353xiong

after： python -m basic.cli --mode train --noload --debug ValueError: Dimensions must be equal, but are 900 and 300 for 'model_0/prepro/u1/fw/fw/while/basic_lstm_cell/MatMul_6' (op: 'MatMul') with input shapes: [?,900], [300,400]. why?

in this function ？ def create_environment(env_name='', stacked=False, representation='extracted', rewards='scoring', write_goal_dumps=False, write_full_episode_dumps=False, render=False, write_video=False, dump_frequency=1, logdir='', extra_players=None, number_of_left_players_agent_controls=1, number_of_right_players_agent_controls=0, channel_dimensions=( observation_preprocessing.SMM_WIDTH, observation_preprocessing.SMM_HEIGHT), other_config_options={}): """Creates a Google Research Football environment.

Traceback (most recent call last): File "/home/xiong/Desktop/dbn_tf/test.py", line 21, in mnist = input_data.read_data_sets("MNIST_data/", one_hot=True) File "/home/xiong/Desktop/dbn_tf/input_data.py", line 154, in read_data_sets train_images = extract_images(local_file) File "/home/xiong/Desktop/dbn_tf/input_data.py", line 43, in extract_images buf...

how to use the function "Autopilot"?

1

Where is the code related to "autopilot" ?

TypeError: unsupported operand type(s) for *: 'IndexedSlices' and 'float'

2

e_w = gradients[i] * self.rho / (grad_norm + 1e-12) TypeError: unsupported operand type(s) for *: 'IndexedSlices' and 'float' How to deal with it?

Can you provide the training configuration file for training vqvae?