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

[AniketGurav]

I have installed all packages as per instruction given on main page. But When run this code I get following error

I tensorflow/core/common_runtime/gpu/gpu_device.cc:975] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX 1080 Ti, pci bus id: 0000:02:00.0)

/home/aniket/PycharmProjects/myVirtual3/local/lib/python2.7/site-packages/tensorflow/python/ops/gradients_impl.py:91: UserWarning: Converting sparse IndexedSlices to a dense Tensor of unknown shape. This may consume a large amount of memory. "Converting sparse IndexedSlices to a dense Tensor of unknown shape. Exception in thread Thread-1: Traceback (most recent call last): File "/usr/lib/python2.7/threading.py", line 801, in __bootstrap_inner self.run() File "/usr/lib/python2.7/threading.py", line 754, in run self.target(*self.args, **self.__kwargs) File "/home/aniket/PycharmProjects/myVirtual3/local/lib/python2.7/site-packages/keras/engine/training.py", line 429, in data_generator_task generator_output = next(self._generator) File "SSD_training.py", line 235, in generate y = self.bbox_util.assign_boxes(y) File "/home/aniket/PycharmProjects/myVirtual3/ssd_keras-master/ssd_utils.py", line 149, in assign_boxes assignment[:, 5:-8][best_iou_mask] = boxes[best_iou_idx, 4:] ValueError: shape mismatch: value array of shape (20,20) could not be broadcast to indexing result of shape (20,3)

Epoch 1/5 Traceback (most recent call last): File "SSD_training.py", line 315, in nb_worker=1) File "/home/aniket/PycharmProjects/myVirtual3/local/lib/python2.7/site-packages/keras/engine/training.py", line 1532, in fit_generator str(generator_output)) ValueError: output of generator should be a tuple (x, y, sample_weight) or (x, y). Found: None

Please note this issue is not same as https://github.com/rykov8/ssd_keras/issues/61

[JunSun666]

I have the same problem. What's the solution?

[atharva-ak]

Did you get the solution? Please let me know @AniketGurav. Thanks!