delightcmu / casd Goto Github PK

THCudaCheck FAIL file=/pytorch/aten/src/THC/THCGeneral.cpp line=383 error=11 : invalid argument
Traceback (most recent call last):
File "./tools/trainval_net.py", line 135, in
max_iters=args.max_iters)
File "/hy-tmp/import_datasets/CASD-master_2022-01-20-210309/CASD-master/tools/../lib/model/train_val.py", line 377, in train_net
sw.train_model(max_iters)
File "/hy-tmp/import_datasets/CASD-master_2022-01-20-210309/CASD-master/tools/../lib/model/train_val.py", line 291, in train_model
cls_det_loss, refine_loss_1, refine_loss_2, consistency_loss, total_loss = self.net.train_step(blobs,self.optimizer,iter)
File "/hy-tmp/import_datasets/CASD-master_2022-01-20-210309/CASD-master/tools/../lib/nets/network.py", line 634, in train_step
self.forward(blobs['data'], blobs['image_level_labels'], blobs['im_info'], blobs['gt_boxes'], blobs['ss_boxes'], step)
File "/hy-tmp/import_datasets/CASD-master_2022-01-20-210309/CASD-master/tools/../lib/nets/network.py", line 562, in forward
roi_labels_1, keep_inds_1, roi_labels_2, keep_inds_2, bbox_pred, rois = self._predict_train(ss_boxes_all, step)
File "/hy-tmp/import_datasets/CASD-master_2022-01-20-210309/CASD-master/tools/../lib/nets/network.py", line 508, in _predict_train
roi_labels_2, keep_inds_2, bbox_pred = self._region_classification_train(pool5_roi, fc7_roi,fc7_context, fc7_frame, step)
File "/hy-tmp/import_datasets/CASD-master_2022-01-20-210309/CASD-master/tools/../lib/nets/network.py", line 398, in _region_classification_train
mask_1 = self._inverted_attention(bbox_feats_new, gt, keep_inds_1_new, 1, step, fg_num_1_new, bg_num_1_new)
File "/hy-tmp/import_datasets/CASD-master_2022-01-20-210309/CASD-master/tools/../lib/nets/network.py", line 147, in _inverted_attention
pooled_feat_before_after = torch.cat((bbox_feats_new, bbox_feats_new * mask_all), dim=0)
RuntimeError: CUDA out of memory. Tried to allocate 766.00 MiB (GPU 0; 10.76 GiB total capacity; 9.17 GiB already allocated; 658.56 MiB free; 118.66 MiB cached)

when i run， i got "RuntimeError: CUDA out of memory."i don't know how to modify.
gpu0: 12G; gpu1: 12G
my command is "bash experiments/scripts/train_faster_rcnn.sh 0 pascal_voc vgg16" or
"bash experiments/scripts/train_faster_rcnn.sh 0,1 pascal_voc vgg16". The two commands both caused "RuntimeError: CUDA out of memory"
And i modified vgg16.yml. TRAIN.BATCH_SIZE : 256 --> 2
Running Logs:

• set -e
• export PYTHONUNBUFFERED=True
• PYTHONUNBUFFERED=True
• GPU_ID=0
• DATASET=pascal_voc
• NET=vgg16
• array=($@)
• len=3
• EXTRA_ARGS=
• EXTRA_ARGS_SLUG=
• case ${DATASET} in
• TRAIN_IMDB=voc_2007_trainval
• TEST_IMDB=voc_2007_test
• STEPSIZE='[50000]'
• ITERS=100000
• ANCHORS='[8,16,32]'
• RATIOS='[0.5,1,2]'
  ++ date +%Y-%m-%d_%H-%M-%S
• LOG=experiments/logs/vgg16_voc_2007_trainval__vgg16.txt.2021-09-11_15-11-21
• exec
  ++ tee -a experiments/logs/vgg16_voc_2007_trainval__vgg16.txt.2021-09-11_15-11-21
  tee: experiments/logs/vgg16_voc_2007_trainval__vgg16.txt.2021-09-11_15-11-21: No such file or directory
• echo Logging output to experiments/logs/vgg16_voc_2007_trainval__vgg16.txt.2021-09-11_15-11-21
  Logging output to experiments/logs/vgg16_voc_2007_trainval__vgg16.txt.2021-09-11_15-11-21
• set +x
• '[' '!' -f output/vgg16/voc_2007_trainval/default/vgg16_MELM_iter_100000.pth.index ']'
• [[ ! -z '' ]]
• CUDA_VISIBLE_DEVICES=0
• python ./tools/trainval_net.py --weight data/imagenet_weights/vgg16.pth --imdb voc_2007_trainval --imdbval voc_2007_test --iters 100000 --cfg experiments/cfgs/vgg16.yml --net vgg16 --set ANCHOR_SCALES '[8,16,32]' ANCHOR_RATIOS '[0.5,1,2]' TRAIN.STEPSIZE '[50000]'
  Called with args:
  Namespace(cfg_file='experiments/cfgs/vgg16.yml', imdb_name='voc_2007_trainval', imdbval_name='voc_2007_test', max_iters=100000, net='vgg16', set_cfgs=['ANCHOR_SCALES', '[8,16,32]', 'ANCHOR_RATIOS', '[0.5,1,2]', 'TRAIN.STEPSIZE', '[50000]'], tag=None, weight='data/imagenet_weights/vgg16.pth')
  /media/omnisky/28db8425-dc36-4700-92ef-0dd7e98ccd67/djt/CASD/tools/../lib/model/config.py:369: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated, as the default Loader is unsafe. Please read https://msg.pyyaml.org/load for full details.
  yaml_cfg = edict(yaml.load(f))
  Loaded dataset voc_2007_trainval for training
  Set proposal method: selective_search
  Appending horizontally-flipped training examples...
  voc_2007_trainval ss roidb loaded from /media/omnisky/28db8425-dc36-4700-92ef-0dd7e98ccd67/djt/CASD/data/cache/voc_2007_trainval_selective_search_roidb.pkl
  done
  Preparing training data...
  done
  10022 roidb entries
  Output will be saved to /media/omnisky/28db8425-dc36-4700-92ef-0dd7e98ccd67/djt/CASD/output/vgg16_MELM/voc_2007_trainval/default
  TensorFlow summaries will be saved to /media/omnisky/28db8425-dc36-4700-92ef-0dd7e98ccd67/djt/CASD/tensorboard/vgg16_MELM/voc_2007_trainval/default
  Loaded dataset voc_2007_test for training
  Set proposal method: selective_search
  Preparing training data...
  voc_2007_test ss roidb loaded from /media/omnisky/28db8425-dc36-4700-92ef-0dd7e98ccd67/djt/CASD/data/cache/voc_2007_test_selective_search_roidb.pkl
  done
  4952 validation roidb entries
  Filtered 0 roidb entries: 10022 -> 10022
  Filtered 0 roidb entries: 4952 -> 4952
  Solving...
  Loading initial model weights from data/imagenet_weights/vgg16.pth
  Loaded.
  Traceback (most recent call last):
  File "./tools/trainval_net.py", line 135, in
  max_iters=args.max_iters)
  File "/media/omnisky/28db8425-dc36-4700-92ef-0dd7e98ccd67/djt/CASD/tools/../lib/model/train_val.py", line 377, in train_net
  sw.train_model(max_iters)
  File "/media/omnisky/28db8425-dc36-4700-92ef-0dd7e98ccd67/djt/CASD/tools/../lib/model/train_val.py", line 291, in train_model
  cls_det_loss, refine_loss_1, refine_loss_2, consistency_loss, total_loss = self.net.train_step(blobs,self.optimizer,iter)
  File "/media/omnisky/28db8425-dc36-4700-92ef-0dd7e98ccd67/djt/CASD/tools/../lib/nets/network.py", line 634, in train_step
  self.forward(blobs['data'], blobs['image_level_labels'], blobs['im_info'], blobs['gt_boxes'], blobs['ss_boxes'], step)
  File "/media/omnisky/28db8425-dc36-4700-92ef-0dd7e98ccd67/djt/CASD/tools/../lib/nets/network.py", line 562, in forward
  roi_labels_1, keep_inds_1, roi_labels_2, keep_inds_2, bbox_pred, rois = self._predict_train(ss_boxes_all, step)
  File "/media/omnisky/28db8425-dc36-4700-92ef-0dd7e98ccd67/djt/CASD/tools/../lib/nets/network.py", line 508, in _predict_train
  roi_labels_2, keep_inds_2, bbox_pred = self._region_classification_train(pool5_roi, fc7_roi,fc7_context, fc7_frame, step)
  File "/media/omnisky/28db8425-dc36-4700-92ef-0dd7e98ccd67/djt/CASD/tools/../lib/nets/network.py", line 398, in _region_classification_train
  mask_1 = self._inverted_attention(bbox_feats_new, gt, keep_inds_1_new, 1, step, fg_num_1_new, bg_num_1_new)
  File "/media/omnisky/28db8425-dc36-4700-92ef-0dd7e98ccd67/djt/CASD/tools/../lib/nets/network.py", line 147, in _inverted_attention
  pooled_feat_before_after = torch.cat((bbox_feats_new, bbox_feats_new * mask_all), dim=0)
  RuntimeError: CUDA out of memory. Tried to allocate 766.00 MiB (GPU 0; 11.91 GiB total capacity; 9.59 GiB already allocated; 99.19 MiB free; 1.49 GiB cached)

I would appreciate it if you could help me.

when i run this code, there occurred an error:'ValueError: zero-size array to reduction operation maximum which has no identity.' what should i do?

Hello! Thanks for sharing your work!

I'm trying to run your work on CUDA11 since I'm using GeForce 3090.

But when i run lib/make_cuda.sh, I met an error:

My environment setting: CUDA11.1 Pytorch 1.8.0, Torchvision 0.9.0 - GeForce 3090

If you have any idea, feel free to share it with me, please.

Hi, thank you for your interesting work.

I tried to set up the code for running. I downloaded the selective search data from the provided link and put them in data/selective_search_data but ran into this error:

Traceback (most recent call last):
  File "./tools/trainval_net.py", line 109, in <module>
    imdb, roidb = combined_roidb(args.imdb_name)
  File "./tools/trainval_net.py", line 74, in combined_roidb
    roidbs = [get_roidb(s) for s in imdb_names.split('+')]
  File "./tools/trainval_net.py", line 74, in <listcomp>
    roidbs = [get_roidb(s) for s in imdb_names.split('+')]
  File "./tools/trainval_net.py", line 71, in get_roidb
    roidb = get_training_roidb(imdb)
  File "/sequoia/data2/vavo/wsod/CASD/tools/../lib/model/train_val.py", line 331, in get_training_roidb
    imdb.append_flipped_images()
  File "/sequoia/data2/vavo/wsod/CASD/tools/../lib/datasets/imdb.py", line 113, in append_flipped_images
    boxes = self.roidb[i]['boxes'].copy()
  File "/sequoia/data2/vavo/wsod/CASD/tools/../lib/datasets/imdb.py", line 74, in roidb
    self._roidb = self.roidb_handler()
  File "/sequoia/data2/vavo/wsod/CASD/tools/../lib/datasets/pascal_voc.py", line 142, in selective_search_roidb
    ss_roidb = self._load_selective_search_roidb(gt_roidb)
  File "/sequoia/data2/vavo/wsod/CASD/tools/../lib/datasets/pascal_voc.py", line 176, in _load_selective_search_roidb
    'Selective search data not found at: {}'.format(filename)
AssertionError: Selective search data not found at: /sequoia/data2/vavo/wsod/CASD/data/selective_search_data/voc_2007_trainval.mat

Do we need to transform the .pkl files to .mat files? Can you provide the code for the transformation please?

Thanks for sharing your great work. But when I run the program, I met an error.
File "./tools/trainval_net.py", line 21, in
from nets.vgg16 import MELM_vgg16
File "/home/username/CASD/tools/../lib/nets/vgg16.py", line 10, in
from nets.network import Network
File "/home/username/CASD/tools/../lib/nets/network.py", line 18, in
from ops.roi_pool import RoIPool
File "/home/username/CASD/tools/../lib/ops/init.py", line 9, in
from .nms import nms, soft_nms
File "/home/username/CASD/tools/../lib/ops/nms/init.py", line 1, in
from .nms_wrapper import nms, soft_nms
File "/home/username/CASD/tools/../lib/ops/nms/nms_wrapper.py", line 4, in
from . import nms_cpu, nms_cuda
ImportError: libcudart.so.9.0: cannot open shared object file: No such file or directory
My Environment: python ==3.7.9, pytorch==1.1.0, torchvision == 0.3.0, cuda ==10.0
Do you have any solution to this error?

Greetings,

This is Aman Goyal. I am currently pursuing research in MSU in the domain of knowledge distillation and I had come across your paper and github repo.
I actually wanted to train on BDD100K detection dataset. Is it possible to integrate with your codebase ?

Regards,
Aman Goyal

Hi~
Does consistency_conf_loss really work?
Firstly, I run your code as you stated in README.md and found the fact that consistency_conf_loss is really small. So I guess that consistency_conf_loss may have no contribution to the performance. Then I tried remove the consistency_conf_loss and run your "baseline" again. I got nearly the same performance 53+ even when the training process had not been finished.
I wonder that the really important part of your codebase is your tricks which are not mentioned in your paper or the consistency_conf_loss.

thanks for your great work!
when I run the codes, there occurred an error: 'Selective search data not found at: data/selective_search_data/voc_2007_trainval.mat', I want to know where or how to get this file?

Hi,Nice work!

Thanks for releasing the code, I have a question about the GPU memory of this code. I ran the default parameter to train the network, like bs=1, net=vgg16. I have seen that the required GPU memory was 24G，When I used four 1080ti to train the network, I met the out of memory error, the memory of 1080ti is 11G. When are you going to release code of mutil gpu training ?

Thank you very much!

Hello, your work is excellent! Proposal files provided by you contain four .pkl files. However, codes seemingly needs .mat file. Whether are proposal files incorrect? Thank you very much! And when I directly load .pkl file as proposals, there exits 'gt_classes', 'image_level_labels' and so on. However, I can not find these in your provided .pkl files. I do not know why. Can you provide the .mat file? Thank you very much!

Hope you can open your code !

Best wishes for you~

Excuse you.
My environment configuration is: 2080ti+cuda9.0+pytorch1.1.0+torchvision 0.3.0
The following problems occur：

Traceback (most recent call last):
File "./tools/trainval_net.py", line 138, in
max_iters=args.max_iters)
File "/disk1/summer/code/CASD/tools/../lib/model/train_val.py", line 377, in train_net
sw.train_model(max_iters)
File "/disk1/summer/code/CASD/tools/../lib/model/train_val.py", line 277, in train_model
self.net.train_step_with_summary(blobs, self.optimizer, iter)
File "/disk1/summer/code/CASD/tools/../lib/nets/network.py", line 651, in train_step_with_summary
self.forward(blobs['data'], blobs['image_level_labels'], blobs['im_info'], blobs['gt_boxes'], blobs['ss_boxes'], step)
File "/disk1/summer/code/CASD/tools/../lib/nets/network.py", line 563, in forward
roi_labels_1, keep_inds_1, roi_labels_2, keep_inds_2, bbox_pred, rois = self._predict_train(ss_boxes_all, step)
File "/disk1/summer/code/CASD/tools/../lib/nets/network.py", line 500, in _predict_train
fc7_roi = self._head_to_tail(pool5_roi)
File "/disk1/summer/code/CASD/tools/../lib/nets/vgg16.py", line 58, in _head_to_tail
fc7 = self.vgg.classifier(pool5_flat)
File "/home/summer/anaconda3/envs/CASD/lib/python3.7/site-packages/torch/nn/modules/module.py", line 493, in call
result = self.forward(*input, **kwargs)
File "/home/summer/anaconda3/envs/CASD/lib/python3.7/site-packages/torch/nn/modules/container.py", line 92, in forward
input = module(input)
File "/home/summer/anaconda3/envs/CASD/lib/python3.7/site-packages/torch/nn/modules/module.py", line 493, in call
result = self.forward(*input, **kwargs)
File "/home/summer/anaconda3/envs/CASD/lib/python3.7/site-packages/torch/nn/modules/linear.py", line 92, in forward
return F.linear(input, self.weight, self.bias)
File "/home/summer/anaconda3/envs/CASD/lib/python3.7/site-packages/torch/nn/functional.py", line 1406, in linear
ret = torch.addmm(bias, input, weight.t())
RuntimeError: cublas runtime error : the GPU program failed to execute at /opt/conda/conda-bld/pytorch_1556653215914/work/aten/src/THC/THCBlas.cu:259

Do you have any suggestions ？Thanks.

I want to train it by:
bash experiments/scripts/train_faster_rcnn.sh 0,1,2,3 pascal_voc vgg16
but found an error:
Traceback (most recent call last):
File "./tools/trainval_net.py", line 21, in
from nets.vgg16 import MELM_vgg16
File "/home/share/CASD/tools/../lib/nets/vgg16.py", line 10, in
from nets.network import Network
File "/home/share/CASD/tools/../lib/nets/network.py", line 18, in
from ops.roi_pool import RoIPool
File "/home/share/CASD/tools/../lib/ops/init.py", line 13, in
from .roi_ring_pool import RoIRingPool
File "/home/share/CASD/tools/../lib/ops/roi_ring_pool/init.py", line 9, in
from .roi_ring_pool import RoIRingPool
File "/home/share/CASD/tools/../lib/ops/roi_ring_pool/roi_ring_pool.py", line 13, in
from . import roi_ring_pool_cuda
ImportError: libcudart.so.10.1: cannot open shared object file: No such file or directory

it makes my crazy,how to solve it (ㄒoㄒ)

Has anyone encountered this problem and how to solve it

Hello, your work is excellent!
But the result of your code is only 53.5% mAP, which is significantly lower than 56.8% mAP reported in your paper.
Any suggestions to how one might reproduce the published results?

the classification AP is                                                                                                                                                                                                                                                      
AP for aeroplane = 0.9836                                                                                                                                                                                                                                                     
AP for bicycle = 0.9709                                                                                                                                                                                                                                                       
AP for bird = 0.9765                                                                                                                                                                                                                                                          
AP for boat = 0.9553                                                                                                                                                                                                                                                          
AP for bottle = 0.8009                                                                                                                                                                                                                                                        
AP for bus = 0.9501                                                                                                                                                                                                                                                           
AP for car = 0.9724                                                                                                                                                                                                                                                           
AP for cat = 0.9677                                                                                                                                                                                                                                                           
AP for chair = 0.7514                                                                                                                                                                                                                                                         
AP for cow = 0.9229                                                                                                                                                                                                                                                           
AP for diningtable = 0.8283                                                                                                                                                                                                                                                   
AP for dog = 0.9770                                                                                                                                                                                                                                                           
AP for horse = 0.9687                                                                                                                                                                                                                                                         
AP for motorbike = 0.9549                                                                                                                                                                                                                                                     
AP for person = 0.9897                                                                                                                                                                                                                                                        
AP for pottedplant = 0.8265                                                                                                                                                                                                                                                   
AP for sheep = 0.9278                                                                                                                                                                                                                                                         
AP for sofa = 0.8116                                                                                                                                                                                                                                                          
AP for train = 0.9726                                                                                                                                                                                                                                                         
AP for tvmonitor = 0.9102                                                                                                                                                                                                                                                     
__________________ 
the mAP is 92.0957                                                                                                                                                                                                                                                            
Evaluating detections                                                                                                                                                                                                                                                         
Writing aeroplane VOC results file                                                                                                                                                                                                                                            
Writing bicycle VOC results file                                                                                                                                                                                                                                              
Writing bird VOC results file                                                                                                                                                                                                                                                 
Writing boat VOC results file                                                                                                                                                                                                                                                 
Writing bottle VOC results file                                                                                                                                                                                                                                               
Writing bus VOC results file                                                                                                                                                                                                                                                  
Writing car VOC results file                                                                                                                                                                                                                                                  
Writing cat VOC results file                                                                                                                                                                                                                                                  
Writing chair VOC results file                                                                                                                                                                                                                                                
Writing cow VOC results file                                                                                                                                                                                                                                                  
Writing diningtable VOC results file                                                                                                                                                                                                                                          
Writing dog VOC results file                                                                                                                                                                                                                                                  
Writing horse VOC results file                                                                                                                                                                                                                                                
Writing motorbike VOC results file                                                                                                                                                                                                                                            
Writing person VOC results file                                                                                                                                                                                                                                               
Writing pottedplant VOC results file                                                                                                                                                                                                                                          
Writing sheep VOC results file                                                                                                                                                                                                                                                
Writing sofa VOC results file                                                                                                                                                                                                                                                 
Writing train VOC results file                                                                                                                                                                                                                                                
Writing tvmonitor VOC results file 
VOC07 metric? Yes                                                                                                                                                                                                                                                             
AP for aeroplane = 0.6933                                                                                                                                                                                                                                                     
AP for bicycle = 0.6773                                                                                                                                                                                                                                                       
AP for bird = 0.5468                                                                                                                                                                                                                                                          
AP for boat = 0.3945                                                                                                                                                                                                                                                          
AP for bottle = 0.2312                                                                                                                                                                                                                                                        
AP for bus = 0.6964                                                                                                                                                                                                                                                           
AP for car = 0.6922                                                                                                                                                                                                                                                           
AP for cat = 0.7217                                                                                                                                                                                                                                                           
AP for chair = 0.2173                                              
AP for cow = 0.6577                                                
AP for diningtable = 0.4632                                        
AP for dog = 0.6464                                                
AP for horse = 0.5931                                              
AP for motorbike = 0.6789                                          
AP for person = 0.1639                                             
AP for pottedplant = 0.2502                                        
AP for sheep = 0.5352                                              
AP for sofa = 0.5645                                               
AP for train = 0.6312                                              
AP for tvmonitor = 0.6608                                          
Mean AP = 0.5358 

Hey, super interesting work. I was wondering, your paper says that N_K positive and negative proposals are selected as in OICR, and then for all of those proposals you compute your CASD attention maps/losses. OICR does no subsampling of proposals, all selective search proposals are labelled as either positive or negative and are backpropogated. Does this mean that you actually just use them all? Or do you use some other method (e.g. only the pseudo ground truths, only the positives, or using an ignore threshold as in Tang et. al. ECCV2018)?

Hi！I want to train the model with my own dataset，could you provide the code of generating selective search box？thank you very much

Thank you for your outstanding work.
During the training of the network, self.ca_iw is always False, I noticed that in network.py#L216, self.ca_iw is modified to False, but when iteration> 45000, self.ca_iw also seems to be False. The result of my training is worse than the result in the paper. Is it because ca_iw has not been used? The return value rampweight of the function that modifies self.ca_iw is also not used in the subsequent code, so I am not too clear about the logic of when to use self.ca_iw.

The total loss has not contained the layer-wise loss.

Hi,
In line216, you can find that self.ca_iw is false at the first several epochs, then it is set to true. I will complete the paralleled code soon.

Originally posted by @Justinhzy in #13 (comment)

Hi, thank you for the interesting work. I was working on a WSOD Project and found your paper to be really interesting and was implementing it for my project. While implementing it, I found a small error in the README i.e. :

While downloading the VOCdevkit you have mentioned the 18-May-2011 version to be downloaded:
wget http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCdevkit_18-May-2011.tar

But while extracting it, you have instead extracted the 8-Jun-2007 version:
tar xvf VOCdevkit_08-Jun-2007.tar

Even though it is not a significant mistake, I thought updating it might help others and make it more complete. Nevertheless, thank you for the great work!

Hi! thanks for sharing your great work. When I run the program, I met an error:
RuntimeError: cuDNN error: CUDNN_STATUS_EXECUTION_FAILED.
So could you tell me the version of cudnn you use? I try 7.6.5 and 7.6.4, but I met the same error. Thanks!

Where is this file？Is it roi_pool_cuda.cpython-37m-x86_64-linux-gnu.so this file？

Hello! I added the bbr regression head on your novel model but the result was not good. Could you share the code of this part, or explain the detail？
Thanks a lot!!

Hi, CASD is really a great job which could get perfect performance.
However, when will the code supporting parallelism be released.
And, could you tell me the performace when remove tricks that are not used in original OICR.
Thanks a lot ~

I am also confused with the cls_det_loss. It seems like different from the normal MIL loss, could you please tell more about that. -> Why using self._predictions['det_cls_prob'] which is computed with the cls_score before softmax.
Thanks~

Thanks for your great job!
I train your model on TITAN RTX and the speed is about 2.7s/iter.
Is the speed the same as yours? Or maybe it’s a problem with my GPU.
Looking forward to your reply.

bash experiments/scripts/train_faster_rcnn.sh 0 pascal_voc vgg16

Hi, I think your work is very interesting, I wonder how to use Inverted Attention (IA) in OICR, thank you!

Here self.ca_iw set to be False, and I can not see any codes setting it to be True, does it mean the consistence loss is always zero during training? Am I got something wrong or the code is not complete?

It is different from the project CASD-master. Does it mean that the project CASD-may 30 has not used the input-wise loss? Thank you.