lfw | Helper app for Local by Flywheel | Command Line Interface library

Your logic seems badly broken. You iterate through all the files in the directory, passing each one to copyFile. But inside that function, you again try to iterate through each file in the "directory" passed to the function: except that you're not passing only directories to the function, you're passing each file found in the original directory.

It's not clear what you are trying to do, but I think you need to remove one of those calls to listdir and the associated loop.

One obvious problem is indentation of your return statement:

Ok so the solution was

imgplot = plt.imshow(out/255)

Try training with a smaller learning rate than the default one (for instance, 1e-4). The random weights from the classification layer can bring about large gradient updates. These will cause large weight updates in the lower layers and basically destroy the pretrained weights in the convolutional base.

In addition, you can use the ReduceLROnPlateau callback to further decrease the learning rate when validation accuracy stops increasing.

Another strategy to avoid large disruptive gradient updates is to freeze the weights in the convolutional base first, pre-train the classification layers, then finetune the entire stack with a small learning rate. This approach is explained in detail in the Keras blogpost on transfer learning: https://blog.keras.io/building-powerful-image-classification-models-using-very-little-data.html

Let's say you have on your desktop a root folder called test containing my_script.py and a subfolder called input where all the ppm files are stored.

You can use the following code to save a png copy of every ppm image.

my_script.py

CDATA just means "Treat this content at plain text" so it ignores the special meaning of characters which would normally have special meaning in XML (like < meaning "start of tag").

The value of the description is a fragment of HTML. If you want to extract specific content from it, then run it through an HTML parser.

Pytorch builds a computational graph each time you propagate through your model. This graph is normally retained until the output variable G_loss is out of scope, e.g. when a new iteration through the loop starts.

However, you append this loss to a list. Hence, the variable is still known to python and the graph not freed. You can use .detach() to detach the variable from the current graph (which is better than .clone() which I proposed before as it will also copy the data of the tensor).

As a little side node: In your train() function, you return D_loss,G_loss in the for loop, not after it; so you always only use the first batch.

Please notice that you want to feed ~ 19 * 40 < 800 example in order to train 16,867,347 parameters. So this is basically 2e6 paramters per example. This simply cannot work properly. Try to delete all FCN layers (Dense layers at the top) and put smaller Dense with e.g. ~ 50 neurons each. In my opinion this should help you in improving accuracy and speeding up training.

Did your print (dst_dir) print? I ran your code but that inner print did not run.

I'm not saying it's a better approach, but this worked for me...obviously you'd need to alter for your situation: