Closed soonchangAI closed 2 years ago
sampled_idx_seq
is a random sample of one of the many answers for each example for "teacher-forcing".
Can make the sampled_idx_seq
constant by adding a line np.random.seed(0)
in mmf/datasets/processors/processors.py
if len(all_idx_seq_list) > 0:
# sample a random decoding answer sequence for teacher-forcing
np.random.seed(0)
idx_seq = all_idx_seq_list[np.random.choice(len(all_idx_seq_list))]
❓ Questions and Help
Hi, I am trying to reproduce the M4C for TextVQA I noticed there is difference in the batch for different runs.
The sample list (same training example but for different runs) are largely similar except for
sampled_idx_seq
andtrain_prev_inds
fields What causes the difference ? Is there any way to make it constant for different runs?For example: During first run:
During second run:
Similarly for
STVQA
During first run:During second run: