=yes&area=default
Some of those can use the GPU to help. Of course, the GPU will only be faster if your data was already in the GPU. Pushing data across the bus onto your video card just for this kind of search would be a net loss.
Use std::max_element() with a single channel cv::Mat like this:
img = img / *max_element(img.begin<float>(), img.end<float>());
No need for OpenCV in this case: it's already in the standard library (std::min_element and std::max_element).
Related
I am currently using Tensorflow 2.0 with a simple CNN, i am initializing the first layer with some handcrafted filters that i would like to visualize during the learning process.
In the histogram part of tensorboard i only see the first kernel of the layer but i would like to see all of them. Is there an easy way to do this?
Thanks in advance
Creating a small function that does this on the displaycallback during the epoch end is the way i solved it, is not the cleanest , and would be nice if someone can correct it :)
class DisplayCallback(tf.keras.callbacks.Callback):
def on_epoch_end(self, epoch, logs=None):
variables_names = [v.name for v in model.trainable_variables]
with file_writer_cm.as_default():
for i in range(model.layers[0].get_weights()[0].shape[3]):
tf.summary.histogram(variables_names[0].split('/')[0]+"/kernel_"+str(i), model.layers[0].get_weights()[0][:,:,:,i], step=epoch)
I'd like to use Caffe to extract image features. However, it takes too long to process an image, so I'm looking for ways to optimize for speed.
One thing I noticed is that the network definition I'm using has four extra layers on top the one from which I'm reading a result (and there are no feedback signals, so they should be safe to delete).
I tried to delete them from the definition file but it had no effect at all. I guess I might need to remove the corresponding part of the file that contains pre-trained weights, too. That is, however, a binary file (a protobuffer) so editing it is not that easy.
Do you think that removing the four layers might have a profound effect of the net performance?
If so then how do I get familiar with the file contents so that I could edit it and how do I know which parts to remove?
first, I don't think removing the binary weights will have any effect.
Second, you can do it easily using the python interface: see this tutorial.
Last but not least, have you tried running caffe time to measure the performance of your net? this may help you identify the bottlenecks of your computations.
PS,
You might find this thread relevant as well.
Caffemodel stores data as key-value pair. Caffe only copies weight for those layers (in train.prototxt) having exactly same name as caffemodel. Hence I don't think removing binary weights will work. If you want to change network structure, just modify train.prototxt and deploy.txt.
If you insist to remove weights from binary file, follow this caffe example.
And to make sure you delete right part, this visualizing tool should help.
I would retrain on a smaller input size, change strides, etc. However if you want to reduce file size, I'd suggest quantizing the weights https://github.com/yuanyuanli85/CaffeModelCompression and then using something like lzma compression (xz for unix). We do this so we can deploy to mobile devices. 8 bit weights compress nicely.
is there a DWT (discrete wavelet transform ) function in opencv ?? else if anyone have link of its implementation in c++
No, I don't believe OpenCV has that functionality.
This page might be useful.
It appears that openCV does not have an implementation of the DWT algorithm, but a quick google search turns up two results which may be relevant.
First is a result from Koders code search, which is an implementation designed to process MPEG4 frames for an image decoding program.
There is also a google code project, wavelet1d which is a version designed to process a 1d array of data.
You may be able to use those two implementations to build your own suitable for your uses?
I need to use the connected component labeling algorithm on an image in a C++ application. I can implement that myself, but I was trying to use Boost's union-find/disjoint sets implementation since it was mentioned in the union-find wiki article.
I can't figure out how to create the disjoint_sets object so that it'll work with the image data I have (unsigned shorts). What am I missing? The examples in the Boost documentation aren't making any sense to me. Do I need all the extra Graph mumbo-jumbo in those examples when I have an image? OR, is there already an OpenCV connected component labeling implementation. Currently we're using OpenCV 1.1pre1 and Boost 1.37.
Surprisingly, there is no CCL in OpenCV. However, there is a workaround that is described in the reference manual. See the example for cvDrawContours. When I tried to use it, I had some strange behaviour on first and last rows and columns of an image, but I probably did something wrong.
An alternative way is to use cvBlobs library.
We ended up writing the algorithms for CCL and Union-Find ourselves using the descriptions found on Wikipedia and elsewhere. It seemed easier and faster than adding another library to our application just for this purpose.
Another possibility is to use the source codes provided provided by Ali Rahimi, and you can have a look at this.
I was able to use disjoint_sets of the boost library for the connected component labeling.
But to test, I was trying to create an image with pixel intensities having the value same as its label.
This led to the problem which I haven't been able to handle yet. Have a look at the thread.
I'm looking for a library to save an array of colour data to a PNG file. (That's all there is to it, right? I know very little about the internals of a PNG.)
This is for use in Nintendo DS development, so something lightweight is preferable. I don't need any other fancy features like rotation, etc.
To encode any kind of PNG file, libpng is the way of the walk.
However, on small devices like the DS you really want to store your image data in the format which the display hardware expects. It is technically possible to get libpng working on the platform, but it will add significant overhead, both in terms of loadtimes and footprint.
Have you looked at libpng? http://www.libpng.org/pub/png/libpng.html
I'm not sure whether the memory footprint will be acceptable, but you should probably be aware that PNG files are a lot more involved than just an array of colors. Performance is likely to be a concern on a DS.
If you go with libpng, you'll also need zlib, and if you're using DevKitPro, you'll probably run into some missing functions (from playing with the code for 5 minutes, it looks like it relies on pow() which doesn't seem to be in libnds.) I have no idea what the official Nintendo SDK offers in the way of a standard library - you might be in better shape if that's what you're using.
I managed to find a library that supports PNG (using libpng) and allows you to just give it raw image data.
It's called LibPicture. It's a bit hefty though: ~1MB.