I know the first step is to create two file lists with the corresponding labels, one for the training and one for the test set. Suppose the former is called train.txt and the latter val.txt. The paths in these file lists should be relative. The labels should start at 0 and look similar to this:
relative/path/img1.jpg 0
relative/path/img2.jpg 0
relative/path/img3.jpg 1
relative/path/img4.jpg 1
relative/path/img5.jpg 2
For each of these two sets, we will create a separate LevelDB. Is this formatted as a text file? I thought I would create a directory with several subdirectories for each of my classes. Do I manually have to create a text file?
Please see this tutorial on how to use convert_imageset to build levelDb or lmdb datasets for caffe's training.
As you can see from these instruction it does not matter how you arrange the image files on your disk (same folder/different folders...) as long as you have the correct paths in your 'train.txt'/'val.txt' files relative to '/path/to/jpegs/' argument. But if you want to use convert_imageset tool, you'll have to create a text file listing all the images you want to use.
Related
I have several HDF5 files all of which have a /dataset that contains vectors. I would like to combine all these vectors into one dataset in one file (that is repeatedly append from one file to another). The combined dataset would have chunked storage and be resizable.
Every option I've seen for doing this seems to require reading all the data into a buffer, and then writing it back out, is there a way to more simply pass a dataset/dataspace from one file to another in order to append the data?
Have you investigated h5py Group .copy() method? Although documented as a group action, it works with any h5py object (groups, datasets, links and references). By default it copies object attributes, and supports recursive copying of group members. If you prefer a command line tool, the HDF Group has one to do this. Take a look at h5copy here: HDF5 Group h5 copy doc
Here is a example that demonstrates a simple h5py .copy() implementation. It creates a set of 3 files -- each with 1 dataset (named /dataset, dtype=float, shape=(10,10)). It then creates a NEW HDF5 file, and is followed by another loop to open the previous files and copies the dataset from the "read" file (h5r) to the new "write" file (h5w).
for i in range (1,4):
with h5py.File('SO_68025342_'+str(i)+'.h5',mode='w') as h5f:
arr = np.random.random(100).reshape(10,10)
h5f.create_dataset('dataset',data=arr)
with h5py.File('SO_68025342_all.h5',mode='w') as h5w:
for i in range (1,4):
with h5py.File('SO_68025342_'+str(i)+'.h5',mode='r') as h5r:
h5r.copy('dataset', h5w, name='dataset_'+str(i) )
Here is a method to copy data from multiple files to a single dataset in the merged file. It comes with caveats: 1) all datasets must have the same shape, and 2) you know the number of datasets in advance to size the new dataset. (If not, you can create a resizeable dataset by addingmaxshape=(None,a0,a1), and then use .resize() as needed. I have another post with 2 examples here: How can I combine multiple .h5 file? Look at Methods 3a and 3b.
with h5py.File('SO_68025342_merge.h5',mode='w') as h5w:
for i in range (1,4):
with h5py.File('SO_68025342_'+str(i)+'.h5',mode='r') as h5r:
if 'dataset' not in h5w.keys():
a0, a1 = h5r['dataset'].shape
h5w.create_dataset('dataset', shape=(3,a0,a1))
h5w['dataset'][i-1,:] = h5r['dataset']
Assuming your files aren't so conveniently named, you can use glob.iglob() to loop on the file names to read. Then use .keys() to get the dataset names in each file. Also, if all of your datasets really are named /dataset, you need to come up with a naming convention for the new datasets.
Here is a link to the h5py docs with more details: h5py Group .copy() method
If you are not bound to a particular library and programming language, one way to solve your issue could be with the usage of HDFql (in C, C++, Java, Python, C#, Fortran or R).
Given that your posts seem to mention C# quite often, find below a solution in C#. It assumes that 1) the dataset name is dset, 2) each dataset is of data type float, and 3) each dataset is a vector of one dimension (size 100) - feel free to adapt the code to your concrete use-case:
// declare variable
float []data = new float[100];
// retrieve all file names (from current directory) that end with '.h5'
HDFql.Execute("SHOW FILE LIKE \\.h5$");
// create an HDF5 file named 'output.h5' and use (i.e. open) it
HDFql.Execute("CREATE AND USE FILE output.h5");
// create a chunked and extendible HDF5 dataset named 'dset' in file 'output.h5'
HDFql.Execute("CREATE CHUNKED(100) DATASET dset AS FLOAT(0 TO UNLIMITED)");
// register variable 'data' for subsequent usage (by HDFql)
HDFql.VariableRegister(data);
// loop cursor and process each file found
while(HDFql.CursorNext() == HDFql.Success)
{
// alter (i.e. extend) dataset 'dset' (from file 'output.h5') with more 100 floats
HDFql.Execute("ALTER DIMENSION dset TO +100");
// select (i.e. read) dataset 'dset' (from file found) and populate variable 'data'
HDFql.Execute("SELECT FROM \"" + HDFql.CursorGetChar() + "\" dset INTO MEMORY " + HDFql.VariableGetNumber(data));
// insert (i.e. write) values stored in variable 'data' into dataset 'dset' (from file 'output.h5') at the end of it (using an hyperslab)
HDFql.Execute("INSERT INTO dset(-1:::) VALUES FROM MEMORY " + HDFql.VariableGetNumber(data));
}
This is a bit of an abstract question.
I have a group of 28x28 px images from certain people, and I would like to label that data with each person who wrote it. How would I go about labeling it for training and testing? This is my first neural network, and I'm having difficulty finding any tutorials that suit my particular need. It feels like most Data, like MNIST/EMNIST, are already labeled.
Some more info is that I'm using Python 3, and Keras with Tensorflow backend.
I am assuming that you know who wrote each image. Then this is a matter of associating that information (the class label) with each image. There are several ways of doing this. Two common approaches are:
Folder structure
Make a folder for each class (person), and put the images inside.
Folder contents:
john/01.png
john/02.png
jane/03.png
susan/...
CSV file
In this case the images can be all in one folder, and then a dedicate Comma-Separated-Values file is used to contain
Folder contents:
dataset.csv
images/01.png
images/02.png
images/03.png
images/....
dataset.csv contents:
filename,person
images/01.png,john
images/02.png,john
images/03.png,jane
...
The CSV approach is nice if you have additional data about each file that you want to store. For instance metadata that could be relevant such as who recorded the file, when was it recorded, with what kind of equipment, what locations etc.
Combinations of the two are also possible, of course.
Limited by the device, I could only produce several h5 files (the format of each file are same with shape of [idx, 1, 224, 224]) for huge dataset (>100GB) and now I'm confused about the solution to combine these files into a single one for further training on PyTorch. enter image description here
In h5py, groups and files support copy(), which can be used to move groups (including the root group) and their contents between files.
See the docs here (scroll down a bit to find copy()):
http://docs.h5py.org/en/latest/high/group.html
The HDF5 distribution also includes a command-line tool called h5copy that can be used to move things around, and the C API has an H5Ocopy() function.
I run caffe using an image_data_layer and don't want to create an LMDB or LevelDB for the data, But The compute_image_mean tool only works with LMDB/LevelDB databases.
Is there a simple solution for creating a mean file from a list of files (the same format that image_data_layer is using)?
You may notice that recent models (e.g., googlenet) do not use a mean file the same size as the input image, but rather a 3-vector representing a mean value per image channel. These values are quite "immune" to the specific dataset used (as long as it is large enough and contains "natural images").
So, as long as you are working with natural images you may use the same values as e.g., GoogLenet is using: B=104, G=117, R=123.
The simplest solution is to create a LMDB or LevelDB database of the image set.
The complicated solution is to write a tool similar to compute_image_mean, which takes image inputs and do the transformations and find the mean!
I do not find a good way to organize various algorithms. Today the file is like this :
1/ Extraction of values from Excel
2/ First algorithm based on these values (extracted from Excel) starting with
"let matriceAlgo1 ="
3/ Second algorithm starting from the same values
"let matriceAlgo2 ="
4/ Synthesis algorithm, doing a weighted average (depending on several values) of the 2/ and 3/ and selecting the result to be shown.
"let matriceSynthesis ="
My question is the following : what should i put before the different parts of this file in order to just call them by there name ? I have seen answers explaining that Module could be an answer but I don't know how to apply it in my case (or anything else if it's not the good answer).At the end, I would like to be able to write something like this :
"launch Extraction
launch First Algorithm
launch Second Algorithm
Launch Synthesis"
The way I usually organize files is to have some clear visual separator between different sections of a file (see for example Crawler.fsx on GitHub) and then have one "main" section at the end that calls functions declared previously.
I don't really use modules unless I have a large number of functions with clashing names. It would be good idea to use modules if your algorithm consists of more functions (e.g. Alg1.initialize, Alg1.run, etc.). Then you could easily switch between using different algorithms using module alias:
module Alg = Alg1 // or Alg2
let a = Alg.initialize
Alg.run a
If the file is getting longer, then you could also move sections to separate files and use #load "File.fs" to load algorithms or functions from a file. In that case, you probably need to use modules, but you can always open the module after loading the file.