According to the paper, there were five subjects, one female and four males. I want to know the gender information of five subjects,
which one is the female?

Thank you for your help!

Is there a simple way of getting which stimulus (image) was presented at which time point? I guess it is stored somewhere?

I apologize if this is an obvious question... but I'm not familiar with the package you are using. Or do you have documentation about how to use the brain decoding toolbox somewhere?

Thanks in advance!

Edit: resolved

Hi, I use python2 and Macbook to run the code, but I get the following error, could you have a look?

Many thanks.

File "analysis_FeaturePrediction.py", line 307, in <module>
    main()
  File "analysis_FeaturePrediction.py", line 75, in main
    data_feature = bdpy.BData(image_feature)
  File "/Users/Pan/Downloads/GenericObjectDecoding/code/python/env2/lib/python2.7/site-packages/bdpy/bdata/bdata.py", line 72, in __init__
    self.load(file_name, file_type)
  File "/Users/Pan/Downloads/GenericObjectDecoding/code/python/env2/lib/python2.7/site-packages/bdpy/bdata/bdata.py", line 558, in load
    self.__load_h5(load_filename)
  File "/Users/Pan/Downloads/GenericObjectDecoding/code/python/env2/lib/python2.7/site-packages/bdpy/bdata/bdata.py", line 700, in __load_h5
    md_keys = dat["metadata"]['key'][:].tolist()
  File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
  File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
  File "/Users/Pan/Downloads/GenericObjectDecoding/code/python/env2/lib/python2.7/site-packages/h5py/_hl/group.py", line 167, in __getitem__
    oid = h5o.open(self.id, self._e(name), lapl=self._lapl)
  File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
  File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
  File "h5py/h5o.pyx", line 190, in h5py.h5o.open
KeyError: "Unable to open object (object 'metadata' doesn't exist)"

Hello,
The code is great. But I noticed that when I wanted to compute averaged features of candidate categories by myself, there is neither image ids nor script for downloading the images. So could you give me the script or images?

Dear all
Can you share stimulus images dataset with me?
I can't download all the images from the experiment.Thank you.
Best regards

Hi
while running createfigure.py no result is coming out. Also it doesn't even plot any value is it because of some python version or something?

Hey, I am trying to use this file with python 2.7.12. However, it seems like that the package provided named bdpy doesn't work well with your .mat document.

Excuse me,when I run the file "analysis_FeaturePrediction.py",There was an error.as follows:
`

Loading data
Traceback (most recent call last):
File "analysis_FeaturePrediction.py", line 306, in
main()
File "analysis_FeaturePrediction.py", line 74, in main
data_feature = bdpy.BData(image_feature)
File "/home/zjt2/.local/lib/python2.7/site-packages/bdpy/bdata/bdata.py", line 72, in init
self.load(file_name, file_type)
File "/home/zjt2/.local/lib/python2.7/site-packages/bdpy/bdata/bdata.py", line 558, in load
self.__load_h5(load_filename)
File "/home/zjt2/.local/lib/python2.7/site-packages/bdpy/bdata/bdata.py", line 700, in __load_h5
md_keys = dat["metadata"]['key'][:].tolist()
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper (/home/ilan/minonda/conda-bld/h5py_1490028130695/work/h5py/_objects.c:2846)
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper (/home/ilan/minonda/conda-bld/h5py_1490028130695/work/h5py/_objects.c:2804)
File "/opt/anaconda/envs/python2/lib/python2.7/site-packages/h5py/_hl/group.py", line 169, in getitem
oid = h5o.open(self.id, self._e(name), lapl=self._lapl)
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper (/home/ilan/minonda/conda-bld/h5py_1490028130695/work/h5py/_objects.c:2846)
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper (/home/ilan/minonda/conda-bld/h5py_1490028130695/work/h5py/_objects.c:2804)
File "h5py/h5o.pyx", line 190, in h5py.h5o.open (/home/ilan/minonda/conda-bld/h5py_1490028130695/work/h5py/h5o.c:3740)

KeyError: "Unable to open object (Object 'metadata' doesn't exist)"

`
can you tell me some reasons?

Hello!

Thank you for your excellent job! I'm doing a research using the .mat data on http://brainliner.jp/data/brainliner/Generic_Object_Decoding . However, when I tried to access this website, I got a 502 error. So I really want to know that will this website return to normal soon? Or it stops service?

Thank you for your replies! Have a good day!

Yours,
dlmdlmacy

Dear all
I have a problem when downloading the image by running your matlab code.
the error is 'The server returned the status 404 with message "Not Found" in response to the request to URL http://image-net.org/download/synset?wnid=n01518878'
could you help what is the wrong with me?
Best regards,

Excuse me, I can't understand why you used four types of computational models. CNN was enough to be used in these experiments and the results also demonstrated that CNN was more effective than others.

Hi，thanks for your share，i have a problem where is fmri_Subject1_VC.pkl

When I used pandas to extract training data from subject 1, I find two problem:

1. Maybe there is a little mistake about category index. As you can see, when I sorted table by image_index, there are only 4 images in the first category and 4 images in the 151th category.
   
2. when I use tsv file to check the relationship between the training image index and the stimulus id, I find that there may be 4 images not in right order. the No.958 image in training data is the No.959 image in the tsv file and the No.1102 image in training data is the No.1103 image in the tsv file.

Using the matlab code, after I've setup all the environment and essential data files, and run the analysis_FeaturePrediction.m file. There is always a mistake. 'Improper assignment with rectangle empty matrix' happens in line 223 in the analysis_FeaturePrediction.m.

Hi,

Following the instruction in the ReadMe file, I downloaded the .h5 files from figshare and put in the "data" directory in code/python and then tried to run the analysis_FeaturePrediction.py script. This is what it gives me:

Loading data
Traceback (most recent call last):
  File "C:/PhD/Courses/Biosignal processing/Project/PythonProject/analysis_FeaturePrediction.py", line 306, in
    main()
  File "C:/PhD/Courses/Biosignal processing/Project/PythonProject/analysis_FeaturePrediction.py", line 67, in main
    data_all[sbj] = bdpy.BData(subjects[sbj][0])
  File "C:\PhD\Courses\Biosignal processing\Project\PythonProject\venv\lib\site-packages\bdpy\bdata\bdata.py", line 79, in init
    self.load(file_name, file_type)
  File "C:\PhD\Courses\Biosignal processing\Project\PythonProject\venv\lib\site-packages\bdpy\bdata\bdata.py", line 708, in load
    self.__load_h5(load_filename)
  File "C:\PhD\Courses\Biosignal processing\Project\PythonProject\venv\lib\site-packages\bdpy\bdata\bdata.py", line 874, in __load_h5
    if isinstance(v.value, np.ndarray):
AttributeError: 'Dataset' object has no attribute 'value'

Process finished with exit code 1

I tried to debug the code but couldn't get much out of it and would appreciate any help greatly.

Thank you.

This might be a silly question... how do I map the downloaded images to the labels?

Hi,
I use your dataset in my thesis. I'm confused about one thing. You wrote in the training session that each image is presented once, but shouldn't we accept it as showing 5 pictures twice in each run? In other words, for instance is it correct to consider fMRI signals as twice generated for the 456th index image?

Hello,

every time i try to run analysis_Feature prediction.m script. ,get_refdata function has an error because trainlabels argument must be a vector and not an array. Any ideas or help about this problem?

Thank you in advance!

I am trying to run a Generic Decoding Demo program.
It shows error “Undefined function or variable 'repadd’” while trying analysis_FeaturePrediction.m
I searched for “reaped.m” in GenericObjectDecoding folder and BrainDecoderToolbox2 folder,
but I couldn’t find it. (I found “reaped.c” instead.)
Any suggestions on how to fix error?
Appreciate your help.

i got an warning error in analysis feature prediction merge results file.it is not a problem but the code was interrupted in subject2 cnn8.i have attached the screenshot(error.png)

Hello,when I run the MATLAB code analysis_FeaturePrediction.m,the error occurs in line251,when the predict_out function calls the weight_out_delay_time function，it requires the array size of 7516192768001x1750 (98000000.0GB),which is out of the max array size,I wonder is there any method to solve this problem？

Hi, recently I have been doing similar analysis on my own dataset. I wonder the difference between these two lines of code:

predAcc.image.perception = nanmean(diag(fastcorr(predPercept, testFeat)))
predAcc.image.perception = corrcoef(predPercept, testFeat)

By using corrcoef, the prediction accuracy on my data can achieve much better results than using fastcorr.

Hi @mitsuaki , I am having trouble finding all the train and test images. I used the URL links and downloaded the images from the internet directly. The total images are however not 1200 now as many links were broken and some images were also corrupt. I have in total 838 images for training and testing. If possible, could you please share all the training and test images or the images_112.npz file ? It would help me a lot.

also, I discovered, that since my images are < 1200 , I might incur problem with the corresponding fMRI matlab files. Please advise. Thanks

Hello! Firstly, thank you for your excellent work! I have one question about the dataset.

I downloaded the data at figshare. There are two kinds of files: Subject1.h5 and Subject1_ImageNetTraining/ImageNetTest/Imagery.h5 (take subject1 for example). I use bdpy to select 'ROI_VC' data, but the length is 4466 and 3444 respectively. Why does this happen? Is this because one was using SPM to preprocess and the other was using fMRIPrep?

Thank you!

i want to ask about more details for image feature file , how it's shape is (16234,) but the stimulus photos are only 1250 image

When i run matlab scirpt 'export_volume.m', it need some *.nii files (./data/Subject%0d_SpaceTemplate.nii and ./data/Subject%0d_Func.nii) and output error:
File "./data/Subject1_SpaceTemplate.nii" does not exist.
How do i get these files? Looking forward to your reply.

I just have another quick question:
Is this the correct way of extracting brain data from a particular ROI? If I run the following code, by checking the shape of X, the number of voxels in 'HVC' is 2049. However, according to the config file, num_voxel['HVC'] is 1000. Am I misunderstanding something?

import bdpy
import numpy as np 

subjects = config.subjects
rois = config.rois
num_voxel = config.num_voxel

sbj = 'Subject1'
roi = 'HVC'

data = bdpy.BData(subjects[sbj][0])
X = data.select(rois[roi])
print(np.shape(X)) 
print(num_voxel[roi])

Thank you very much in advance!