rohit-gupta/Video2Language

bash run-feature-extractor.sh Memory Error

roycedry opened this issue · 4 comments

Hi, I got the following error. I am using Tensorflow version 1.12.

Using TensorFlow backend.
Frames will be extracted for 1968 Videos
2018-11-16 23:04:06.951863: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA


Layer (type) Output Shape Param #

input_1 (InputLayer) (None, 40, 224, 224, 3) 0


time_distributed_1 (TimeDist (None, 40, 2048) 23587712


lambda_1 (Lambda) (None, 2048) 0

Total params: 23,587,712
Trainable params: 0
Non-trainable params: 23,587,712


2018-11-16 23:04:23.350239: W tensorflow/core/framework/allocator.cc:122] Allocation of 2055208960 exceeds 10% of system memory.
2018-11-16 23:04:30.131324: W tensorflow/core/framework/allocator.cc:122] Allocation of 2129264640 exceeds 10% of system memory.
2018-11-16 23:04:31.361599: W tensorflow/core/framework/allocator.cc:122] Allocation of 2055208960 exceeds 10% of system memory.
terminate called after throwing an instance of 'std::bad_alloc'
what(): std::bad_alloc
run-feature-extractor.sh: line 2: 15804 Aborted (core dumped) python2 batched_extractor.py

@roycedry How much RAM do you have ? I haven't tried it with a very low RAM machine, but it works fine if you have 64GB of RAM, usually.

Hi, I solved this problem by increasing swap. However, when I run the last step to get the score, I got the following error:

IOError: [Errno 2] No such file or directory: 'results/beam_search_medvoc_simplepredtags_batch128_lowdropout_avgfeat_threshold_minvallosspredicted.json'

What is this file? I didn't find any file under the results folder.

@roycedry the file will be generated when you run the model on MSVD dataset, this is the results file.

hsrev commented

@rohit-gupta i run the model but still dont have results/beam_search_medvoc_simplepredtags_batch128_lowdropout_avgfeat_threshold_minvallosspredicted.json this file. if you have this can you share with me