Error regarding 'exception'

[khbadii]

Hello

I tried to train my data, but I received the below error:
[[{{node PyFunc}}]]
[[{{node ITeratorGetNext}}]]

'During handling of the above exception, another exception occurred:'

[[{{node PyFunc}}]]
[[node ITeratorGetNext (defined at train.py: 60) ]]

and line 60 is:
image_ids, image, y_true_13, y_true_26, y_true_52 = iterator.get_next()

My system has no GPU and I am running the program on CPU. How can I solve it?

Regards

[xliu79]

same problem.I already trained my custom data with old version.But cannot make it with new version

[wizyoung]

Please report your detailed hardware, software environments(like tf version, python version) and detailed error logs. I'll look into this issue at this weekend.

[khbadii]

Thanks a lot.
Please find below the hardware specifications:
Processor: Intel(R) Core(TM) i5-5200U CPU @ 2.20GHz
Installed RAM: 4.00 GB
System type: 64-bit operating system, x64-based processor

, environments:
Python: version 3.7.2
TF: version 1.13.1 (some parts 2.0)
anaconda command line: version 1.7.2

, and the error on the screen:
Traceback (most recent call last):
File "C:\ProgramData\Anaconda3\Lib\site-packages\tensorflow\python\client\session.py", line 1334, in _do_call
return fn(*args)
File C:\ProgramData\Anaconda3\Lib\site-packages\tensorflow\python\client\session.py", line 1319, in _run_fn
options, feed_dict, fetch_list, target_list, run_metadata)
File C:\ProgramData\Anaconda3\Lib\site-packages\tensorflow\python\client\session.py", line 1334, in _call_tf_sessionrun
run_metadata)
tensorflow.python, framework.errors_impl.InvalidArgumentError: 0-th value returned by pyfunc_0 is int32, but experts int64
[[{{node PyFunc}}]]
[[{{node ITeratorGetNext}}]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "train.py" line 140, in
feed_dict={is_training: True})
File "C:\ProgramData\Anaconda3\Lib\site-packages\tensorflow\python\client\session.py", line 929, in run
run_metadata_ptr)
File C:\ProgramData\Anaconda3\Lib\site-packages\tensorflow\python\client\session.py", line 1152, in _run
feed_dict_tensor, options, run_metadata)
File C:\ProgramData\Anaconda3\Lib\site-packages\tensorflow\python\client\session.py", line 1328, in _do_run
run_metadata)
File C:\ProgramData\Anaconda3\Lib\site-packages\tensorflow\python\client\session.py", line 1348, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python, framework.errors_impl.InvalidArgumentError: 0-th value returned by pyfunc_0 is int32, but experts int64
[[{{node PyFunc}}]]
[[node ITeratorGetNext (defined at train.py: 60) ]]

Note: the number of lines may be different from the original train.py file. I added some 'print()' to follow the procedure. They have no effect on the process.
progress.log]

[wizyoung]

From the log you provided, I guess it's system platform related. For a quick fix, you may try changing the first np.asarray function of this line to np.asarray(img_idx_batch, np.int64).

[eain3314]

Gradient exploded! Please train again and you may need modify some parameters.
how to solve it？

[khbadii]

Hello

Thanks. That problem has been solved and it built a model with the following name in checkpoint sub-directory:
"best_model_Epoch_9_step_190.0_mAP_0.0007_loss_141.8792_lr_0.00096"
, but the training program has been stopped with the following message (line number may be changed due to adding some print command):
Traceback (most recent call last):
File "train.py",line 170, in
if loss_total.last_avg <= 2.:
AttributeError: 'AverageMeter' object has no attribute 'last_avg'
Is it serious? How can I solve it? Please find the attached file as the 'log' file:
progress.log
Thanks again.

[qfzack]

Hello

Thanks. That problem has been solved and it built a model with the following name in checkpoint sub-directory:
"best_model_Epoch_9_step_190.0_mAP_0.0007_loss_141.8792_lr_0.00096"
, but the training program has been stopped with the following message (line number may be changed due to adding some print command):
Traceback (most recent call last):
File "train.py",line 170, in
if loss_total.last_avg <= 2.:
AttributeError: 'AverageMeter' object has no attribute 'last_avg'
Is it serious? How can I solve it? Please find the attached file as the 'log' file:
progress.log
Thanks again.

I had the same problem, 'AverageMeter' object has no attribute 'last_avg' ,how did you solve it?

[henbucuoshanghai]

AttributeError: 'AverageMeter' object has no attribute 'last_avg'
why？？？？？？？？？？？？？？？？？？？？？