Few weeks ago when I was preparing the dataset, the visualization of MNIST images were in gray-scale even with out using cmap='Greys'. But now the images are displayed in different color if cmap is not used(image shown below).
So I am a bit confused on whats going on.
Is it normal? if not what can I do to bring the images to their normal form?
Preview of the visualization
Related
My example is that I have an image with 5 other images on it. Whats the best way to have TensorFlow find/calculate the bounding boxes for each of those... need to take into account that in other images there might only be 3 separate images.
I've found that if I run a cv2.Laplacian on the source image it nicely outlines the 5 individual images but I'm not sure how best to use tensorflow to detect each of those bounding boxes?
UPDATE: My ONE issue is how do I use tensorflow to find each images boundaries? obviously I can find the 4 corners of the whole image but that doesn't help me - I need it to first know how many images their are and then find each of those boundaries.
I have to visualize the interactive 3D plot on tensorboard. Can the tensorboard visualize this or is there any way to display this on tensorboard.
Thank you.
Yes, you can use the mesh plugin on TensorBoard. It'll allow you to create a visualization similar to those found on Three.js . You pass in the vertices, colors, and faces of the 3D data and TensorBoard will create a 3D interactive visualization. There are other options such as projections but those are mainly used for embeddings.
I am still a beginner in deep learning, I am wondering is it necessary to have for the input images of a size equal to 32*32 (or X*X)? the dimensions of my images are 457*143.
Thank you.
If you want to implement a LeNet and train it from the scratch, you don't have to resize your images. However, if you want to do transfer learning, you'd better resize your images according to the image size of the dataset on which your neural net is already trained.
I'm trying to collect my own training data set for the image detection (Recognition, yet). Right now, I have 4 classes and 750 images for each. Each images are just regular images of the each classes; however, some of images are blur or contain outside objects such as, different background or other factors (but nothing distinguishable stuff). Using that training data set, image recognition is really bad.
My question is,
1. Does the training image set needs to contain the object in various background/setting/environment (I believe not...)?
2. Lets just say training worked fairly accurately and I want to know the location of the object on the image. I figure there is no way I can find the location just using the image recognition, so if I use the bounding box, how/where in the code can I see the location of the bounding box?
Thank you in advance!
It is difficult to know in advance what features your programm will learn for each class. But then again, if your unseen images will be in the same background, the background will play no role. I would suggest data augmentation in training; randomly color distortion, random flipping, random cropping.
You can't see in the code where the bounding box is. You have to label/annotate them yourself first in your collected data, using a tool as LabelMe for example. Then comes learning the object detector.
It is possible to produce a graphic in gnuplot of the sort of the ones that they like in neuroscienes journals, where the traces (plots) of the electric measurements are drawn over an image (density) plot of other representation of the neural activity? To be clear, I have allready managed to do it in matplotlib (pyplot), but it is to slow for the data sets that I have, and I think gnuplot could be faster and nicer. The example graphic is below.