Training Sample Dataset Error

[NaeemKhan333]

I am training on the Mars data set but I am facing following error "" EnqueueError: Cannot take a larger sample than population when 'replace=False' "" Please guide me

[nwojke]

Looks like there is something wrong with the data. My guess is that the error occurs during batch sampling. Have a look at issue #9. The training script prints the number of identities in the data here. What is the output?

[duyao-art]

@nwojke Hello, Thank you for your sharing for this code.

I got the following error when running the train_veri.py.

/home/duyao/anaconda3/envs/cosine_metric_learning/lib/python3.7/site-packages/tensorflow/python/summary/writer/writer.py:386: UserWarning: Attempting to use a closed FileWriter. The operation will be a noop unless the FileWriter is explicitly reopened.

However, I found the reopen.py was existed in your profile.

def reopen(self): """Reopens the EventFileWriter.

Can be called after `close()` to add more events in the same directory.
The events will go into a new events file.

Does nothing if the EventFileWriter was not closed.
"""
self.event_writer.reopen()
self._closed = False

So could you give me some advice for solving this problem? Thank you so much.

[duyao-art]

@nwojke Hello, Thank you for your sharing for this code.

I got the following error when running the train_veri.py.

/home/duyao/anaconda3/envs/cosine_metric_learning/lib/python3.7/site-packages/tensorflow/python/summary/writer/writer.py:386: UserWarning: Attempting to use a closed FileWriter. The operation will be a noop unless the FileWriter is explicitly reopened.

However, I found the reopen.py was existed in your profile.

def reopen(self): """Reopens the EventFileWriter.

Can be called after close() to add more events in the same directory. The events will go into a new events file.

Does nothing if the EventFileWriter was not closed. """ self.event_writer.reopen() self._closed = False

So could you give me some advice for solving this problem? Thank you so much.