Closed fharman closed 4 years ago
Hi @fharman ,
Thanks for posting the issue on GitHub, and again, thanks for using fastmri-reproducible-benchmark
.
Like I said in my e-mail, I think the problem is that you didn't put the h5 files for the validation set in the right place. You need to put them in $FASTMRI_DATA_DIR/singlecoil_val
, which in your case is /home/fatma/fastmri-reproducible-benchmark/fastmri_recon/data/knee_singlecoil_val/singlecoil_val
.
2 minor comments:
Hi Z. Ramzi,
Thank you for your return, i encountered this error after i applied your recommendation. So i had to write down the Github. I am very novice in Github and Unet. So i faced lots of errors.
According to your recommendation, i copy validation set to the ../fastmri_recon/data folder. And of course i changed the path. But still, i have seen the same error.
I will try to apply your comments about Github. Thank you very much.
In windows, i tried some deep learning algorithms for Segnet(liver segmentation) and RCNN,FastRCNN,FasterRCNN (for pedestrian detection).(on MATLAB). I try to catch everything in my problem. I tried to install CUDA10. But encountered some problems.(attached screenshot). Is the reason of this problem because of CUDA10 installation error?
Thank you very much for help, Stay safe
Best regards,
Zaccharie Ramzi notifications@github.com, 8 Eyl 2020 Sal, 11:26 tarihinde şunu yazdı:
Hi @fharman https://github.com/fharman ,
Thanks for posting the issue on GitHub, and again, thanks for using fastmri-reproducible-benchmark.
Like I said in my e-mail, I think the problem is that you didn't put the h5 files for the validation set in the right place. You need to put them in $FASTMRI_DATA_DIR/singlecoil_val, which in your case is /home/fatma/fastmri-reproducible-benchmark/fastmri_recon/data/knee_singlecoil_val/singlecoil_val .
2 minor comments:
- for GitHub issues, in my opinion, it's better to copy-paste the error message and use backquotes '`', rather than using a screenshot. It helps for other people searching this issue, and it helps people help you.
- If you don't have access to a GPU, the training will be very slow. Do you have access to a GPU?
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/zaccharieramzi/fastmri-reproducible-benchmark/issues/94#issuecomment-688708243, or unsubscribe https://github.com/notifications/unsubscribe-auth/AO4IQ2VFC5S4J5K3TI2PPCTSEXTFBANCNFSM4Q7U5XFQ .
fatma harman fatmaharman89@gmail.com, 8 Eyl 2020 Sal, 12:51 tarihinde şunu yazdı:
Hi Z. Ramzi,
Thank you for your return, i encountered this error after i applied your recommendation. So i had to write down the Github. I am very novice in Github and Unet. So i faced lots of errors.
According to your recommendation, i copy validation set to the ../fastmri_recon/data folder. And of course i changed the path. But still, i have seen the same error.
I will try to apply your comments about Github. Thank you very much.
In windows, i tried some deep learning algorithms for Segnet(liver segmentation) and RCNN,FastRCNN,FasterRCNN (for pedestrian detection).(on MATLAB). I try to catch everything in my problem. I tried to install CUDA10. But encountered some problems.(attached screenshot). Is the reason of this problem because of CUDA10 installation error?
Thank you very much for help, Stay safe
Best regards,
Zaccharie Ramzi notifications@github.com, 8 Eyl 2020 Sal, 11:26 tarihinde şunu yazdı:
Hi @fharman https://github.com/fharman ,
Thanks for posting the issue on GitHub, and again, thanks for using fastmri-reproducible-benchmark.
Like I said in my e-mail, I think the problem is that you didn't put the h5 files for the validation set in the right place. You need to put them in $FASTMRI_DATA_DIR/singlecoil_val, which in your case is /home/fatma/fastmri-reproducible-benchmark/fastmri_recon/data/knee_singlecoil_val/singlecoil_val .
2 minor comments:
- for GitHub issues, in my opinion, it's better to copy-paste the error message and use backquotes '`', rather than using a screenshot. It helps for other people searching this issue, and it helps people help you.
- If you don't have access to a GPU, the training will be very slow. Do you have access to a GPU?
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/zaccharieramzi/fastmri-reproducible-benchmark/issues/94#issuecomment-688708243, or unsubscribe https://github.com/notifications/unsubscribe-auth/AO4IQ2VFC5S4J5K3TI2PPCTSEXTFBANCNFSM4Q7U5XFQ .
@fharman no no this problem is not about Cuda 10 (although you do have another problem with your installation of Cuda 10).
This problem is really about the location of the validation files.
Can you give the output of the following command (to be executed in the terminal):
ls -al /home/fatma/fastmri-reproducible-benchmark/fastmri_recon/data/knee_singlecoil_val/singlecoil_val | grep *.h5
?
Thank you again,
In spite of seeing the h5 files in the folder, after the command running, there is nothing. it is not listed. I am abit confused.
It did not see the h5 files.why?
best regards
Zaccharie Ramzi notifications@github.com, 8 Eyl 2020 Sal, 13:08 tarihinde şunu yazdı:
@fharman https://github.com/fharman no no this problem is not about Cuda 10 (although you do have another problem with your installation of Cuda 10).
This problem is really about the location of the validation files.
Can you give the output of the following command (to be executed in the terminal):
ls -al /home/fatma/fastmri-reproducible-benchmark/fastmri_recon/data/knee_singlecoil_val/singlecoil_val | grep *.h5
?
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/zaccharieramzi/fastmri-reproducible-benchmark/issues/94#issuecomment-688766706, or unsubscribe https://github.com/notifications/unsubscribe-auth/AO4IQ2SE6JZRPORY24TGDGTSEX7C7ANCNFSM4Q7U5XFQ .
If the command didn't list all the h5 files it means that they are not present there. An explanation might be that there are some typos in the file names, or that when you are using the file explorer you are not looking where you think you are.
Where do you think you placed the validation h5 files and what allow you to check that?
Hello,
After open the terminal in the ~/fastmri-reproducible-benchmark/fastmri_recon/data/knee_singlecoil_val, i wrote down ls -al. I saw the folder information. But still worried about why it did not find it.
total 20 drwxrwxr-x 3 fatma fatma 4096 Eyl 7 15:04 . drwxrwxr-x 7 fatma fatma 4096 Eyl 8 10:38 .. drwxrwxr-x 2 fatma fatma 12288 Kas 23 2018 singlecoil_val
Zaccharie Ramzi notifications@github.com, 8 Eyl 2020 Sal, 13:28 tarihinde şunu yazdı:
If the command didn't list all the h5 files it means that they are not present there. An explanation might be that there are some typos in the file names, or that when you are using the file explorer you are not looking where you think you are.
Where do you think you placed the validation h5 files and what allow you to check that?
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/zaccharieramzi/fastmri-reproducible-benchmark/issues/94#issuecomment-688776963, or unsubscribe https://github.com/notifications/unsubscribe-auth/AO4IQ2QCFDEPPDPX6ZNIMQLSEYBNTANCNFSM4Q7U5XFQ .
With what you did you are checking the content of ~/fastmri-reproducible-benchmark/fastmri_recon/data/knee_singlecoil_val
not ~/fastmri-reproducible-benchmark/fastmri_recon/data/knee_singlecoil_val/singlecoil_val
. Please check the content of ~/fastmri-reproducible-benchmark/fastmri_recon/data/knee_singlecoil_val/singlecoil_val
.
hi again,
when i looked at the validation path, i saw this screenshot.(attached as first screenshot) (sorry for attching screenshot but to show you the results, i have to attach) as you see , i could see the h5 files. but in the code, i encountered this error. i could not understand the reason.
The error is like this.
ValueError: No h5 files of given contrast None at path /home/fatma/fastmri-reproducible-benchmark/fastmri_recon/data/knee_singlecoil_val/singlecoil_val
How do you overcome this problem?
thank you again, best regards
Zaccharie Ramzi notifications@github.com, 8 Eyl 2020 Sal, 15:30 tarihinde şunu yazdı:
With what you did you are checking the content of ~/fastmri-reproducible-benchmark/fastmri_recon/data/knee_singlecoil_val not ~/fastmri-reproducible-benchmark/fastmri_recon/data/knee_singlecoil_val/singlecoil_val. Please check the content of ~/fastmri-reproducible-benchmark/fastmri_recon/data/knee_singlecoil_val/singlecoil_val .
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/zaccharieramzi/fastmri-reproducible-benchmark/issues/94#issuecomment-688834839, or unsubscribe https://github.com/notifications/unsubscribe-auth/AO4IQ2TDBNQL7OQRYITSL23SEYPX7ANCNFSM4Q7U5XFQ .
Hi @fharman ,
I am not sure which screenshot you are referring to which shows you have the validation h5 files located in the right place. You need to move the validation h5 files to the path indicated in the error.
Thank you again, i overcame that problem.
Now, i encountered a training error. It is
Training: 0% 0/10 [00:00<?, ?it/s] Epoch 0: 0% 0/5 [00:00<?, ?it/s]
---------------------------------------------------------------------------KeyError
Traceback (most recent call
last)run_distribute_coordinator
already.
~/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py
in fit(self, x, y, batch_size, epochs, verbose, callbacks,
validation_split, validation_data, shuffle, class_weight,
sample_weight, initial_epoch, steps_per_epoch, validation_steps,
validation_batch_size, validation_freq, max_queue_size, workers,
use_multiprocessing) 853 context.async_wait()
854 logs = tmp_logs # No error, now safe to assign to
logs.--> 855 callbacks.on_train_batch_end(step, logs)
856 epoch_logs = copy.copy(logs) 857
~/.local/lib/python3.8/site-packages/tensorflow/python/keras/callbacks.py
in on_train_batch_end(self, batch, logs) 388 if
self._should_call_train_batch_hooks: 389 logs =
self._process_logs(logs)--> 390
self._call_batch_hook(ModeKeys.TRAIN, 'end', batch, logs=logs) 391
392 def on_test_batch_begin(self, batch, logs=None):
~/.local/lib/python3.8/site-packages/tensorflow/python/keras/callbacks.py
in _call_batch_hook(self, mode, hook, batch, logs) 296 for
callback in self.callbacks: 297 batch_hook =
getattr(callback, hook_name)--> 298 batch_hook(batch, logs)
299 self._delta_ts[hook_name].append(time.time() -
t_before_callbacks) 300
~/.local/lib/python3.8/site-packages/keras_tqdm/tqdm_callback.py in
on_batch_end(self, batch, logs) 115 self.inner_count +=
update 116 if self.inner_count < self.inner_total:--> 117
self.append_logs(logs) 118 metrics =
self.format_metrics(self.running_logs) 119 desc =
self.inner_description_update.format(epoch=self.epoch,
metrics=metrics)
~/.local/lib/python3.8/site-packages/keras_tqdm/tqdm_callback.py in
append_logs(self, logs) 134 135 def append_logs(self,
logs):--> 136 metrics = self.params['metrics'] 137
for metric, value in six.iteritems(logs): 138 if metric
in metrics:
KeyError: 'metrics'
Have anyone faced a problem like this? How did you solve this problem?
Thank you for your help, Stay safe
Best regards,
Zaccharie Ramzi notifications@github.com, 9 Eyl 2020 Çar, 10:32 tarihinde şunu yazdı:
Hi @fharman https://github.com/fharman ,
I am not sure which screenshot you are referring to which shows you have the validation h5 files located in the right place. You need to move the validation h5 files to the path indicated in the error.
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/zaccharieramzi/fastmri-reproducible-benchmark/issues/94#issuecomment-689366555, or unsubscribe https://github.com/notifications/unsubscribe-auth/AO4IQ2XHAPZVAPC3VNYDZFTSE4VPVANCNFSM4Q7U5XFQ .
Hi @fharman ,
Glad to hear you solved the error. Can you open another issue for this specific problem?
Hi everyone,
I encountered an error while running.(the screenshot is attached ). Has anyone faced a problem like this and known how to overcome and solve this?
If you help, i will appreciate.