lsa-pucrs / acerta-abide Goto Github PK

I am trying to do model training with hdf5 . I am using python 3.6. My code is :

def hdf5_handler(filename, mode="r"):
    h5py.File(filename, "a").close()
    propfaid = h5py.h5p.create(h5py.h5p.FILE_ACCESS)
    settings = list(propfaid.get_cache())
    settings[1] = 0
    settings[2] = 0
    propfaid.set_cache(*settings)
    with contextlib.closing(h5py.h5f.open(filename, fapl=propfaid)) as fid:
        return h5py.File(fid, mode)

the function call : hdf5 = hdf5_handler("./data/abide.hdf5".encode('utf-8'), "a".encode('utf-8'))
I get the following error:
Traceback (most recent call last):
File "prepare_data.py", line 139, in
prepare_folds(hdf5, folds, pheno, derivatives, experiment="{derivative}_whole")
File "prepare_data.py", line 83, in prepare_folds
fold["train"] = ids[train_index].tolist()
File "C:\Users\jfsra\AppData\Local\Programs\Python\Python36\lib\site-packages\h5py_hl\group.py", line 385, in setitem
ds = self.create_dataset(None, data=obj, dtype=base.guess_dtype(obj))
File "C:\Users\jfsra\AppData\Local\Programs\Python\Python36\lib\site-packages\h5py_hl\group.py", line 136, in create_dataset
dsid = dataset.make_new_dset(self, shape, dtype, data, **kwds)
File "C:\Users\jfsra\AppData\Local\Programs\Python\Python36\lib\site-packages\h5py_hl\dataset.py", line 118, in make_new_dset
tid = h5t.py_create(dtype, logical=1)
File "h5py\h5t.pyx", line 1630, in h5py.h5t.py_create
File "h5py\h5t.pyx", line 1652, in h5py.h5t.py_create
File "h5py\h5t.pyx", line 1713, in h5py.h5t.py_create
TypeError: No conversion path for dtype: dtype('<U16')

Thank you for help !

Hello,. When I test ABIDE data ,the Accuracy rate instability. How to avoid this?

The instruction in README.md to install all requirements:

pip install -r requirements.txt

Fails upon trying to install tensorflow

Downloading/unpacking tensorflow-gpu (from -r requirements.txt (line 4))
  Could not find any downloads that satisfy the requirement tensorflow-gpu (from -r requirements.txt (line 4))
Cleaning up...
No distributions at all found for tensorflow-gpu (from -r requirements.txt (line 4))

Hello Team,
I really appreciate your work. I just have one question regarding the CSV dataset how did your team filter out missing data? I appreciate your help.

Looking forward to your response.

Given how python3 works, this line should be changed to

hdf5 = hdf5_handler(bytes("./data/abide.hdf5",encoding="utf-8"), "a")

By adding the comma, you are making them a nested list. This is the case at least in python3.

I'm sorry to bother you. When I was running prepare_data I met this problem . I hope you can help me answer it, thank you!!!!!!

when I run the prepared_data.py, I can't solve the problem .Could you help me? Thank you !!!!

problem:
Traceback (most recent call last):
File "D:/Project/lsa-pucrs-acerta-abide-cc28c56/prepare_data.py", line 128, in
hdf5 = hdf5_handler("./data/abide.hdf5", "a")
File "D:\Project\lsa-pucrs-acerta-abide-cc28c56\utils.py", line 50, in hdf5_handler
with contextlib.closing(h5py.h5f.open(filename, fapl=propfaid)) as fid:
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\h5f.pyx", line 65, in h5py.h5f.open
TypeError: expected bytes, str found

The instruction to run

nvidia-docker run -it --rm -v $(realpath .):/opt/acerta-abide acerta-abide /bin/bash

Fails to run in LSA (and so, this may not be completely generic)

The following error message comes to me (when in the acerta-abide git clone folder)

meneguzzi@lsa:~/code/acerta-abide$ nvidia-docker run -it --rm -v $(realpath .):/opt/acerta-abide acerta-abide /bin/bash
Using default tag: latest
nvidia-docker | 2017/03/29 22:00:45 Error: Error response from daemon: repository acerta-abide not found: does not exist or no pull access

The following error occurs while running the docker build. The latest version of tensorflow-gpu is installed.

Sending build context to Docker daemon 1.349GB
Step 1/5 : FROM gcr.io/tensorflow/tensorflow:latest-gpu
manifest for gcr.io/tensorflow/tensorflow:latest-gpu not found

Sorry to bother you!
I am wondering did you train a MLP for each fold?
If there were 10 MLP models for 10 folds, why the models could fit well on the entire dataset?
I am really confused about it. Looking forward to your reply, thank you!

Whenever I run prepare_data.py this error occurs.
I have tried adding all the answers of the previous issues about the same file, however it's still not fixed.
Is there any solution to my problem?

It should be just "experiment" instead of "experiment[0]"

In README, the example commands should be corrected

Hi there!
I am an enthusiast so I just wanted to check out the results and wanted to run the repository. I wasn't able to find steps to reproduce to run the SVM or Random Forest Classifier. Any guidance regarding that would be really great!
Also, I would like to mention that at some places the code is redundant to Python 2.

Thanks!

Update the README.md file to include instructions on how to get and prepare the data in order to run this.

Hi,

I am writing because I have reviewed and tested your code following the "cc200" derivation with 10 folds on the entire data set. However, at the time of evaluation all cases are predicted as ASD (0). Also, I have tried other configurations obtaining the same result.
I really don't understand why this is happening. It seems that the weights and final biases of the autoencoders are not being saved. I have run all the tests from Google Colaboratory. I would appreciate any instructions or suggestions on this.

Thank you very much!