Tensorflow Incompatable Shapes Error in Tutorial -
i've been trying create convolutional network tensorflow tutorial , i've been having trouble. reason, i'm getting errors size of y_conv 4x larger size of y_, , have no idea why. found this question , appears different problem mine, though looks similar. to clear, batch size in below code 50, error it's coming is tensorflow.python.framework.errors.invalidargumenterror: incompatible shapes: [200] vs. [50] and when change batch size 10, get tensorflow.python.framework.errors.invalidargumenterror: incompatible shapes: [40] vs. [10] so it's related batch size somehow, can't figure out. can tell me what's wrong code? it's pretty straight tutorial linked above. from tensorflow.examples.tutorials.mnist import input_data mnist = input_data.read_data_sets('mnist_data', one_hot=true) import tensorflow tf sess = tf.interactivesession() def weight_variable(shape): initial = tf.truncated_normal(shape, stddev=0.1) return tf.var