lihang

This error is due to "dataloader.py". You need to change the __getitem__ function of the class VideoDataset.According to the "idx", get your video id `video_feat = np.load(os.path.join(self.feats_dir[0], your video id...

I encounter the RuntimeError: CUDNN_STATUS_EXECUTE"_FAILED. I fixed it by changing the run evironment as follows: pytorch 0.4.1 CUDA9.0 cudnn7.6.5 python3.6 It maybe help you.

#41 the same as it. You must make sure one idx, one video id, one caption. Otherwise, the dismatch error will occur.

`def build_model(self): tf.variable_scope().reuse_variables() def build_generator(self): tf.variable_scope().reuse_variables()` change to `with tf.variable_scope("model") as scope: scope.reuse_variables() with tf.variable_scope("generator") as scope: scope.reuse_variables()` It works. I'm new in tensorflow. Now I can't tell what happened.

if use python3.x to compile, you need: ` current_feats[ind][:len(current_feats_vals[ind])] = feat` change to `current_feats_vals = list(map(lambda vid: np.load(vid), current_videos))` Python 2.x return list。 Python 3.x return 'map' object。