danielegrattarola / deep-q-atari Goto Github PK

hi.
im trying to port in python3. Ive changed all print to print().
and
from keras.models import Sequential
from keras.layers import Conv2D, Flatten, Dense
to
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv2D, Flatten, Dense
But got a error -
tensorflow.python.framework.errors_impl.UnimplementedError: The Conv2D op currently only supports the NHWC tensor format on the CPU. The op was given the format: NCHW
[[{{node conv2d/Conv2D}}]]
Quitting...
As i know it should be changed in DQNetwork.py model formation -
from
self.model.add(Conv2D(32, 8, strides=(4, 4),
padding='valid',
activation='relu',
input_shape=input_shape,
data_format='channels_first'))
to
self.model.add(Conv2D(32, 8, strides=(4, 4),
padding='valid',
activation='relu',
input_shape=input_shape,
data_format='channels_last'))
But this time new error appears:
ValueError: Negative dimension size caused by subtracting 8 from 4 for 'conv2d/Conv2D' (op: 'Conv2D') with input shapes: [?,4,110,84], [8,8,84,32].

How to solve it ? Help a bit.

In the documentation, you mentioned ("both files will be saved when the script quits or is killed with ctrl+c")
But ctrl+c does not invoke the exit handler.
Is there any way around it or am I doing something wrong