I have a function which accepts a tensor and calculates the num_classes variable from the shape of this tensor using an equation which looks something like this:
num_classes = tensor.shape[4] - 5.
now if I call this function standalone wthi random input , it works just fine, but as this function is part of a logic which computes some metric while runnnig the model on validation data after every epoch , it fails and outputs this error:
File "train.py", line 142, in <module>
main()
File "train.py", line 120, in main
train(input_size,
File "train.py", line 81, in train
face_detector.fit(train_data_generator ,
File "/home/yogeesh/yogeesh/tf2/lib/python3.8/site-packages/keras/engine/training.py", line 1215, in fit
val_logs = self.evaluate(
File "/home/yogeesh/yogeesh/tf2/lib/python3.8/site-packages/keras/engine/training.py", line 1501, in evaluate
tmp_logs = self.test_function(iterator)
File "/home/yogeesh/yogeesh/tf2/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py", line 885, in __call__
result = self._call(*args, **kwds)
File "/home/yogeesh/yogeesh/tf2/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py", line 933, in _call
self._initialize(args, kwds, add_initializers_to=initializers)
File "/home/yogeesh/yogeesh/tf2/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py", line 759, in _initialize
self._stateful_fn._get_concrete_function_internal_garbage_collected( # pylint: disable=protected-access
File "/home/yogeesh/yogeesh/tf2/lib/python3.8/site-packages/tensorflow/python/eager/function.py", line 3066, in _get_concrete_function_internal_garbage_collected
graph_function, _ = self._maybe_define_function(args, kwargs)
File "/home/yogeesh/yogeesh/tf2/lib/python3.8/site-packages/tensorflow/python/eager/function.py", line 3463, in _maybe_define_function
graph_function = self._create_graph_function(args, kwargs)
File "/home/yogeesh/yogeesh/tf2/lib/python3.8/site-packages/tensorflow/python/eager/function.py", line 3298, in _create_graph_function
func_graph_module.func_graph_from_py_func(
File "/home/yogeesh/yogeesh/tf2/lib/python3.8/site-packages/tensorflow/python/framework/func_graph.py", line 1007, in func_graph_from_py_func
func_outputs = python_func(*func_args, **func_kwargs)
File "/home/yogeesh/yogeesh/tf2/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py", line 668, in wrapped_fn
out = weak_wrapped_fn().__wrapped__(*args, **kwds)
File "/home/yogeesh/yogeesh/tf2/lib/python3.8/site-packages/tensorflow/python/framework/func_graph.py", line 994, in wrapper
raise e.ag_error_metadata.to_exception(e)
TypeError: in user code
/home/yogeesh/yogeesh/tf2/lib/python3.8/site-packages/keras/engine/training.py:1330 test_function *
return step_function(self, iterator)
/home/yogeesh/yogeesh/object_detection/Yolov3_tf2/metrics/mAP.py:102 update_state *
box_objects = tf_postprocessing.post_process(predictions ,
/home/yogeesh/yogeesh/object_detection/Yolov3_tf2/postprocessing/tf_postprocessing.py:137 post_process *
all_gt = modify_locs(ground_truth , scale_anchors , gt = True)
/home/yogeesh/yogeesh/object_detection/Yolov3_tf2/postprocessing/tf_postprocessing.py:35 modify_locs *
modified_loc = pp_utils.modify_locs_util(localizations , this_scale_anchor , ground_truth = gt)
/home/yogeesh/yogeesh/object_detection/Yolov3_tf2/postprocessing/tf_utils.py:20 modify_locs_util *
num_classes = localizations.shape[4] - 5
TypeError: unsupported operand type(s) for -: 'NoneType' and 'int'
2021-10-21 18:33:00.783103: W tensorflow/core/kernels/data/generator_dataset_op.cc:107] Error occurred when finalizing GeneratorDataset iterator: Failed precondition: Python interpreter state is not initialized. The process may be terminated.
[[{{node PyFunc}}]]
This happens only while training , using tf.keras.model.fit function where it runs a overridden test_Step function in "evaluate" call.
this is the function where i am getting an error.
def modify_locs_util(localizations , anchors , img_shape = [416, 416] , ground_truth = False):
# localizations.shape : [batch_size , grid_size , grid_size , 3 , 7] (for this dataset)
# where grid_size can be 13,26,52 (Yolov3 model).
locs_shape = tf.shape(localizations)
grid_shape = locs_shape[1:3]
num_anchors = locs_shape[3]
num_classes = locs_shape[4] - 5
strides = [img_shape[0] // grid_shape[0], img_shape[1] // grid_shape[1]]
cell_grid = comman_utils.gen_cell_grid(grid_shape[0] , grid_shape[1] , num_anchors)
weird thing is , if i print the shape of localizations there result comes something as this:
(None, 13, 13, 3, 7)
(None, 26, 26, 3, 7)
(None, 52, 52, 3, 7)
(None, None, None, None, None)
as you can see, first 3 times the shape is fine , but i dont why is it calling again (it should call this fucntion only 3 times) and now it is referring the shape as all None's. Its almost like its doing a architechure check first to figure out shapes but even then static dims shouldnt be None.
CodePudding user response:
Maybe try the following code:
num_classes = tf.shape(tensor)[4] - 5.
which will be evaluated when the fit(*) method is called.