Pix2Pix | Real-time pix2pix implementation with Unity | Machine Learning library

The reason behind the error turned out to be a type error. When passing the size to AdaptiveAvgPool3d I was getting the values for the size through division. Although the remainder was 0, division by default saves values as float in python. This meant the tuple being passed as the output_size was in fact a tuple of float which the _list_with_default turns into a list but likely doesn't if the tuple was made of int. Simply using int(..) for each dimension passed to AdaptiveAvgPool3d was the solution.

The (API) Key is shown in both screenshots and begins AIza.

You should delete the API Key that you included in the screenshots and create another

Please be very careful about sharing data like this because it is a so-called bearer token which means that anyone (the bearer) who has it can use it (although you are trying to enforce API and IP restrictions which is good practice).

It's possible someone could infer the entire key from both screenshots that you've included. Deleting it will void it. Please create another and don't share it with anyone that doesn't require it.

I'm unfamiliar with pix2pix but all API keys should be treated as secret(s). Google only provides one value for API keys so there's no "API Key" and "Secret API Key" only "API Key" that should always be treated as secrets.

As it is said in the Keras documentation the solution is to "provide the same seed and keyword arguments to the fit and flow methods - seed = 1".

Just add to the flow_from_directory method seed = 1.

Check out the link for more information here

I think the problem here is some layer the bias=None but in testing the model required this, you should check the code for details.

After I check your config in train and test, the norm is different. For the code in GitHub, the norm difference may set the bias term is True or False.

torch.cat's first argument is expected to be a sequence of tensors rather than a single tensor. So you pass in like:

After digging in the code for a few hours I discovered how zi2zi utilizes the pix2pix methodology. If I am correct, the data is split into two parts: real_A and real_B. real_A is fed into the generator along with the class label embedding_ids and produces fake_b. The discriminator then aims at discriminating a fake_b and real_b with real_a as the target image.

Conclusively, this seemingly works like an autoencoder, but with the discriminator as an evaluation metric. In concept, there isn't much that is a difference between pix2pix and other GANs with encoders.

When using fp16, you need to have the final layer give fp32 output.

Change

From here:

You can try: