Tensorflow InvalidArgumentError（请参阅上面的回溯）：平面索引不会索引到参数中

Question

I'm using tensorflow to build a recommendationg system using collaborative filtering algorithm.

Due to memory usage I have to use sparse matrices.

#Arbitrary number of items are rated by arbitrary number of users
ratings = tf.sparse_placeholder(tf.float32, shape=[None, None])
ratings = tf.sparse_reorder(ratings)

With my feed_dict, ratings.dense_shape == (45776, 60184)

pred = tf.matmul(items_features, user_preferences, name='Prediction') + global_mean

I have hardcoded so pred.shape == (45776, 60184)

So how comes when I try to collect predictions to later calculate the cost

pred_values = tf.gather_nd(pred, ratings.indices)

I get error
InvalidArgumentError (see above for traceback): flat indices[2714679, :] = [48375, 2227] does not index into param (shape: [45776,60184]).
?

Answer 1

It turns out I did mess up with dimensions. I fed indices in the opposite order than I thought, ie, for shape (60184,45776) instead of needed (45776,60184) .

Having an error telling that my flat indices[2714679, :] are indexing [48375, 2227] - shape that does not appear - didn't help.