Keras: ValueError: output of generator should be a tuple (x, y, sample_weight) or (x, y). Found: None

[monajalal]

Please suggest how to fix this?

mona@pascal:~/computer_vision/VPilot$ python train.py 
Using TensorFlow backend.
I tensorflow/stream_executor/dso_loader.cc:111] successfully opened CUDA library libcublas.so.8.0 locally
I tensorflow/stream_executor/dso_loader.cc:111] successfully opened CUDA library libcudnn.so.5.0 locally
I tensorflow/stream_executor/dso_loader.cc:111] successfully opened CUDA library libcufft.so.8.0 locally
I tensorflow/stream_executor/dso_loader.cc:111] successfully opened CUDA library libcuda.so.1 locally
I tensorflow/stream_executor/dso_loader.cc:111] successfully opened CUDA library libcurand.so.8.0 locally
/usr/local/lib/python2.7/dist-packages/keras/backend/tensorflow_backend.py:1938: UserWarning: Expected no kwargs, you passed 1
kwargs passed to function are ignored with Tensorflow backend
  warnings.warn('\n'.join(msg))
Epoch 1/1000
Exception in thread Thread-1:
Traceback (most recent call last):
  File "/usr/lib/python2.7/threading.py", line 810, in __bootstrap_inner
    self.run()
  File "/usr/lib/python2.7/threading.py", line 763, in run
    self.__target(*self.__args, **self.__kwargs)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 429, in data_generator_task
    generator_output = next(self._generator)
  File "/home/mona/computer_vision/VPilot/model.py", line 61, in dataGenerator
    x[batchCount, frameIndex, :, :, :] = cv2.imread(frameFile, mode).astype('float32')
AttributeError: 'NoneType' object has no attribute 'astype'

Traceback (most recent call last):
  File "train.py", line 56, in <module>
    callbacks=[ckp_callback]
  File "/usr/local/lib/python2.7/dist-packages/keras/models.py", line 935, in fit_generator
    initial_epoch=initial_epoch)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 1528, in fit_generator
    str(generator_output))
ValueError: output of generator should be a tuple (x, y, sample_weight) or (x, y). Found: None

code is: https://github.com/ai-tor/VPilot/blob/master/train.py

[patyork]

Your generator threw an exception:

Exception in thread Thread-1:
Traceback (most recent call last):
  File "/usr/lib/python2.7/threading.py", line 810, in __bootstrap_inner
    self.run()
  File "/usr/lib/python2.7/threading.py", line 763, in run
    self.__target(*self.__args, **self.__kwargs)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 429, in data_generator_task
    generator_output = next(self._generator)
  File "/home/mona/computer_vision/VPilot/model.py", line 61, in dataGenerator
    x[batchCount, frameIndex, :, :, :] = cv2.imread(frameFile, mode).astype('float32')
AttributeError: 'NoneType' object has no attribute 'astype'

cv2.imread() returned None, meaning, I guess, that it couldn't open the file that was specified.

---

If your issue is an implementation question, please ask your question on StackOverflow or join the Keras Slack channel and ask there instead of filing a GitHub issue.

[shyam1992atri]

Traceback (most recent call last):
File "model.py", line 163, in
main()
File "model.py", line 159, in main
train_model(model, args, *data)
File "model.py", line 120, in train_model
verbose=1)
File "/home/shyam/anaconda3/envs/car-behavioral-cloning/lib/python3.5/site-packages/keras/models.py", line 924, in fit_generator
pickle_safe=pickle_safe)
File "/home/shyam/anaconda3/envs/car-behavioral-cloning/lib/python3.5/site-packages/keras/engine/training.py", line 1481, in fit_generator
str(generator_output))
ValueError: output of generator should be a tuple (x, y, sample_weight) or (x, y). Found: None

[shyam1992atri]

can someone help me how to solve this error

[patyork]

Your generator yielded None, or nothing. It could be caused either by the generator not being in a loop and running out of data to yield, or the generator itself might cause an Exception which would give this error.

Sent from my Verizon, Samsung Galaxy smartphone
-------- Original message --------From: shyam1992atri [e-mail] Date: 6/26/17 10:54 AM (GMT-08:00) To: fchollet/keras [e-mail] Cc: Pat York [e-mail], Comment [e-mail] Subject: Re: [fchollet/keras] ValueError: output of generator should be a tuple (x, y, sample_weight) or (x, y). Found: None (#5196)
can someone help me how to solve this error

—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub, or mute the thread.

{"api_version":"1.0","publisher":{"api_key":"05dde50f1d1a384dd78767c55493e4bb","name":"GitHub"},"entity":{"external_key":"github/fchollet/keras","title":"fchollet/keras","subtitle":"GitHub repository","main_image_url":"https://cloud.githubusercontent.com/assets/143418/17495839/a5054eac-5d88-11e6-95fc-7290892c7bb5.png","avatar_image_url":"https://cloud.githubusercontent.com/assets/143418/15842166/7c72db34-2c0b-11e6-9aed-b52498112777.png","action":{"name":"Open in GitHub","url":"https://github.com/fchollet/keras"}},"updates":{"snippets":[{"icon":"PERSON","message":"@shyam1992atri in #5196: can someone help me how to solve this error\r\n"}],"action":{"name":"View Issue","url":"https://github.com/fchollet/keras/issues/5196#issuecomment-311133455"}}}

[shyam1992atri]

Thank you for your reply.
I got it fixed from here
https://github.com/llSourcell/How_to_simulate_a_self_driving_car/issues/7

[ohernpaul]

My fix was making sure batch size was int, not float when passing to flow from directory.

[Abonia1]

I got the same error and traceback as follow:

Traceback (most recent call last):
File "c:\Users\asojasingarayar.vscode\extensions\ms-python.python-2019.1.0\pythonFiles\ptvsd_launcher.py", line 45, in
main(ptvsdArgs)
File "c:\Users\asojasingarayar.vscode\extensions\ms-python.python-2019.1.0\pythonFiles\lib\python\ptvsd__main__.py", line 348, in main
run()
File "c:\Users\asojasingarayar.vscode\extensions\ms-python.python-2019.1.0\pythonFiles\lib\python\ptvsd__main__.py", line 253, in run_file
runpy.run_path(target, run_name='__main__')
File "C:\Users\asojasingarayar\AppData\Local\Continuum\anaconda3\envs\car-behavioral-cloning\lib\runpy.py", line 254, in run_path
pkg_name=pkg_name, script_name=fname)
File "C:\Users\asojasingarayar\AppData\Local\Continuum\anaconda3\envs\car-behavioral-cloning\lib\runpy.py", line 96, in _run_module_code
mod_name, mod_spec, pkg_name, script_name)
File "C:\Users\asojasingarayar\AppData\Local\Continuum\anaconda3\envs\car-behavioral-cloning\lib\runpy.py", line 85, in _run_code
exec(code, run_globals)
File "d:\MyProjects\finding-lanes\Simulate-Self-driving-Car\model.py", line 174, in
main()
File "d:\MyProjects\finding-lanes\Simulate-Self-driving-Car\model.py", line 170, in main
train_model(model, args, *data)
File "d:\MyProjects\finding-lanes\Simulate-Self-driving-Car\model.py", line 131, in train_model
verbose=1)
File "C:\Users\asojasingarayar\AppData\Local\Continuum\anaconda3\envs\car-behavioral-cloning\lib\site-packages\keras\models.py", line 924, in fit_generator
pickle_safe=pickle_safe)
File "C:\Users\asojasingarayar\AppData\Local\Continuum\anaconda3\envs\car-behavioral-cloning\lib\site-packages\kerasengine\training.py", line 1481, in fit_generator
str(generator_output))
ValueError: output of generator should be a tuple (x, y, sample_weight) or (x, y). Found: None

Model train script is available here

[sunshower76]

I solve this problem.
I think that 'segmentation_models' is implemented using 'keras' not 'tf.keras'.

Error version(for using segmentation models)
import tensorflow Class Datagenerator('tf.keras.utils.Sequence')

Revised Version
import keras class Datagenerator('keras.utils.Sequence')

and it worked. I hope you guys get help. thanks

[S26825]

validation_data should be a tuple (val_x, val_y, val_sample_weight) or `(val_x, val_y)