arpanmangal / covidaid Goto Github PK

Can we use covidaid for binary classification?(normal and covid)

Traceback (most recent call last):
File "/content/CovidAID/tools/transfer.py", line 32, in
chexnet_model = load_weights(chexnet_model_checkpoint)
File "/content/CovidAID/tools/transfer.py", line 22, in load_weights
model = torch.load(checkpoint_pth)
File "/usr/local/lib/python3.7/dist-packages/torch/serialization.py", line 581, in load
with _open_file_like(f, 'rb') as opened_file:
File "/usr/local/lib/python3.7/dist-packages/torch/serialization.py", line 230, in _open_file_like
return _open_file(name_or_buffer, mode)
File "/usr/local/lib/python3.7/dist-packages/torch/serialization.py", line 211, in init
super(_open_file, self).init(open(name, mode))
FileNotFoundError: [Errno 2] No such file or directory: './data/CheXNet_model.pth.tar'

what should be the model path?

Hey, after making your model torch>1.0 compatible I got the RISE "explainer" predictions for the covid-19 file "4-x-day1.jpg" twice. The predictions are the same:

but the heatmaps produced by RISE look totally different:

Does the same happen to your torch<1.0 model? If not, do you know what could be the issue?

I am getting assertion error in transfer.py code in line no:46
assert len(c_keys.difference(t_keys)) == 0
The error is:

AssertionError Traceback (most recent call last)
~\CovidAID-master\tools\transfer.py in
44 #print (len(c_keys.difference(t_keys)))
45 #print (len(t_keys.difference(c_keys)))
---> 46 assert len(c_keys.difference(t_keys)) == 0
47 assert len(t_keys.difference(c_keys)) == 0
48

AssertionError:

python3 tools/transfer.py --combine_pneumonia
Traceback (most recent call last):
File "tools/transfer.py", line 45, in
assert len(c_keys.difference(t_keys)) == 0
AssertionError

I am using google colab to run the code. Whenever I am running the code using "!python trainer.py", it is showing this error.
usage: trainer.py [-h] [--local_rank LOCAL_RANK] --mode {train,test,f1}
--checkpoint CHECKPOINT [--combine_pneumonia] [--save SAVE]
[--start START] [--lr LR] [--freeze] [--bs BS]
[--cm_path CM_PATH] [--roc_path ROC_PATH]
trainer.py: error: the following arguments are required: --checkpoint
An exception has occurred, use %tb to see the full traceback.
SystemExit: 2
Can you please help me with this?

I followed all the commands provided in Getting_Started.md file. Previously i installed all the dependent modules mentioned in install.md file. When i run the trainer.py with necessary arguments, the following error occurs.

Distributed training OFF
Loading model from ../models/CovidAID_transfered.pth.tar
Freezing feature layers
100%|██████████| 115/115.0 [02:07<00:00, 1.11s/it]
0%| | 0/10.0 [00:00<?, ?it/s]
Traceback (most recent call last):
File "/home/sabuj/PycharmProjects/CovidAid/tools/trainer.py", line 438, in
start_epoch=args.start, save_path=args.save, freeze_feature_layers=args.freeze)
File "/home/sabuj/PycharmProjects/CovidAid/tools/trainer.py", line 147, in train
for i, (inputs, target) in tqdm(enumerate(val_loader), total=len(val_dataset)/BATCH_SIZE):
File "/home/sabuj/PycharmProjects/CovidAid/venv/lib/python3.6/site-packages/tqdm/std.py", line 1178, in iter
for obj in iterable:
File "/home/sabuj/PycharmProjects/CovidAid/venv/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 210, in next
return self._process_next_batch(batch)
File "/home/sabuj/PycharmProjects/CovidAid/venv/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 230, in _process_next_batch
raise batch.exc_type(batch.exc_msg)
IndexError: Traceback (most recent call last):
File "/home/sabuj/PycharmProjects/CovidAid/venv/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 42, in _worker_loop
samples = collate_fn([dataset[i] for i in batch_indices])
File "/home/sabuj/PycharmProjects/CovidAid/venv/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 42, in
samples = collate_fn([dataset[i] for i in batch_indices])
File "/home/sabuj/PycharmProjects/CovidAid/tools/read_data.py", line 157, in getitem
image_name = random.choice(self.image_names[class_idx])
File "/usr/lib/python3.6/random.py", line 260, in choice
raise IndexError('Cannot choose from an empty sequence') from None
IndexError: Cannot choose from an empty sequence

Can anyone please suggest what might be causing this issue?

Hi, I was just trying to replicate the ROC's you presented in your paper using the test_set you described in prepare_data.py. I'm executing trainer.py with your proposed settings:

                "--mode","test",
                "--checkpoint","path_to_CovidAID_transfered.pth.tar",
                "--cm_path","path_to_plots/cm_best",
                "--roc_path","path_to_plots/roc_best",
                "--combine_pneumonia"

I see that default batch size is 64 which brings the total inputs.shape to [640,3,224,224] (default 10 crops). This doesn't fit on GPU's memory. I was wondering what other settings you used to validate on the test set? E.g.: did you added a specific batch size "--bs","1" or did you use the distributed processing - if so can you explain to me how to use this in your code?
Thanks!

Present code requires pytorch0.3 and CUDA<=8.0. The code needs to be updated to support pytorch>1.0. The main reason for using pytorch0.3 is compatibility with trained CheXNet model.