Getting a ValueError on building and training 3D Keras U-NET Question: On training my model which I have built for 3D Unet using keras I’m getting ValueError: Input 0 of layer conv3d_46 is incompatible with the layer: expected ndim=5, found ndim=6. Full shape received: [None, 2, 256, 256, 120, 4]. The size of shape of …
Tensorflow 2 throwing ValueError: as_list() is not defined on an unknown TensorShape Question: I’m trying to train a Unet model in Tensorflow 2.0 which takes as input an image and a segmentation mask, but I’m getting a ValueError : as_list() is not defined on an unknown TensorShape. The stack trace shows the problem occurs during …
Some questions about the plotted results of a Unet Question: I’m studying this example about Unet. It is about binary segmentation, and I have some questions about the code: what is the meaning of doing: #preprocess the mask mask[mask >= 2] = 0 mask[mask != 0 ] = 1 The dataset contains “mask” pictures composed …
Strange results while training with keras Question: I am trying to train a unet model on braTS18 dataset (medical data with nifiti images) using keras with tensorflow. However I am getting very strange results: as you can see, accuracy starts with 96% and gets to 99% at the third epoch. Also the validation loss doesn’t …
expected conv2d to have 4 dimensions, but got array with shape Question: I am trying to perform a convolutional network on some medical images that have nifti format, using Keras. When I try to fit the model like this: model.fit(X_train, Y_train, batch_size=batch_size, epochs = n_epoch, validation_data=(X_test, Y_test)) I get this error: expected conv2d_171 to have …
