Failed precondition: Attempting to use uninitialized value yolo_layer_

[ar-ramchandra]

First of all, thank you for your amazing work! I have learned so very much in trying to implement this!

I'm sorry if I'm doing something wrong, I'm very new to this field.

Initially, I was getting an error with tf.float() in YOLO.py

After a variety of searches, adding the following line just after the imports fixed it:

import tensorflow.compat.v1 as tf
tf.disable_v2_behavior()

Now, I am getting an error in train.py

---------------------------------------------------------------------------
FailedPreconditionError                   Traceback (most recent call last)
~\Documents\GitStuff\cv capstone\CapstonecvYOLO REAL\keras-yolo3\train.py in <module>
    289 
    290     args = argparser.parse_args()
--> 291     _main_(args)

~\Documents\GitStuff\cv capstone\CapstonecvYOLO REAL\keras-yolo3\train.py in _main_(args)
    259     callbacks = create_callbacks(config['train']['saved_weights_name'], config['train']['tensorboard_dir'], infer_model)
    260 
--> 261     train_model.fit_generator(
    262         generator        = train_generator,
    263         steps_per_epoch  = len(train_generator) * config['train']['train_times'],

c:\users\offic\venv\lib\site-packages\keras\legacy\interfaces.py in wrapper(*args, **kwargs)
     89                 warnings.warn('Update your `' + object_name + '` call to the ' +
     90                               'Keras 2 API: ' + signature, stacklevel=2)
---> 91             return func(*args, **kwargs)
     92         wrapper._original_function = func
     93         return wrapper

c:\users\offic\venv\lib\site-packages\keras\engine\training.py in fit_generator(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, validation_freq, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
   1716         ```
   1717         """
-> 1718         return training_generator.fit_generator(
   1719             self, generator,
   1720             steps_per_epoch=steps_per_epoch,

c:\users\offic\venv\lib\site-packages\keras\engine\training_generator.py in fit_generator(model, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, validation_freq, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
    215                 callbacks.on_batch_begin(batch_index, batch_logs)
    216 
--> 217                 outs = model.train_on_batch(x, y,
    218                                             sample_weight=sample_weight,
    219                                             class_weight=class_weight,

c:\users\offic\venv\lib\site-packages\keras\engine\training.py in train_on_batch(self, x, y, sample_weight, class_weight, reset_metrics)
   1512             ins = x + y + sample_weights
   1513         self._make_train_function()
-> 1514         outputs = self.train_function(ins)
   1515 
   1516         if reset_metrics:

c:\users\offic\venv\lib\site-packages\tensorflow\python\keras\backend.py in __call__(self, inputs)
   3629       self._make_callable(feed_arrays, feed_symbols, symbol_vals, session)
   3630 
-> 3631     fetched = self._callable_fn(*array_vals,
   3632                                 run_metadata=self.run_metadata)
   3633     self._call_fetch_callbacks(fetched[-len(self._fetches):])

c:\users\offic\venv\lib\site-packages\tensorflow\python\client\session.py in __call__(self, *args, **kwargs)
   1468       try:
   1469         run_metadata_ptr = tf_session.TF_NewBuffer() if run_metadata else None
-> 1470         ret = tf_session.TF_SessionRunCallable(self._session._session,
   1471                                                self._handle, args,
   1472                                                run_metadata_ptr)

FailedPreconditionError: 2 root error(s) found.
  (0) Failed precondition: Attempting to use uninitialized value yolo_layer_2/Variable
     [[{{node yolo_layer_2/AssignAdd}}]]
     [[loss/Identity_2/_5921]]
  (1) Failed precondition: Attempting to use uninitialized value yolo_layer_2/Variable
     [[{{node yolo_layer_2/AssignAdd}}]]
0 successful operations.
0 derived errors ignored.

I have tried to change the behavior to v1, but in vain.

From what I'm able to make out, it is an orror in about the last line,

if __name__ == '__main__':
    argparser = argparse.ArgumentParser(description='train and evaluate YOLO_v3 model on any dataset')
    argparser.add_argument('-c', '--conf', help='path to configuration file')   

    args = argparser.parse_args()
    _main_(args)

Any guidance is appreciated

[leonilpark]

I had same error. Did you solved?