Hello, I am running on Colab using tf 2.0 and keras 2.3.1 and training using another dataset in .nii format.

Unfortunately, the algorithm outputs an error in the first epoch:

Epoch 1/20 2020-01-24 16:05:30.895469: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2020-01-24 16:05:36.929059: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10.0 Traceback (most recent call last): File "train.py", line 285, in <module> n_imgs=15*10**4, batch_size=8) File "train.py", line 275, in keras_fit_generator use_multiprocessing=True) File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/training.py", line 1297, in fit_generator steps_name='steps_per_epoch') File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/training_generator.py", line 323, in model_iteration steps_name='validation_steps') File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/training_generator.py", line 265, in model_iteration batch_outs = batch_function(*batch_data) File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/training.py", line 1070, in test_on_batch reset_metrics=reset_metrics) File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/training_v2_utils.py", line 327, in test_on_batch output_loss_metrics=model._output_loss_metrics) File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/training_eager.py", line 354, in test_on_batch output_loss_metrics=output_loss_metrics)) File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/training_eager.py", line 166, in _model_loss per_sample_losses = loss_fn.call(targets[i], outs[i]) File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/losses.py", line 221, in call return self.fn(y_true, y_pred, **self._fn_kwargs) File "/content/drive/My Drive/promise12_segmentation2/codes/metrics.py", line 18, in dice_coef_loss return -dice_coef(y_true, y_pred) File "/content/drive/My Drive/promise12_segmentation2/codes/metrics.py", line 12, in dice_coef intersection = K.sum(y_true_f * y_pred_f) File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/math_ops.py", line 899, in binary_op_wrapper return func(x, y, name=name) File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/math_ops.py", line 1206, in _mul_dispatch return gen_math_ops.mul(x, y, name=name) File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/gen_math_ops.py", line 6698, in mul _six.raise_from(_core._status_to_exception(e.code, message), None) File "<string>", line 3, in raise_from tensorflow.python.framework.errors_impl.InvalidArgumentError: cannot compute Mul as input #1(zero-based) was expected to be a int64 tensor but is a float tensor [Op:Mul] name: loss/conv2d_22_loss/mul/

Any ideas how to solve this?

Thanks in advance!

Hi everyone
I trying to run this code, the training it's done but when i tried to do the test, i did not find the folder test_samples, i dont know if i need to transfer the files in test data to .png format or if there a missed folder for this repository.

Thank for your reply

Thanks for sharing the code. I am sorry to Sorry to bother you.I want use this model to do segement in my own dataset. But I do not know how to label my own pictures which are .png or .jpg to use this model？

Sorry to bother you,but I notice that you use python2.7,now I want to transform it to python3.5,.But in py3.5,filter produce a generator format, not like py2.7(list format),I do not know how to transform it so I delete the line48 and 95(fileList.sort() can not work).
but problem still happened:
Traceback (most recent call last):
File "C:/Users/lz666/PycharmProjects/promise12_segmentation/codes/train.py", line 233, in
n_imgs=15*10**4, batch_size=32)
File "C:/Users/lz666/PycharmProjects/promise12_segmentation/codes/train.py", line 167, in keras_fit_generator
data_to_array(img_rows, img_cols)
File "C:/Users/lz666/PycharmProjects/promise12_segmentation/codes/train.py", line 72, in data_to_array
images = np.concatenate( images , axis=0 ).reshape(-1, img_rows, img_cols, 1)
ValueError: need at least one array to concatenate
I do not think that is the problem with py2.7 and 3.5,I use CPU only,can you fix it or transform it to py3.5?

I ran the train.py file and have been stuck on `Epoch 1/20 for over an hour. I'm using a Google Cloud Platform VM instance to run the file. Any thoughts?

Hi,

Thanks for this great tutorial. I modify this to satisfy python3, however, when I run this codes, this error shows as below, could you please give me some advice to fix this problem?

Thank you very much!

Input arrays should have the same number of samples as target arrays. Found 950 input samples and 910 target samples.

Total params: 53,249,754
Trainable params: 53,237,530
Non-trainable params: 12,224
_________________________________________________________________________________________________
Traceback (most recent call last):
  File "train.py", line 237, in <module>
    n_imgs=15*10**4, batch_size=32)
  File "train.py", line 227, in keras_fit_generator
    use_multiprocessing=True)
  File "/opt/Anaconda3/lib/python3.6/site-packages/keras/legacy/interfaces.py", line 91, in wapper
    return func(*args, **kwargs)
  File "/opt/Anaconda3/lib/python3.6/site-packages/keras/engine/training.py", line 2116, in ft_generator
    val_x, val_y, val_sample_weight)
  File "/opt/Anaconda3/lib/python3.6/site-packages/keras/engine/training.py", line 1438, in _tandardize_user_data
    _check_array_lengths(x, y, sample_weights)
  File "/opt/Anaconda3/lib/python3.6/site-packages/keras/engine/training.py", line 217, in _ceck_array_lengths
    'and ' + str(list(set_y)[0]) + ' target samples.')
ValueError: Input arrays should have the same number of samples as target arrays. Found 950 iput samples and 910 target samples.