Open JohnFarl opened 7 years ago
conv2d_layer_one = tf.contrib.layers.convolution2d(
float_image_batch,
#num_output_channels=32, # The number of filters to generate
num_outputs=32,
kernel_size=(5,5), # It's only the filter height and width.
activation_fn=tf.nn.relu,
#weight_init=tf.random_normal,
weights_initializer=tf.random_normal_initializer(),
stride=(2, 2),
trainable=True)
my updated code seems OK.
The version of tf used in book is 0.8.0 as mentioned in requirements, my version is latest 0.12.0.
I have already fixed some errors by myself however the way how parameters are passed in this method seems wrong and I get the error got an unexpected keyword argument
layer_one = tf.contrib.layers.convolution2d( float_image_batch, num_output_channels=32,
kernel_size=(5,5),
activation_fn=tf.nn.relu, weight_init=tf.random_normal, stride=(2, 2), trainable=True)
More details on my Stackoverflow question http://stackoverflow.com/questions/41539658/tensorflow-error-when-i-try-to-use-tf-contrib-layers-convolution2d/41540092#41540092