yalaudah / facies_classification_benchmark Goto Github PK

In section test, line#28:

splits = [args.split if 'both' not in args.split else 'test1', 'test2']

when args.split = "test2", the output split will be ["test2", "test2"]
when args.split = "test1", the output split will be ["test1", "test2"]

@yalaudah

Hi,

The links to dropbox seem to be broken. I keep getting 404 when trying to download.

Hello! I have loved his work with facies and machine learning. I am currently doing my undergraduate work to obtain a Geophysical Engineering degree, and my project is based on the use of supervised and unsupervised neural networks to recognize facies and petrophysical attributes. At the moment I am working with the Opendtect and H&R programs but right now I am looking for a Python library that can automate the generation of Horizons and fault detection in seismic (which I am working on in time). I would really appreciate if you have any suggestions in this regard. @yalaudah

Hi Alaudah,

Thanks for sharing data and results. I am wondering if you have SEGY version of raw seismic data and label instead of numpy format.

Thanks.

Thank you for your wonderful work. If I want to change the size of the input images to even numbers, such as 255701 -> 256768, so that it is more convenient to use Unet and other networks, how should I adjust it? I look forward to your reply.

I've tried running the training part as suggested in the readme, but it seems your training validation splits are missing from the data/repository.

Could you add these files, or point me to where I can obtain these?

Traceback (most recent call last):
  File "patch_train.py", line 375, in <module>
    train(args)
  File "patch_train.py", line 84, in train
    split_train_val(args, per_val=args.per_val)
  File "patch_train.py", line 68, in split_train_val
    pjoin('data', 'splits', loader_type + '_train_val.txt'), 'w')
FileNotFoundError: [Errno 2] No such file or directory: 'data/splits/patch_train_val.txt'

Hello, Thanks for your great code for seismic facies classification. It an useful work for my research.

But, when I try it, a problem appered like follow figure.

I think that I miss a file name "data\splits\section_train_val.txt". however, I dont know how to get it.

Please Help Me！
Look Forward to Your Reply.

I am getting an error of KeyError: ((1, 1, 99), '|u1') with TypeError: Cannot handle this data type.
More specific error:

Epoch [1/101] training Loss: 1.8266
Traceback (most recent call last):
  File "/home/akshita/anaconda2/envs/Faster_RCNN/lib/python3.6/site-packages/PIL/Image.py", line 2460, in fromarray
    mode, rawmode = _fromarray_typemap[typekey]
KeyError: ((1, 1, 99), '|u1')

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "patch_train.py", line 365, in <module>
    train(args)
  File "patch_train.py", line 204, in train
    writer.add_image('train/original_label',correct_label_decoded, epoch + 1)
  File "/home/akshita/anaconda2/envs/Faster_RCNN/lib/python3.6/site-packages/tensorboardX/writer.py", line 412, in add_image
    self.file_writer.add_summary(image(tag, img_tensor), global_step, walltime)
  File "/home/akshita/anaconda2/envs/Faster_RCNN/lib/python3.6/site-packages/tensorboardX/summary.py", line 205, in image
    image = make_image(tensor, rescale=rescale)
  File "/home/akshita/anaconda2/envs/Faster_RCNN/lib/python3.6/site-packages/tensorboardX/summary.py", line 243, in make_image
    image = Image.fromarray(tensor)
  File "/home/akshita/anaconda2/envs/Faster_RCNN/lib/python3.6/site-packages/PIL/Image.py", line 2463, in fromarray
    raise TypeError("Cannot handle this data type")
TypeError: Cannot handle this data type``

I have tried the code on torch 0.4.1 and 1.0

Hello!

Are the split sizes described in the paper correctly matching the data files shapes?
In your train/test split session you state:

1. Training set: Inline range: [300-701] (402 inlines) and crosslines [300-1000] (701 crosslines)
2. Testing set 1: Inline range: [100-299] (200 inlines) and crossline range: [300-1000] (701 crosslines)
3. Testing set 2: Inline range: [100-701] (602 inlines) and crossline range: [1001-1200] (200 crosslines)

But I just opened the corresponding label files, whose shapes give me:

1. (401,701,255)
2. (200,701,255)
3. (601,200,255)

Are the inlines wrong in the volumes 1 and 3 or am I missing something?

Thank you!

Traceback (most recent call last):
File "patch_train.py", line 373, in
train(args)
File "patch_train.py", line 177, in train
for i, (images, labels) in enumerate(trainloader):
File "D:\Python\Python38\lib\site-packages\torch\utils\data\dataloader.py", line 355, in iter
return self._get_iterator()
File "D:\Python\Python38\lib\site-packages\torch\utils\data\dataloader.py", line 301, in _get_iterator
return _MultiProcessingDataLoaderIter(self)
File "D:\Python\Python38\lib\site-packages\torch\utils\data\dataloader.py", line 914, in init
w.start()
File "D:\Python\Python38\lib\multiprocessing\process.py", line 121, in start
self._popen = self._Popen(self)
File "D:\Python\Python38\lib\multiprocessing\context.py", line 224, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "D:\Python\Python38\lib\multiprocessing\context.py", line 326, in _Popen
return Popen(process_obj)
File "D:\Python\Python38\lib\multiprocessing\popen_spawn_win32.py", line 93, in init
reduction.dump(process_obj, to_child)
File "D:\Python\Python38\lib\multiprocessing\reduction.py", line 60, in dump
ForkingPickler(file, protocol).dump(obj)
OSError: [Errno 22] Invalid argument
PS D:\dz_yalaudah\facies_classification_benchmark-master> Traceback (most recent call last):
File "", line 1, in
File "D:\Python\Python38\lib\multiprocessing\spawn.py", line 116, in spawn_main
exitcode = _main(fd, parent_sentinel)
File "D:\Python\Python38\lib\multiprocessing\spawn.py", line 126, in _main
self = reduction.pickle.load(from_parent)
_pickle.UnpicklingError: pickle data was truncated