Cant read Inputfiles

[michaelwachter]

I've set the default Path, in the main.py script, to my Dataset Folder:

parser.add_argument("--train_data", default="./dataset/img", help="Directory for training images")

My folder sctruture inside the project looks like this:

• dataset
  • img
    • images
    • masks

When i call the main.py script without arguments, i get the error: TypeError: Input 'filename' of 'ReadFile' Op has type float32 that does not match expected type of string.

[HasnainRaz]

It seems your file_paths list somehow has floats instead of filepath strings. Can you share the full error message?
Also, what format are your images?

[michaelwachter]

`
(bachelor) c:\Users\MiHi\GitHub\FC-DenseNet2ClassificationNN_tensorflow\FC-DenseNet-TensorFlow>python main.py
WARNING: Logging before flag parsing goes to stderr.
W0902 11:21:51.432162 15556 deprecation_wrapper.py:119] From c:\Users\MiHi\GitHub\FC-DenseNet2ClassificationNN_tensorflow\FC-DenseNet-TensorFlow\utility.py:5: The name tf.read_file is deprecated. Please use tf.io.read_file instead.

Traceback (most recent call last):
File "C:\ProgramData\Anaconda3\envs\bachelor\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 527, in _apply_op_helper
preferred_dtype=default_dtype)
File "C:\ProgramData\Anaconda3\envs\bachelor\lib\site-packages\tensorflow\python\framework\ops.py", line 1224, in internal_convert_to_tensor
ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
File "C:\ProgramData\Anaconda3\envs\bachelor\lib\site-packages\tensorflow\python\framework\ops.py", line 1018, in _TensorTensorConversionFunction
(dtype.name, t.dtype.name, str(t)))
ValueError: Tensor conversion requested dtype string for Tensor with dtype float32: 'Tensor("args_0:0", shape=(), dtype=float32)'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "main.py", line 44, in
main()
File "main.py", line 38, in main
FLAGS.batch_size, FLAGS.epochs, FLAGS.learning_rate)
File "c:\Users\MiHi\GitHub\FC-DenseNet2ClassificationNN_tensorflow\FC-DenseNet-TensorFlow\model.py", line 281, in train
train_image_paths, train_mask_paths, batch_size)
File "c:\Users\MiHi\GitHub\FC-DenseNet2ClassificationNN_tensorflow\FC-DenseNet-TensorFlow\utility.py", line 89, in data_batch
num_parallel_calls=num_threads).prefetch(30)
File "C:\ProgramData\Anaconda3\envs\bachelor\lib\site-packages\tensorflow\python\data\ops\dataset_ops.py", line 1776, in map
self, map_func, num_parallel_calls, preserve_cardinality=False))
File "C:\ProgramData\Anaconda3\envs\bachelor\lib\site-packages\tensorflow\python\data\ops\dataset_ops.py", line 3228, in init
use_legacy_function=use_legacy_function)
File "C:\ProgramData\Anaconda3\envs\bachelor\lib\site-packages\tensorflow\python\data\ops\dataset_ops.py", line 2555, in init
self._function = wrapper_fn._get_concrete_function_internal()
File "C:\ProgramData\Anaconda3\envs\bachelor\lib\site-packages\tensorflow\python\eager\function.py", line 1355, in _get_concrete_function_internal
*args, **kwargs)
File "C:\ProgramData\Anaconda3\envs\bachelor\lib\site-packages\tensorflow\python\eager\function.py", line 1349, in _get_concrete_function_internal_garbage_collected
graph_function, _, _ = self._maybe_define_function(args, kwargs)
File "C:\ProgramData\Anaconda3\envs\bachelor\lib\site-packages\tensorflow\python\eager\function.py", line 1652, in _maybe_define_function
graph_function = self._create_graph_function(args, kwargs)
File "C:\ProgramData\Anaconda3\envs\bachelor\lib\site-packages\tensorflow\python\eager\function.py", line 1545, in _create_graph_function
capture_by_value=self._capture_by_value),
File "C:\ProgramData\Anaconda3\envs\bachelor\lib\site-packages\tensorflow\python\framework\func_graph.py", line 715, in func_graph_from_py_func
func_outputs = python_func(*func_args, **func_kwargs)
File "C:\ProgramData\Anaconda3\envs\bachelor\lib\site-packages\tensorflow\python\data\ops\dataset_ops.py", line 2549, in wrapper_fn
ret = _wrapper_helper(*args)
File "C:\ProgramData\Anaconda3\envs\bachelor\lib\site-packages\tensorflow\python\data\ops\dataset_ops.py", line 2489, in _wrapper_helper
ret = func(*nested_args)
File "c:\Users\MiHi\GitHub\FC-DenseNet2ClassificationNN_tensorflow\FC-DenseNet-TensorFlow\utility.py", line 5, in _parse_data_infer
image_content = tf.read_file(image_paths)
File "C:\ProgramData\Anaconda3\envs\bachelor\lib\site-packages\tensorflow\python\ops\gen_io_ops.py", line 626, in read_file
"ReadFile", filename=filename, name=name)
File "C:\ProgramData\Anaconda3\envs\bachelor\lib\site-packages\ten`

My Images are in JPG format, i did use the JPG decoder Function from Tensorflow though.

[michaelwachter]

Ok, so i converted the JPG's to PNG, now it runs fine. But i get a OOM Error while running it. I'll open a new issue and close this one.

[HasnainRaz]

You could also change the read png function to the read jpeg function in utility.py

OOM errors are common with Tiramisu, since it's memory usage grows quadratically. You can either reduce the batch size, your image size, or the number of layers in the model to resolve them.