resingm/field-boundary-delineation

Code & trained network files of FCNs to delineate agricultural field boundaries

field-boundary-delineation's Issues

Image input size for inference

There is the following description in network-prediction.ipynb.
"Takes an input image, patches it into smaller patches and feeds the FCN with each of the patches. The output samples are patches of the predicted classification. These patches are combined into one large image, that can be compared with the classified image of the corresponding input data."
However, I don't see any such process. I can't understand why I can input an image of a different size than during training and not get an error. Could you please explain?

Pre-trained weights

Hi, Thanks for sharing your work. Do you have any plans for sharing pre-trained weights? Thank you.

Input 0 is incompatible with layer model_6

Hello,i am working on your notebook and i have this bug :

ValueError Traceback (most recent call last)

in ()
98 # Train the network
99 y_train = to_categorical_4d(y_train, NUMBER_CLASSES)
--> 100 history = train(model, x_train, y_train, NUMBER_EPOCHS, batch_size=BATCH_SIZE, validation_split=VALIDATION_SPLIT).history
101
102

10 frames

/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/func_graph.py in wrapper(*args, **kwargs)
984 except Exception as e: # pylint:disable=broad-except
985 if hasattr(e, "ag_error_metadata"):
--> 986 raise e.ag_error_metadata.to_exception(e)
987 else:
988 raise

ValueError: in user code:

/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:855 train_function  *
    return step_function(self, iterator)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:845 step_function  **
    outputs = model.distribute_strategy.run(run_step, args=(data,))
/usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:1285 run
    return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:2833 call_for_each_replica
    return self._call_for_each_replica(fn, args, kwargs)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:3608 _call_for_each_replica
    return fn(*args, **kwargs)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:838 run_step  **
    outputs = model.train_step(data)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:795 train_step
    y_pred = self(x, training=True)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py:1013 __call__
    input_spec.assert_input_compatibility(self.input_spec, inputs, self.name)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/input_spec.py:270 assert_input_compatibility
    ', found shape=' + display_shape(x.shape))

ValueError: Input 0 is incompatible with layer model_6: expected shape=(None, 200, 200, 4), found shape=(None, 200, 200, 3)

I did change the code in the function visualize_data() from data = arr[ :, :,0:-1] to data = arr[ :, 0:-1] because it didn't work otherwise.

Thank you in advance