aras62 / SF-GRU

Pedestrian Action Anticipation using Contextual Feature Fusion in Stacked RNNs

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Test set of PIE

MoonBlvd opened this issue · comments

Hi Amir,

I was trying to run the test script. However it only generated 656 test samples, not 3185 that you mentioned in your paper. Could you please let me know how you get that 3185 test samples?

I added a break point here and then find the length of test_data['test'][0][0] is 656:

test_data, _, _ = self.get_data({'test': data_test}, model_opts)

Thank you,
Brian

Okay, I'm closing this issue since the authors indicated that they will answer this problem in their new code soon.