Hi, thanks for sharing the code. It helps a lot for my research.
BTW, I think there's a typo in the model definition. In line 472 of hourglasstiny.py
sum[i] = tf.addn([out[i], sum[i-1], ll[0]], name= 'merge')
I think ll[0] should be fixed to ll[i]. This might be critical for the performance..
Hi, thanks for sharing the code. It helps a lot for my research. BTW, I think there's a typo in the model definition. In line 472 of hourglasstiny.py sum[i] = tf.addn([out[i], sum[i-1], ll[0]], name= 'merge') I think ll[0] should be fixed to ll[i]. This might be critical for the performance..