Phil 5.12.20


#COVID Aseel’s docs don’t seem to be in the proper unicode? I tried downloading a version of the Quran from here, and that seems to be working. Hmmm. Trying to train on the Quran with these args:

--output_dir=output --model_type=gpt2 --model_name_or_path=gpt2 --per_gpu_train_batch_size=1 --do_train --train_data_file=..\input\quran-simple.txt

GPT-2 Agents

  • Added basic moves for all the pieces. Still need to handle hints
    Evaluating move [d4 Nf6]
     Fred Van der Vliet moves white pawn from d2 to d4.
     Loek Van Wely moves black knight from g8 to f6.
    Evaluating move [c4 g6]
     Fred Van der Vliet moves white pawn from c2 to c4.
     Loek Van Wely moves black pawn from g7 to g6.
    Evaluating move [g3 Bg7]
     Fred Van der Vliet moves white pawn from g2 to g3.
     Loek Van Wely moves black bishop from f8 to g7.
    Evaluating move [Bg2 O-O]
     Fred Van der Vliet moves white bishop from f1 to g2.
     Loek Van Wely kingside castles.


  • Working on NoiseGAN
    • Seems to be training without blowing up….
    • It ran, but the results are weird.



    • As you can see, the fake data seems to have learned the noise well, but the scale is wrong.
    • It does seem to be able to learn about the scale though:


    • Adding dropout seems to help:


    • The discriminator so far:
      self.d_model = Sequential()
      self.d_model.add(Dense(64, activation='relu', kernel_initializer='he_uniform', input_dim=self.vector_size))
      self.d_model.add(Dense(25, activation='relu', kernel_initializer='he_uniform', input_dim=self.vector_size))
      self.d_model.add(Dense(1, activation='sigmoid'))
      # compile model
      self.d_model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])