Division by zero #4

Michaelwhite34 · 2022-01-21T08:59:30Z

(PVDNet) PS D:\PVDNet> python run.py --mode PVDNet_large_nah --config config_PVDNet_large --data random --ckpt_abs_name ckpt/PVDNet_large_nah.pytorch
Laoding Config for evaluation
Traceback (most recent call last):
File "run.py", line 311, in
config = config_lib.get_config(args.project, args.mode, args.config)
File "D:\PVDNet\configs\config_PVDNet_large.py", line 42, in get_config
IpE = math.ceil((len(list(range(0, total_frame_num - (config.frame_itr_num-1), config.frame_itr_num)))) / actual_batch_size) * config.frame_itr_num
ZeroDivisionError: division by zero

codeslake · 2022-01-21T09:02:15Z

Hi, @Michaelwhite34.

Is Cuda available on your device?

Michaelwhite34 · 2022-01-21T09:13:44Z

Hi, @Michaelwhite34.

Is Cuda available on your device?

Yes,I have a gtx 1660Ti,by the way it's on windows 10.

codeslake · 2022-01-21T09:22:27Z

I've never tried running PyTorch on Windows.
Is nvidia-smi available on Windows?
Would you prepend CUDA_VISIBLE_DEVICES=0 before the command for evaluating PVDNet?

Or, you can just set IpE=0. I just put it to check the number of iterations needed for an epoch.

Michaelwhite34 · 2022-01-21T12:54:46Z

I've never tried running PyTorch on Windows. Is nvidia-smi available on Windows? Would you prepend CUDA_VISIBLE_DEVICES=0 before the command for evaluating PVDNet?

Or, you can just set IpE=0. I just put it to check the number of iterations needed for an epoch.

After setting it to 0,(PVDNet) PS D:\PVDNet> python run.py --mode PVDNet_large_nah --config config_PVDNet_large --data random --ckpt_abs_name ckpt/PVDNet_large_nah.pytorch
Laoding Config for evaluation
Project : PVDNet_TOG2021
Mode : PVDNet_large_nah
Config: config_PVDNet_large
Network: PVDNet_large
Trainer: trainer
Loading Model...
initializing deblurring network
Traceback (most recent call last):
File "run.py", line 341, in
eval(config)
File "D:\PVDNet\eval.py", line 198, in eval
eval_quan_qual(config)
File "D:\PVDNet\eval.py", line 68, in eval_quan_qual
blur_folder_path_list, blur_file_path_list, gt_file_path_list = init(config, mode)
File "D:\PVDNet\eval.py", line 43, in init
model = create_model(config)
File "D:\PVDNet\models_init_.py", line 5, in create_model
model = lib.Model(config)
File "D:\PVDNet\models\trainers\trainer.py", line 35, in init
self.network = DeblurNet(config).to(torch.device('cuda'))
File "D:\PVDNet\models\trainers\trainer.py", line 255, in init
lib = importlib.import_module('models.archs.{}'.format(config.network_BIMNet))
File "D:\anaconda3\lib\importlib_init_.py", line 127, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
File "", line 1014, in _gcd_import
File "", line 991, in _find_and_load
File "", line 975, in _find_and_load_unlocked
File "", line 671, in _load_unlocked
File "", line 783, in exec_module
File "", line 219, in _call_with_frames_removed
File "D:\PVDNet\models\archs\liteFlowNet.py", line 6, in
if float(torch.version.cuda) > 10.1:
TypeError: float() argument must be a string or a number, not 'NoneType'

codeslake · 2022-01-21T16:26:09Z

You will need to find a way to get cuda version in Windows (which is torch.viersion.cuda in ubuntu).

Michaelwhite34 · 2022-01-22T02:14:18Z

You will need to find a way to get cuda version in Windows (which is torch.viersion.cuda in ubuntu).

codeslake · 2022-01-22T02:23:02Z

I meant to find a way to replace this line for Windows, but, since your machine has cuda 11, try replacing these 4 lines to from models.archs.torch_correlation_C11 import FunctionCorrelation

I hope the correlation layer needed for the lineFlowNet is installed without problem for Windows (I can't help with that).

Michaelwhite34 · 2022-01-22T03:27:53Z

(PVDNet) PS D:\PVDNet> python run.py --mode PVDNet_large_nah --config config_PVDNet_large --data random --ckpt_abs_name ckpt/PVDNet_large_nah.pytorch
�[1m�[32mLaoding Config for evaluation�[0m
�[1m�[31m Project : PVDNet_TOG2021�[0m
�[1m�[31m Mode : PVDNet_large_nah�[0m
�[1m�[31m Config: config_PVDNet_large�[0m
�[1m�[31m Network: PVDNet_large�[0m
�[1m�[31m Trainer: trainer�[0m
�[1m�[32mLoading Model...�[0m
�[1m�[31m initializing deblurring network�[0m
Warning! No positional inputs found for a module, assuming batch size is 1.
�[1m�[32mComputing model complexity...�[0m
Computational complexity (Macs): 1755.80841016 B
Number of parameters: 23.36178 M

Loading checkpoint 'PVDNet_large_nah.pytorch' on model 'PVDNet_large_nah':
Traceback (most recent call last):
File "run.py", line 341, in
eval(config)
File "D:\PVDNet\eval.py", line 198, in eval
eval_quan_qual(config)
File "D:\PVDNet\eval.py", line 186, in eval_quan_qual
total_itr_time = total_itr_time / total_norm
ZeroDivisionError: division by zero

codeslake · 2022-01-22T03:33:29Z

That means the evaluation has never gone through a loop. Make sure the test set is in the right place.

Michaelwhite34 · 2022-01-22T03:39:03Z

My sequence structure is D:\PVDNet\datasets\video_deblur\random\1\ *.png ...Is this not right ?

codeslake · 2022-01-22T03:42:11Z

I believe it is right. Did you change data_offset?

Michaelwhite34 · 2022-01-22T03:43:47Z

No,should I change it ?

Michaelwhite34 · 2022-01-22T03:45:28Z

emm,should I just unmark the line "config.data_offset = 'datasets/video_deblur" ?

codeslake · 2022-01-22T03:47:48Z

Set it to D:\PVDNet\datasets\video_deblur.
Also, for checking the result, change log_offet to ./.

Michaelwhite34 · 2022-01-22T03:49:41Z

(PVDNet) PS D:\PVDNet> python run.py --mode PVDNet_large_nah --config config_PVDNet_large --data random --ckpt_abs_name ckpt/PVDNet_large_nah.pytorch
Traceback (most recent call last):
File "run.py", line 201, in
from configs.config import set_train_path
File "D:\PVDNet\configs\config.py", line 43
config.data_offset = 'D:/PVDNet/datasets/video_deblur'
^
IndentationError: unexpected indent

codeslake · 2022-01-22T03:50:59Z

It says indentation error. Check the indentation.

Michaelwhite34 · 2022-01-22T03:53:06Z

Still
(PVDNet) PS D:\PVDNet> python run.py --mode PVDNet_large_nah --config config_PVDNet_large --data random --ckpt_abs_name ckpt/PVDNet_large_nah.pytorch
�[1m�[32mLaoding Config for evaluation�[0m
�[1m�[31m Project : PVDNet_TOG2021�[0m
�[1m�[31m Mode : PVDNet_large_nah�[0m
�[1m�[31m Config: config_PVDNet_large�[0m
�[1m�[31m Network: PVDNet_large�[0m
�[1m�[31m Trainer: trainer�[0m
�[1m�[32mLoading Model...�[0m
�[1m�[31m initializing deblurring network�[0m
Warning! No positional inputs found for a module, assuming batch size is 1.
�[1m�[32mComputing model complexity...�[0m
Computational complexity (Macs): 1755.80841016 B
Number of parameters: 23.36178 M

Loading checkpoint 'PVDNet_large_nah.pytorch' on model 'PVDNet_large_nah':
Traceback (most recent call last):
File "run.py", line 341, in
eval(config)
File "D:\PVDNet\eval.py", line 198, in eval
eval_quan_qual(config)
File "D:\PVDNet\eval.py", line 186, in eval_quan_qual
total_itr_time = total_itr_time / total_norm
ZeroDivisionError: division by zero

codeslake · 2022-01-22T03:54:36Z

Try to use '\' for data_offset, not '/'.

I will be out for a few hours. I am pretty sure it is the path problem.

Michaelwhite34 · 2022-01-22T03:55:46Z

Try to use '' for data_offset, not '/'.

I will be out for a few hours. I am pretty sure it is the path problem.

I am using \ already

codeslake · 2022-01-22T03:57:02Z

(PVDNet) PS D:\PVDNet> python run.py --mode PVDNet_large_nah --config config_PVDNet_large --data random --ckpt_abs_name ckpt/PVDNet_large_nah.pytorch
Traceback (most recent call last):
File "run.py", line 201, in
from configs.config import set_train_path
File "D:\PVDNet\configs\config.py", line 43
config.data_offset = 'D:/PVDNet/datasets/video_deblur'
^
IndentationError: unexpected indent

Here, you are using '/'.

Michaelwhite34 · 2022-01-22T03:57:48Z

(PVDNet) PS D:\PVDNet> python run.py --mode PVDNet_large_nah --config config_PVDNet_large --data random --ckpt_abs_name ckpt/PVDNet_large_nah.pytorch
Traceback (most recent call last):
File "run.py", line 201, in
from configs.config import set_train_path
File "D:\PVDNet\configs\config.py", line 43
config.data_offset = 'D:/PVDNet/datasets/video_deblur'
^
IndentationError: unexpected indent

Here, you are using '/'.

I changed after that.
config.data_offset = 'D:\PVDNet\datasets\video_deblur'

Michaelwhite34 · 2022-01-22T04:00:10Z

Do I need to change the line "config.data = 'DVD' # 'nah'"?

codeslake · 2022-01-22T06:27:28Z

Do I need to change the line "config.data = 'DVD' # 'nah'"?

No, it is given in python run.py --mode PVDNet_large_nah --config config_PVDNet_large --data random --ckpt_abs_name ckpt/PVDNet_large_nah.pytorch. Did you get it running?

Michaelwhite34 · 2022-01-22T06:49:47Z

Do I need to change the line "config.data = 'DVD' # 'nah'"?

No, it is given in python run.py --mode PVDNet_large_nah --config config_PVDNet_large --data random --ckpt_abs_name ckpt/PVDNet_large_nah.pytorch. Did you get it running?

still (PVDNet) PS D:\PVDNet> python run.py --mode PVDNet_large_nah --config config_PVDNet_large --data random --ckpt_abs_name ckpt/PVDNet_large_nah.pytorch
�[1m�[32mLaoding Config for evaluation�[0m
�[1m�[31m Project : PVDNet_TOG2021�[0m
�[1m�[31m Mode : PVDNet_large_nah�[0m
�[1m�[31m Config: config_PVDNet_large�[0m
�[1m�[31m Network: PVDNet_large�[0m
�[1m�[31m Trainer: trainer�[0m
�[1m�[32mLoading Model...�[0m
�[1m�[31m initializing deblurring network�[0m
Warning! No positional inputs found for a module, assuming batch size is 1.
�[1m�[32mComputing model complexity...�[0m
Computational complexity (Macs): 1755.80841016 B
Number of parameters: 23.36178 M

Loading checkpoint 'PVDNet_large_nah.pytorch' on model 'PVDNet_large_nah':
Traceback (most recent call last):
File "run.py", line 341, in
eval(config)
File "D:\PVDNet\eval.py", line 198, in eval
eval_quan_qual(config)
File "D:\PVDNet\eval.py", line 186, in eval_quan_qual
total_itr_time = total_itr_time / total_norm
ZeroDivisionError: division by zero

codeslake · 2022-01-22T07:01:54Z

Would you replace this line to the following lines and print out the result?

print(config.EVAL.data_path, config.EVAL.input_path)
blur_folder_path_list, blur_file_path_list, _ = load_file_list(config.EVAL.data_path, config.EVAL.input_path)
print(blur_file_path_list)

Michaelwhite34 · 2022-01-22T07:03:26Z

Would you replace this line to the following lines and print out the result?

print(config.EVAL.data_path, config.EVAL.input_path)
blur_folder_path_list, blur_file_path_list, _ = load_file_list(config.EVAL.data_path, config.EVAL.input_path)
print(blur_file_path_list)

Got it working,turns out I should use "/"

codeslake · 2022-01-22T07:04:41Z

Got it working, turns out I should use "/"

Great!

Michaelwhite34 · 2022-01-22T07:21:11Z

Can we deal with cuda out of memory?

codeslake · 2022-01-22T07:23:02Z

You may try smaller model e.g., python run.py --mode PVDNet_nah --config config_PVDNet --data random --ckpt_abs_name ckpt/PVDNet_nah.pytorch.
You may also try downsmaple input frames.

codeslake closed this as completed Jan 24, 2022

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Division by zero #4

Division by zero #4

Michaelwhite34 commented Jan 21, 2022

codeslake commented Jan 21, 2022

Michaelwhite34 commented Jan 21, 2022

codeslake commented Jan 21, 2022 •

edited

Michaelwhite34 commented Jan 21, 2022

codeslake commented Jan 21, 2022

Michaelwhite34 commented Jan 22, 2022

codeslake commented Jan 22, 2022 •

edited

Michaelwhite34 commented Jan 22, 2022

codeslake commented Jan 22, 2022

Michaelwhite34 commented Jan 22, 2022 •

edited

codeslake commented Jan 22, 2022

Michaelwhite34 commented Jan 22, 2022

Michaelwhite34 commented Jan 22, 2022

codeslake commented Jan 22, 2022 •

edited

Michaelwhite34 commented Jan 22, 2022 •

edited

codeslake commented Jan 22, 2022

Michaelwhite34 commented Jan 22, 2022

codeslake commented Jan 22, 2022 •

edited

Michaelwhite34 commented Jan 22, 2022

codeslake commented Jan 22, 2022

Michaelwhite34 commented Jan 22, 2022 •

edited

Michaelwhite34 commented Jan 22, 2022

codeslake commented Jan 22, 2022

Michaelwhite34 commented Jan 22, 2022

codeslake commented Jan 22, 2022

Michaelwhite34 commented Jan 22, 2022

codeslake commented Jan 22, 2022

Michaelwhite34 commented Jan 22, 2022

codeslake commented Jan 22, 2022

Division by zero #4

Division by zero #4

Comments

Michaelwhite34 commented Jan 21, 2022

codeslake commented Jan 21, 2022

Michaelwhite34 commented Jan 21, 2022

codeslake commented Jan 21, 2022 • edited

Michaelwhite34 commented Jan 21, 2022

codeslake commented Jan 21, 2022

Michaelwhite34 commented Jan 22, 2022

codeslake commented Jan 22, 2022 • edited

Michaelwhite34 commented Jan 22, 2022

codeslake commented Jan 22, 2022

Michaelwhite34 commented Jan 22, 2022 • edited

codeslake commented Jan 22, 2022

Michaelwhite34 commented Jan 22, 2022

Michaelwhite34 commented Jan 22, 2022

codeslake commented Jan 22, 2022 • edited

Michaelwhite34 commented Jan 22, 2022 • edited

codeslake commented Jan 22, 2022

Michaelwhite34 commented Jan 22, 2022

codeslake commented Jan 22, 2022 • edited

Michaelwhite34 commented Jan 22, 2022

codeslake commented Jan 22, 2022

Michaelwhite34 commented Jan 22, 2022 • edited

Michaelwhite34 commented Jan 22, 2022

codeslake commented Jan 22, 2022

Michaelwhite34 commented Jan 22, 2022

codeslake commented Jan 22, 2022

Michaelwhite34 commented Jan 22, 2022

codeslake commented Jan 22, 2022

Michaelwhite34 commented Jan 22, 2022

codeslake commented Jan 22, 2022

codeslake commented Jan 21, 2022 •

edited

codeslake commented Jan 22, 2022 •

edited

Michaelwhite34 commented Jan 22, 2022 •

edited

codeslake commented Jan 22, 2022 •

edited

Michaelwhite34 commented Jan 22, 2022 •

edited

codeslake commented Jan 22, 2022 •

edited

Michaelwhite34 commented Jan 22, 2022 •

edited