Training New Data
chnanc001 opened this issue · 5 comments
Would it be possible to train using a completely new set of data? Why is it necessary to download a pre-trained model for training?
Yes, you can train a new set of data. The pre-trained model is optional.
thanks for the response,
would you be able to help me determine what the cause for the following error is?
Traceback (most recent call last):
File "C:\Users\Administrator\Desktop\LIP_JPPNet-master\train_JPPNet-s2.py", line 333, in
main()
File "C:\Users\Administrator\Desktop\LIP_JPPNet-master\train_JPPNet-s2.py", line 287, in main
summary, loss_value, _ = sess.run([loss_summary, reduced_loss, train_op], feed_dict=feed_dict)
File "C:\ProgramData\Miniconda3\lib\site-packages\tensorflow\python\client\session.py", line 900, in run
run_metadata_ptr)
File "C:\ProgramData\Miniconda3\lib\site-packages\tensorflow\python\client\session.py", line 1135, in _run
feed_dict_tensor, options, run_metadata)
File "C:\ProgramData\Miniconda3\lib\site-packages\tensorflow\python\client\session.py", line 1316, in _do_run
run_metadata)
File "C:\ProgramData\Miniconda3\lib\site-packages\tensorflow\python\client\session.py", line 1335, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.OutOfRangeError: FIFOQueue '_1_create_inputs/batch/fifo_queue' is closed and has insufficient elements (requested 1, current size 0)
[[Node: create_inputs/batch = QueueDequeueManyV2[component_types=[DT_FLOAT, DT_UINT8, DT_FLOAT], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/device:CPU:0"](create_inputs/batch/fifo_queue, Tower_0/gradients/Tower_0/Mean_7_grad/Maximum)]]
Caused by op 'create_inputs/batch', defined at:
File "C:\Program Files (x86)\pyzo\source\pyzo\pyzokernel\start.py", line 151, in
pyzo.run()
File "C:\Program Files (x86)\pyzo\source\pyzo\pyzokernel\interpreter.py", line 222, in run
self.guiApp.run(self.process_commands, self.sleeptime)
File "C:\Program Files (x86)\pyzo\source\pyzo\pyzokernel\guiintegration.py", line 424, in run
self.QtGui.real_QApplication.exec()
File "C:\Program Files (x86)\pyzo\source\pyzo\pyzokernel\interpreter.py", line 568, in process_commands
self._process_commands()
File "C:\Program Files (x86)\pyzo\source\pyzo\pyzokernel\interpreter.py", line 596, in _process_commands
self.runfile(tmp)
File "C:\Program Files (x86)\pyzo\source\pyzo\pyzokernel\interpreter.py", line 872, in runfile
self.execcode(code)
File "C:\Program Files (x86)\pyzo\source\pyzo\pyzokernel\interpreter.py", line 935, in execcode
exec(code, self.locals)
File "C:\Users\Administrator\Desktop\LIP_JPPNet-master\train_JPPNet-s2.py", line 333, in
main()
File "C:\Users\Administrator\Desktop\LIP_JPPNet-master\train_JPPNet-s2.py", line 47, in main
image_batch, label_batch, heatmap_batch = reader.dequeue(BATCH_SIZE)
File "C:\Users\Administrator\Desktop\LIP_JPPNet-master\utils\lip_reader.py", line 271, in dequeue
image_batch, label_batch, heatmap_batch = tf.train.batch([self.image, self.label, self.heatmap], num_elements)
File "C:\ProgramData\Miniconda3\lib\site-packages\tensorflow\python\training\input.py", line 988, in batch
name=name)
File "C:\ProgramData\Miniconda3\lib\site-packages\tensorflow\python\training\input.py", line 762, in _batch
dequeued = queue.dequeue_many(batch_size, name=name)
File "C:\ProgramData\Miniconda3\lib\site-packages\tensorflow\python\ops\data_flow_ops.py", line 483, in dequeue_many
self._queue_ref, n=n, component_types=self._dtypes, name=name)
File "C:\ProgramData\Miniconda3\lib\site-packages\tensorflow\python\ops\gen_data_flow_ops.py", line 3799, in queue_dequeue_many_v2
component_types=component_types, timeout_ms=timeout_ms, name=name)
File "C:\ProgramData\Miniconda3\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "C:\ProgramData\Miniconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 3414, in create_op
op_def=op_def)
File "C:\ProgramData\Miniconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 1740, in init
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access
OutOfRangeError (see above for traceback): FIFOQueue '_1_create_inputs/batch/fifo_queue' is closed and has insufficient elements (requested 1, current size 0)
[[Node: create_inputs/batch = QueueDequeueManyV2[component_types=[DT_FLOAT, DT_UINT8, DT_FLOAT], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/device:CPU:0"](create_inputs/batch/fifo_queue, Tower_0/gradients/Tower_0/Mean_7_grad/Maximum)]]
Hi，have you solve the problem？I have the same problem
Thanks！
Hi, you need to create heatmaps from landmarks using dataset/lip/create_heatmap.py. This resolved the error for me.
Hi I am working on person reidentification problem and for that I am trying to create heatmap on market 1501 dataset. Can anybody please guide me how can I do that?