Doubts

[AndresPMD]

Hello!

Congrats for your implementation. Currently I am working in a similar project but implementing it with full Yolov2 instead of tiny yolo. I was thinking of using a similar approach as you and my question is if your code works for training and what is still to be developed.

Please let me know any answer, thank you!

[AndresPMD]

@joycex99 I have been trying to adapt your code to the full YOLOv2 version. However I am experiencing this error:

---

ValueError Traceback (most recent call last) in () 8 verbose = 2, 9 callbacks = [early_stop, checkpoint], ---> 10 max_q_size = 3)

~/anaconda3/envs/tensorflow/lib/python3.5/site-packages/keras/legacy/interfaces.py in wrapper(*args, **kwargs) 86 warnings.warn('Update your ' + object_name + 87 ' call to the Keras 2 API: ' + signature, stacklevel=2) ---> 88 return func(*args, **kwargs) 89 wrapper._legacy_support_signature = inspect.getargspec(func) 90 return wrapper

~/anaconda3/envs/tensorflow/lib/python3.5/site-packages/keras/engine/training.py in fit_generator(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, class_weight, max_q_size, workers, pickle_safe, initial_epoch) 1875 'a tuple (x, y, sample_weight) ' 1876 'or (x, y). Found: ' + -> 1877 str(generator_output)) 1878 if len(generator_output) == 2: 1879 x, y = generator_output

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

Do you have an idea why the generator is having this issue?