smivv / pytorch-django-chexnet Goto Github PK

Settings:

python 3.6.3
pytorch 0.3.0.post4
django 2.0.1
cuda

nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2016 NVIDIA Corporation
Built on Tue_Jan_10_13:22:03_CST_2017
Cuda compilation tools, release 8.0, V8.0.61

Getting this insane error:

python manage.py runserver 0:8000
Performing system checks...

System check identified no issues (0 silenced).

You have 14 unapplied migration(s). Your project may not work properly until you apply the migrations for app(s): admin, auth, contenttypes, sessions.
Run 'python manage.py migrate' to apply them.

January 31, 2018 - 04:06:50
Django version 2.0.1, using settings 'chexnetsite.settings'
Starting development server at http://0:8000/
Quit the server with CONTROL-C.
[31/Jan/2018 04:07:07] "GET / HTTP/1.1" 200 404
THCudaCheck FAIL file=/opt/conda/conda-bld/pytorch_1512386481460/work/torch/lib/THC/THCGeneral.c line=70 error=30 : unknown error
Internal Server Error: /handle
Traceback (most recent call last):
File "/home/ubuntu/anaconda3/lib/python3.6/site-packages/django/core/handlers/exception.py", line 35, in inner
response = get_response(request)
File "/home/ubuntu/anaconda3/lib/python3.6/site-packages/django/core/handlers/base.py", line 128, in _get_response
response = self.process_exception_by_middleware(e, request)
File "/home/ubuntu/anaconda3/lib/python3.6/site-packages/django/core/handlers/base.py", line 126, in _get_response
response = wrapped_callback(request, *callback_args, **callback_kwargs)
File "/home/ubuntu/chexnet/pytorch-chexnet/chexnetsite/views.py", line 26, in handle
pred = process([path])
File "/home/ubuntu/chexnet/pytorch-chexnet/classes/model.py", line 57, in process
model = DenseNet121(N_CLASSES).cuda()
File "/home/ubuntu/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 216, in cuda
return self._apply(lambda t: t.cuda(device))
File "/home/ubuntu/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 146, in _apply
module._apply(fn)
File "/home/ubuntu/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 146, in _apply
module._apply(fn)
File "/home/ubuntu/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 146, in _apply
module._apply(fn)
File "/home/ubuntu/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 152, in _apply
param.data = fn(param.data)
File "/home/ubuntu/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 216, in
return self._apply(lambda t: t.cuda(device))
File "/home/ubuntu/anaconda3/lib/python3.6/site-packages/torch/_utils.py", line 69, in cuda
return new_type(self.size()).copy(self, async)
File "/home/ubuntu/anaconda3/lib/python3.6/site-packages/torch/cuda/init.py", line 358, in _lazy_new
_lazy_init()
File "/home/ubuntu/anaconda3/lib/python3.6/site-packages/torch/cuda/init.py", line 121, in _lazy_init
torch._C._cuda_init()
RuntimeError: cuda runtime error (30) : unknown error at /opt/conda/conda-bld/pytorch_1512386481460/work/torch/lib/THC/THCGeneral.c:70
[31/Jan/2018 04:07:18] "POST /handle HTTP/1.1" 500 146635
Segmentation fault (core dumped)

1. How do I generate heatmap?

2. how do I interpret the results? I ran one on this image (xray with nodules detected) and got this result:

[ { "Atelectasis":0.49452733993530273 }, { "Cardiomegaly":0.6072946786880493 }, { "Effusion":0.5043863654136658 }, { "Infiltration":0.6327313780784607 }, { "Mass":0.4583894908428192 }, { "Nodule":0.3783107101917267 }, { "Pneumonia":0.565626323223114 }, { "Pneumothorax":0.46577414870262146 }, { "Consolidation":0.721723198890686 }, { "Edema":0.27183231711387634 }, { "Emphysema":0.6521075963973999 }, { "Fibrosis":0.3962574005126953 }, { "Pleural_Thickening":0.6883941292762756 }, { "Hernia":0.3340536057949066 } ]

hi，I would like to ask how to deploy the pytorch model using Django. When using import argpare in the model（code A）,I can not unable to start manage.py .Prompt to enter parameters for calling function（code A).Can you tell me how to solve this problem. I am looking forward to your reply.Thank your!

False positives is everywhere.

I ran on few, such as this one: https://radiopaedia.org/cases/normal-chest-x-ray..

Results:

[ { "Atelectasis":0.513898491859436 }, { "Cardiomegaly":0.4632066786289215 }, { "Effusion":0.7996526956558228 }, { "Infiltration":0.3642980754375458 }, { "Mass":0.4949002265930176 }, { "Nodule":0.2438926249742508 }, { "Pneumonia":0.35062509775161743 }, { "Pneumothorax":0.2875746786594391 }, { "Consolidation":0.5513240098953247 }, { "Edema":0.4362095892429352 }, { "Emphysema":0.5255514979362488 }, { "Fibrosis":0.4974825382232666 }, { "Pleural_Thickening":0.38915345072746277 }, { "Hernia":0.5669712424278259 } ]

I ran on few other actual CXR with no known issues.. yet its' producing all kinds of false positives. Any ideas where I might be going wrong?

what modifications would i need to make?