search

ramakanth-pasunuru / video_captioning_rl

Code and Models for paper "Reinforced Video Captioning with Entailment Rewards (EMNLP 2017)"
MIT License
43 stars 13 forks source link

Code Question #4

Closed AmingWu closed 5 years ago

AmingWu commented 5 years ago

There is an error in your code.

video_captioning_rl/models/seq2seq_atten.py

frame_packed = nn.utils.rnn.pack_padded_sequence(frames, flengths, batch_first=True)

ValueError: some of the strides of a given numpy array are negative. This is currently not supported, b ut will be added in future releases.

ramakanth-pasunuru commented 5 years ago

This error occurs with the latest version of the pytorch. This repo doesn't support the lastest version of the pytorch.

The fix for this issue is discussed in this thread: https://github.com/facebookresearch/InferSent/issues/99