Abdullah Khilji
Abdullah Khilji
I have used the same code for the purpose of text summarization but after a few iterations on the data I start to receive empty predictions, i.e. ``` [0, 1,...
Usually the batch variable comes at the start for example: `[B, X]` But, `print(src.shape)` gives `tensor([20, 4])`, `tensor([22, 4])` where 4 is the batch size.
``` Instructions for updating: Use `tf.data.experimental.map_and_batch(...)`. INFO:tensorflow:Calling model_fn. INFO:tensorflow:memory input None INFO:tensorflow:Use float type Traceback (most recent call last): File "/home/abdullahkhilji/miniconda3/envs/xlnet/lib/python3.6/site-packages/tensorflow/python/ops/array_ops.py", line 1805, in zeros output = _constant_if_small(zero, shape, dtype,...
``` tokenize_piece_test.cc:(.text.startup+0xb): undefined reference to `boost::unit_test::unit_test_main(bool (*)(), int, char**)' ```