aras62 / sf-gru Goto Github PK
View Code? Open in Web Editor NEWPedestrian Action Anticipation using Contextual Feature Fusion in Stacked RNNs
License: MIT License
Pedestrian Action Anticipation using Contextual Feature Fusion in Stacked RNNs
License: MIT License
Hi, thanks for impressive work! I want to only run the test (using the pretrained you have provided) but when I run, I get this error:
File "/home/SF-GRU/test.py", line 9, in
beh_seq_test = imdb.generate_data_trajectory_sequence('test', **data_opts)
File "/home/SF-GRU/pie_data.py", line 891, in generate_data_trajectory_sequence
sequence_data = self._get_crossing(image_set, annot_database, **params)
File "/home/SF-GRU/pie_data.py", line 1003, in _get_crossing
set_ids, _pids = self._get_data_ids(image_set, params)
File "/home/SF-GRU/pie_data.py", line 791, in _get_data_ids
_pids = self._get_random_pedestrian_ids(image_set, **params['random_params'])
File "/home/SF-GRU/pie_data.py", line 724, in _get_random_pedestrian_ids
train_samples, test_samples = train_test_split(ped_ids, train_size=ratios[0])
File "/home/SF-GRU/pedintent/lib/python3.5/site-packages/sklearn/model_selection/_split.py", line 2122, in train_test_split
default_test_size=0.25)
File "/home/SF-GRU/pedintent/lib/python3.5/site-packages/sklearn/model_selection/_split.py", line 1805, in _validate_shuffle_split
ValueError: With n_samples=0, test_size=None and train_size=0.5, the resulting train set will be empty. Adjust any of the aforementioned parameters.
I have put the test annotations in the following format:
SF-GRU
pie_dataset
annotations
set01
video_0001_annt.xml
video_0002_annt.xml
video_0003_annt.xml
video_0004_annt.xml
Do you know what the issue is? If you could be provide more detail about the test and train file (or sample.py file in the repo), that will be very helpful. Thanks!
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:
Line 655 in a72997a
Thank you,
Brian
Hi,
Thanks for this wonderful works, it brings a lot of idea for my own research.
I wonder how to test vary ttc prediction behavior after I trained a model.
I just set
"min_track_size" to be observation_time + ttc in test_script.py
However, no matter how I set this value, the output of accuracy is still high (above 0.85 up)
How is this possible when it has such accuracy for about 10 sec event prediction?
Sincerely
One thing you might want to check first is to make sure to delete the dataset cache file and run it again. If you change the sets in _get_image_set_ids it might have an issue with the cached file. Second thing is that what is the dimension of d['act']? it should be three dimensions as [num_samples, seq_length, 1] and after d['act'] = d['act'][:,0,:] should be [num_samples,1]. If you changed anything in the get_sequence, it might affect that
Originally posted by @aras62 in #1 (comment)
Hello authors, firstly thank you for your contribution. I just wanted to take your help in fixing this issue. I have taken the PIE dataset from the repository and having this index out of dimensions error. I am also attaching screenshot of the output screen when running on colab. Moreover as you suggested to check the dimensions. I am getting dimensions of all the elements of dictionary d as (num_samples, ). So does this dataset require some preprocessing? as I am also getting some visibledeprecation warning.
Also I am not changing anything in get_sequence nor I am running on some part of dataset. I am running on complete 6 set of videos. Kindly help
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.