image_generator | GANのpytorch実装 | Machine Learning library

Your bce_logdice_loss loss looks fine to me.

Do you know where 2560000 could come from?

Note that the shape of y_pred and y_true is None at first because Tensorflow is creating the computation graph without knowing the batch_size. Once created only, the model will use shapes with batch_size as first dimension instead of None.

I am quite certain that it has something to do with how you load the data, and more specifically the x, y = image.next() part. If you are able to split the data from ./util/untitled folder to separate folders having training and validation data respectively, you could use the same kind on pipeline as in the examples section on Tensorflow page:

in your case :

It could be that the decay_rate argument in tf.keras.optimizers.schedules.ExponentialDecay is decaying your learning rate quicker than you think it is, effectively making your learning rate zero.

Use class_mode="input" at the flow_from_directory so returned Y will be same as X

https://github.com/tensorflow/tensorflow/blob/v2.4.1/tensorflow/python/keras/preprocessing/image.py#L867-L958

class_mode: One of "categorical", "binary", "sparse", "input", or None. Default: "categorical". Determines the type of label arrays that are returned: - "categorical" will be 2D one-hot encoded labels, - "binary" will be 1D binary labels, "sparse" will be 1D integer labels, - "input" will be images identical to input images (mainly used to work with autoencoders). - If None, no labels are returned (the generator will only yield batches of image data, which is useful to use with model.predict()). Please note that in case of class_mode None, the data still needs to reside in a subdirectory of directory for it to work correctly.

Code should end up like:

This is a bug in Keras, reported here: https://github.com/keras-team/keras/issues/13839

Basically, when class_mode == "raw" and the labels are numpy arrays, flow_from_dataframe generates batches for the labels in the shape of an array of numpy arrays rather than a 2D array, which then makes the fit method fail.

As a workaround until it's fixed, add these lines after you create your generators

I believe you need to do two things. One resize the images you wish to predict, then rescale the images as you did for the training images. I also recommend that you set the validation_freq=1 so that you can set how the validation loss and accuracy are trending. This allows you to see how your model is performing relative to over fitting etc. You can detect if your model is over fitting if the training loss continues to declined but in later epochs your validation loss begins to increase. If you see over fitting add a Dropout layer after your dense 512 node dense layer. Documentation is here. Prediction accuracy should be close to the validation accuracy for the last epoch. I also recommend you consider using the keras callback ModelCheckpoint. Documentation is here. Set it up to monitor validation loss and save the model with the lowest validation loss. Then load the saved model to do predictions. Finally I find it effective to use an adjustable learning rate. The keras callback ReduceLROnPlateau makes this easy to do. Documentation is here. Set it up to monitor validation loss. The callback will automatically reduce the learning rate by a factor (parameter factor) if after (parameter patience) patience number of epochs the validation loss fails to decrease. I use factor=.5 and patience=1. This allows you to use a larger learning rate initially and have it decrease as needed so convergence will be faster. One more thing in your val_data_gen set shuffle=False so the validation images are processed in the same order each time.

The error says it directly: you give [1,3] which is a list, where it expects either a number or a slice.

Maybe you meant [1:3] ?

You seem to give the [1,3] there so maybe should change:

The generator produces tuples as an output (image, label) that is where the dimension 2 comes from. Then 32 is the batch size 64, 64 is the image size and 3 is the number of channels