0 minutes to go
  • 34 Participants
  • 336 Submissions
  • 4000 Prize
  • Competition Ends: Aug. 20, 2019, midnight
  • Server Time: 7:19 a.m. UTC

Fully Automated Image and Video Classification
without ANY human intervention

Congratulations to the ECML PKDD AutoCV2 winners (see final phase result table at the bottom of the page):

This is AutoCV2: IMAGE + VIDEO Automated Computer Vision challenge, part of ECML PKDD 2019 competition program! This is a 2-phase challenge; after the feed-back phase (leaderboard shown here) we ran a final blind testing starting August 20. The LAST SUBMISSION of the participants ranked better than baseline2 in the feed-back phase were used in the final phase to determine the winners. This submission was tested on five new datasets and the training/testing was repeated 3 times to reduce computational time variance. 

The winners will present at the ECML PKDD conference.

The IJCNN conf. AutoCV1 winners were [slides]:

The first AutoCV challenge had only Images. In AutoCV2 we have Images + Video, getting closer to full AutoDL yet: Despite recent successes of deep learning and other machine learning techniques, practical experience and expertise is still required to select models and/or choose hyper-parameters when applying techniques to new datasets. This problem is drawing increasing interest, yielding progress towards fully automated solutions. In this challenge your machine learning code is trained and tested on this platform, without human intervention whatsoever, on image or video classification tasks you have never seen before, with time and memory limitations. All problems are multi-label classification problems, coming from various domains including medical imaging, satellite imaging, object recognition, character recognition, face recognition, etc. They lend themselves to deep learning solutions, but other methods may be used. Raw data is provided, but formatted in a uniform manner, to encourage you to submit generic algorithms. 

FINAL PHASE RESULT TABLE


User
submissions
Dataset 1
Dataset 2
Dataset 3
Dataset 4
Dataset 5
<Rank>
Max 1
Max 2
Max 3
Max 4
Max 5
<Max Rank>
Final Max Rank
Final Rank
kakaobrain
6271 6385 6505 6655 6661 6667 6745 6751 6757
0.6277±0.0628 (8)
0.9048±0.0517 (5)
0.4076±0.0139 (8)
0.4640±0.0443 (2)
0.2091±0.0122 (3)
5.2
0.6963 (6)
0.9276 (1)
0.4206 (7)
0.5067 (2)
0.2217 (3)
3.8
1
1
tanglang
6619 6625 6631 6817 6823 6829 6835 6841 6847
0.6231±0.0449 (9)
0.8406±0.0461 (11)
0.4527±0.0270 (4)
0.3688±0.0260 (6)
0.2363±0.0130 (1)
6.2
0.6635 (8)
0.8772 (10)
0.4734 (3)
0.4105 (5)
0.2507 (1)
5.4
2
2
kvr
6283 6397 6517 6709 6715 6721 6799 6805 6811
0.6835±0.0299 (2)
0.9115±0.0150 (3)
0.4658±0.0083 (2)
-0.0417±0.0060 (16)
0.1627±0.0120 (8)
6.2
0.7174 (2)
0.9226 (2)
0.4778 (2)
-0.0289 (17)
0.1810 (7)
6
4
2
DXY0808
6373 6493 6607 6691 6697 6703 6781 6787 6793
0.6469±0.0268 (6)
0.8673±0.0094 (8)
0.3560±0.0158 (11)
0.3702±0.0235 (5)
0.2223±0.0159 (2)
6.4
0.6763 (7)
0.8800 (9)
0.3690 (11)
0.4056 (6)
0.2403 (2)
7
6
4
ether
6307 6427 6541 6673 6679 6685 6763 6769 6775
0.6756±0.0301 (5)
0.9086±0.0065 (4)
0.4700±0.0065 (1)
-0.0430±0.0088 (18)
0.1711±0.0153 (6)
6.8
0.7043 (4)
0.9181 (5)
0.4781 (1)
-0.0255 (15)
0.1979 (4)
5.8
3
5
Hana.Inst.Tech
6379 6499 6613
0.6815±0.0180 (3)
0.9194±0.0018 (1)
0.4640±0.0067 (3)
-0.0550±0.0082 (19)
0.1523±0.0087 (9)
7
0.7005 (5)
0.9213 (3)
0.4688 (5)
-0.0463 (19)
0.1623 (9)
8.2
8
6
myelinio
6301 6421 6535 6637 6643 6727 6733 6739 6853
0.6774±0.0370 (4)
0.8829±0.0657 (6)
0.4491±0.0255 (5)
-0.0420±0.0082 (17)
0.1724±0.0114 (5)
7.4
0.7114 (3)
0.9207 (4)
0.4702 (4)
-0.0276 (16)
0.1853 (6)
6.6
5
7
Letrain
6289 6403 6523
0.4684±0.0020 (14)
0.8406±0.0075 (10)
0.4030±0.0028 (9)
0.3972±0.0222 (3)
0.1865±0.0021 (4)
8
0.4707 (14)
0.8489 (12)
0.4047 (10)
0.4147 (4)
0.1878 (5)
9
9
8
team_zhaw
6277 6391 6511
0.5418±0.0340 (10)
0.8355±0.0915 (12)
0.4110±0.0072 (7)
0.3970±0.0298 (4)
0.1677±0.0052 (7)
8
0.5776 (10)
0.9006 (7)
0.4166 (8)
0.4178 (3)
0.1734 (8)
7.2
7
8
automl_freiburg
6295 6415 6529
0.1836±0.0022 (20)
0.9138±0.0021 (2)
0.4009±0.0079 (10)
0.5169±0.0404 (1)
0.1031±0.0070 (14)
9.4
0.1856 (20)
0.9158 (6)
0.4066 (9)
0.5494 (1)
0.1111 (13)
9.8
10
10
accheng
6331 6451 6565
0.6912±0.0366 (1)
0.7757±0.0466 (14)
0.4455±0.0080 (6)
-0.0075±0.0019 (14)
0.0543±0.0128 (17)
10.4
0.7331 (1)
0.8098 (13)
0.4547 (6)
-0.0053 (14)
0.0648 (17)
10.2
11
11
mmadadi
6361 6481 6595
0.6376±0.0149 (7)
0.8540±0.0040 (9)
0.2131±0.0039 (14)
0.2712±0.0276 (8)
0.0907±0.0052 (15)
10.6
0.6548 (9)
0.8582 (11)
0.2176 (14)
0.2970 (8)
0.0958 (15)
11.4
13
12
upwind_flys
6313 6433 6547
0.5220±0.0459 (11)
0.7933±0.0030 (13)
0.3523±0.0040 (12)
0.2862±0.0196 (7)
0.1358±0.0179 (11)
10.8
0.5630 (11)
0.7967 (14)
0.3567 (12)
0.3036 (7)
0.1519 (11)
11
12
13
brunosez
6343 6463 6577
0.4822±0.0094 (13)
0.7149±0.0600 (17)
0.2077±0.0050 (15)
0.1117±0.0305 (11)
0.1114±0.0080 (12)
13.6
0.4912 (13)
0.7506 (16)
0.2132 (15)
0.1357 (11)
0.1206 (12)
13.4
14
14
baseline2
6355 6475 6589
0.4514±0.0196 (16)
0.7297±0.0120 (16)
0.2199±0.0100 (13)
0.1388±0.0177 (10)
0.1055±0.0040 (13)
13.6
0.4633 (15)
0.7381 (17)
0.2306 (13)
0.1499 (10)
0.1094 (14)
13.8
15
14
OsbornArchibald
6319 6439 6553
0.4562±0.0042 (15)
0.8679±0.0112 (7)
0.0248±0.0067 (18)
-0.0363±0.0032 (15)
0.0393±0.0081 (18)
14.6
0.4597 (16)
0.8808 (8)
0.0296 (18)
-0.0340 (18)
0.0471 (18)
15.6
17
16
Pavao
6325 6445 6559
0.2293±0.0157 (19)
0.5047±0.0341 (19)
0.0598±0.0076 (17)
0.1688±0.0154 (9)
0.1389±0.0220 (10)
14.8
0.2474 (19)
0.5423 (19)
0.0673 (17)
0.1801 (9)
0.1622 (10)
14.8
16
17
bamboo_pandas
6337 6457 6571
0.2576±0.0160 (18)
0.7541±0.0243 (15)
-1.0000±0.0000 (20)
0.0015±0.0005 (13)
0.0680±0.0041 (16)
16.4
0.2691 (18)
0.7820 (15)
-1.0000 (20)
0.0021 (13)
0.0721 (16)
16.4
18
18
baseline1
6367 6487 6601
0.3098±0.0044 (17)
0.3590±0.0068 (20)
0.1349±0.0147 (16)
0.0038±0.0033 (12)
0.0177±0.0029 (19)
16.8
0.3148 (17)
0.3667 (20)
0.1471 (16)
0.0068 (12)
0.0198 (19)
16.8
19
19
chenweiwei-1
6349 6469 6583
0.5118±0.0337 (12)
0.6752±0.0128 (18)
-0.0156±0.0062 (19)
-1.0000±0.0000 (20)
-0.0116±0.0220 (20)
17.8
0.5456 (12)
0.6842 (18)
-0.0089 (19)
-1.0000 (20)
0.0101 (20)
17.8
20
20
 
 

Quick start

This is a challenge with code submission. We provide 3 baseline methods for test purposes (Note: to avoid that tests take too long, we set in model.py self.num_epochs_we_want_to_train = 1; you may change that):

Baseline 0: Constant (zero) predictions

Baseline 1: Linear classifier

Baseline 2: 3D Convolutional Neural Network

To make a test submission, download one of the baseline methods, click on the blue button "Upload a Submission" in the upper right corner of the page and re-upload it. You must click first the orange tab "All datasets" if you want to make a submission simultaneously on all datasets and get ranked in the challenge. You may also submit on a single dataset at a time (for debug purposes). To check progress on your submissions go to the "My Submissions" tab. Your best submission is shown on the leaderboard visible under the "Results" tab. 

Complete starting kit

The starting kit contains everything you need to create your own code submission (just by modifying the file model.py) and to test it on your local computer, with the same handling programs and Docker image as those of the Codalab platform (but the hardware environment is in general different).

Download the Starting Kit

This includes a jupyter notebook tutorial.ipynb with step-by-step instructions. The interface is simple and generic: you must supply a Python class model.py with:

  • a constructor
  • a `train` method
  • a `test` method
  • a `done_training` attribute

To make submissions, zip model.py (without the directory), then use the "Upload a Submission" button. That's it!

Computational limitations

  • A submission on one dataset is limited to a maximum of 20 minutes.
  • We currently limit participants to 5 hours of compute time per day (subject to change, depending on the number of participants).
  • Participants are limited to 5 submissions per day per dataset.

Since for one dataset a submission may take up to 20 minutes and there are 5 datasets, if you do not stop your model early, you will only be able to make 3 full submissions (on all datasets) per day: 3 times x 5 datasets x (1/3 h)/dataset ~ 5h. However, you may manage your time in a more effective way by stopping your models early. This is done by setting the "done_training" attribute to "True" once you are done training, e.g. after a certain number of epochs.

Larger practice datasets

The starting kit contains sample data, but you may want to develop your code with larger practice datasets. We provide 8 public datasets for this purpose. You will have access to the data (training set and test set) AND the true labels for these datasets. Notice that the video datasets do not include a sound track.

 #   Name  Type  Domain  Size  Source

 Data (w/o test labels)

 Test labels
 1  Munster  Image  HWR  18 MB  MNIST  munster.data  munster.solution
 2  Chucky  Image  Objects  128 MB  Cifar-100  chucky.data  chucky.solution
 3  Pedro  Image  People  377 MB  PA-100K  pedro.data  pedro.solution
 4  Decal  Image  Aerial  73 MB  NWPU VHR-10  decal.data  decal.solution
 5  Hammer  Image  Medical  111 MB  Ham10000  hammer.data  hammer.solution
 6  Kraut  Video  Action  1.9 GB  KTH  kraut.data  kraut.solution
 7  Katze  Video  Action  1.9 GB  KTH  katze.data  katze.solution
 8  Kreatur  Video  Action  469 MB  KTH  kreatur.data  kreatur.solution

 

 

 

 

 

 

 

 

 # 

 Name

 num_train

 num_test

 sequence_size

 row_count

 col_count

 num_channels

 output_dim   
 1  Munster  60000  10000  1  28  28  1  10  
 2  Chucky  48061  11939  1  32  32  3  100  
 3  Pedro  80095  19905  1  -1  -1  3  26  
 4  Decal  634  166  1  -1  -1  3  11  
 5  Hammer  8050  1965  1  400  300  3  7  
 6  Kraut  1528  863  181  120  160  1  4  
 7  Katze  1528  863  181  120  160  1  6  
 8  Kreatur  1528  863  181  60  80  3  4  

 

 

 

 

 

 

 

 

  • num_train/num_test: number of training/test examples
  • sequence_size/row_count/col_count/num_channels: shape parameters of the examples (in AutoCV challenge, every example is represented by a 4D tensor with axes t, x, y and c (t for time and c for channel)). A row_count or col_count of -1 means the value varies from one example to another.
  • output_dim: number of classes
  • has_locality_col (resp. has_locality_row): A flag indicating whether rows (resp. columns) in the tensor correspond to variables interrelated with some underlying topological structure ,reflected by the closeness of indices, like in images or videos.

These data were re-formatted from original public datasets. If you use them, please make sure to acknowledge the original data donnors (see "Source" in the data table) and check the tems of use.

To download all public datasets at once:

cd autodl_starting_kit_stable
python download_public_datasets.py

Format and use your own datasets

Raw data are preserved, but formatted in a generic data format based on TFRecords, used by TensorFlow. However, this will not impose to participants to use deep learning algorithms nor even Tensorflow. If you want to practice designing algorithms with your own datasets, follow these steps

Competition protocol

This challenge has two phases. This is the feed-back phase: when you submit your code, you get immediate feed-back on five development datasets. In the final test phase, you will be evaluated on five new datasets. Eligible participants to the final phase will be notified when and where to submit their code for a final blind test on these five new datasets. The ranking in the final phase will count towards determining the winners.

Code submitted is trained and tested automatically, without any human intervention. Code submitted on "All datasets" is run on all five development datasets in parallel on separate compute workers, each one with its own time budget. 

The identities of the datasets used for testing on the platform are concealed. The data are provided in a raw form (no feature extraction) to encourage researchers to use Deep Learning methods performing automatic feature learning, although this is NOT a requirement. All problems are multi-label classification problems. The tasks are constrained by the time budget (20 minutes/dataset)

Here is some pseudo-code of the evaluation protocol:

# For each dataset, our evaluation program calls the model constructor:
M = Model(metadata=dataset_metadata)
# Initialize
remaining_time budget = overall_time_budget
start_time = time()
# Ingestion program calls multiple times train and test:
repeat until M.done_training or remaining_time_budget < 0
{
  M.train (training_data, remaining_time_budget)
  remaining_time_budget = start_time + overall_time_budget - time.time()
  results = M.test(test_data, remaining_time_budget)
  remaining_time_budget = start_time + overall_time_budget - time.time()
# Results made available to scoring program (run in separate container) save(results) }

It is the responsibility of the participants to make sure that neither the "train" nor the "test" methods exceed the “remaining_time_budget”. The method “train” can choose to manage its time budget such that it trains in varying time increments. There is pressure that it does not use all "overall_time_budget" at the first iteration because we use the area under the learning curve as metric.

Metrics

The participants can train in batches of pre-defined duration to incrementally improve their performance, until the time limit is attained. In this way we can plot learning curves: "performance" as a function of time. Each time the "train" method terminates, the "test" method is called and the results are saved, so the scoring program can use them, together with their timestamp.

We treat both multi-class and multi-label problems alike. Each label/class is considered a separate binary classification problem, and we compute the normalized AUC (or Gini coefficient)

    2 * AUC - 1

as score for each prediction, here AUC is the usual area under ROC curve (ROC AUC).

For each dataset, we compute the Area under Learning Curve (ALC). The learning curve is drawn as follows:

  • at each timestamp t, we compute s(t), the normalized AUC (see above) of the most recent prediction. In this way, s(t) is a step function w.r.t time t;
  • in order to normalize time to the [0, 1] interval, we perform a time transformation by

    where T is the time budget (of default value 1200 seconds = 20 minutes) and t0 is a reference time amount (of default value 60 seconds).
  • then compute the area under learning curve using the formula

    we see that s(t) is weighted by 1/(t + t0)), giving a stronger importance to predictions made at the beginning of th learning curve.

After we compute the ALC for all 5 datasets, the overall ranking is used as the final score for evaluation and will be used in the learderboard. It is computed by averaging the ranks (among all participants) of ALC obtained on the 5 datasets.

Examples of learning curves:

Challenge Rules

  • General Terms: This challenge is governed by the General ChaLearn Contest Rule Terms, the Codalab Terms and Conditions, and the specific rules set forth.
  • Announcements: To receive announcements and be informed of any change in rules, the participants must provide a valid email.
  • Conditions of participation: Participation requires complying with the rules of the challenge. No team can register after August 13. Prize eligibility is restricted by US government export regulations, see the General ChaLearn Contest Rule Terms. The organizers, sponsors, their students, close family members (parents, sibling, spouse or children) and household members, as well as any person having had access to the truth values or to any information about the data or the challenge design giving him (or her) an unfair advantage, are excluded from participation. A disqualified person may submit one or several entries in the challenge and request to have them evaluated, provided that they notify the organizers of their conflict of interest. If a disqualified person submits an entry, this entry will not be part of the final ranking and does not qualify for prizes. The participants should be aware that ChaLearn and the organizers reserve the right to evaluate for scientific purposes any entry made in the challenge, whether or not it qualifies for prizes.
  • Dissemination: The challenge is part of the official selection of the ECML PKDD conference. Top ranking participants will be invited to submit a paper to a special issue on Automated Machine learning of the IEEE transactions PAMI.
  • Registration: The participants must register to Codalab and provide a valid email address. Teams must register only once and provide a group email, which is forwarded to all team members. Teams or solo participants registering multiple times to gain an advantage in the competition may be disqualified.
  • Anonymity: The participants who do not present their results at the workshop can elect to remain anonymous by using a pseudonym. Their results will be published on the leaderboard under that pseudonym, and their real name will remain confidential. However, the participants must disclose their real identity to the organizers to claim any prize they might win. See our privacy policy for details.
  • Submission method: The results must be submitted through this CodaLab competition site. The number of submissions per day and maximum total computational time are restrained and subject to change, according to the number of participants. Using multiple accounts to increase the number of submissions in NOT permitted. In case of problem, send email to autodl@chalearn.org. The entries must be formatted as specified on the Instructions page.
  • Prizes: The three top ranking participants in the Final phase blind testing may qualify for prizes. To compete for prizes, the participants must make a valid submission on the Feed-back phase; their last submission in the Feed-back phase will be forwarded to the Final phase for ranking using five new datasets. Only submissions ranked better than baseline2 in the Feed-back phase will be eligible for the final ranking. The be ranked, the participants must also fill out a fact sheet briefly describing their methods. There is no other publication requirement. The winners will be required to make their code publicly available under an OSI-approved license such as, for instance, Apache 2.0, MIT or BSD-like license, if they accept their prize, within a week of the deadline for submitting the final results. Entries exceeding the time budget will not qualify for prizes. In case of a tie, the prize will go to the participant who submitted his/her entry first. Non winners or entrants who decline their prize retain all their rights on their entries and are not obliged to publicly release their code.

Help

Can organizers compete in the challenge?

No, they can make entries that show on the leaderboard for test purposes and to stimulate participation, but they are excluded from winning prizes. Excluded entrants include: baseline0, baseline1, baseline2, baiyu, eric, hugo.jair, juliojj, Lukasz, madclam, Pavao, shangeth, thomas, tthomas, Zhen, Zhengying.

Are there prerequisites to enter the challenge?

No, except accepting the TERMS AND CONDITIONS.

Can I enter any time?

Yes, until the challenge deadline.

Where can I download the data?

You can download "public data" only from the Instructions page. The data on which your code is evaluated cannot be downloaded, it will be visible to your code only, on the Codalab platform.

How do I make submissions?

To make a valid challenge entry, make sure to click first the orange button "All datasets", then click the blue button on the upper right side "Upload a Submission". This will ensure that you submit on all 5 datasets of the challenge simultaneously. You may also make a submission on a single dataset for debug purposes, but it will not count towards the final ranking.

Do you provide tips on how to get started?

We provide a Starting Kit in Python with step-by-step instructions in a Jupyter notebook called "tutorial.ipynb", which can be found in the github repository https://github.com/zhengying-liu/autodl_starting_kit_stable. You can also have a well rendered preview here.

Are there publication opportunities?

Yes. Top ranking participants will be invited to submit papers to a special issue of the IEEE transaction journal PAMI on Automated Machine Learning and will be entered in a contest for the best paper. Deadline November 30, 2019.

There will be 2 best paper awards of $1000 ("best paper" and "best student paper").

Are there prizes?

Yes, a 4000 USD prize pool.

 

1st place

2nd place

3rd place

Prize

2000 USD

1500 USD

500 USD

Do I need to submit code to participate?

Yes, participation is by code submission.

When I submit code, do I surrender all rights to that code to the SPONSORS or ORGANIZERS?

No. You just grant to the ORGANIZERS a license to use your code for evaluation purposes during the challenge. You retain all other rights.

If I win, I must submit a fact sheet, do you have a template?

Yes, please download it [HERE].

What is your CPU/GPU computational configuration?

We are running your submissions on Google Cloud NVIDIA Tesla P100 GPUs. In non peak times we are planning to use 10 workers, each of which will have one NVIDIA Tesla P100 GPU (running CUDA 10 with drivers cuDNN 7.5) and 4 vCPUs, with 26 GB of memory, 100 GB disk.

The PARTICIPANTS will be informed if the computational resources increase. They will NOT decrease.

Can I pre-train a model on my local machine and submit it?

This is not explicitly forbidden, but it is discouraged. We prefer if all calculations are performed on the server. If you submit a pre-trained model, you will have to disclose it in the fact sheets. 

Will there be a final test round on separate datasets?

YES. The ranking of participants will be made from a final blind test made by evaluating a SINGLE SUBMISSION made on the final test submission site. The submission will be evaluated on five new datasets in a completely "blind testing" manner. The final test ranking will determine the winners.

What is my time budget?

Each execution must run in less than 20 minutes (1200 seconds) for each dataset. Your cumulative time is limited to 5 hours per day in total.

Does the time budget correspond to wall time or CPU/GPU time?

Wall time.

My submission seems stuck, how long will it run?

In principle no more than its time budget. We kill the process if the time budget is exceeded. Submissions are queued and run on a first time first serve basis. We are using several identical servers. Contact us if your submission is stuck more than 24 hours. Check on the leaderboard the execution time.

How many submissions can I make?

Five per day (and up to a total of 100), but up to a total computational time of 5 hours (submissions taking longer will be aborted). This may be subjet to change, according to the number of participants. Please respect other users. It is forbidden to register under multiple user IDs to gain an advantage and make more submissions. Violators will be DISQUALIFIED FROM THE CONTEST.

Do my failed submissions count towards my number of submissions per day?

No. Please contact us if you think the failure is due to the platform rather than to your code and we will try to resolve the problem promptly.

Why did my submission crash (immediately) with no error message? 

The submission evaluation logic is implemented such that most errors coming from executing your model.py are catched by ingestion program. We made this choice to always (hopefully) terminate the evaluation process within the scope of ingestion program, independent of the CodaLab platform.

To find the error message, you can go to "My Submissions" -> "Dataset 2" (for example) -> Click "+" button of your corresponding submission -> "Output Log" of "Ingestion Step".

What happens if I exceed my time budget?

This should be avoided. In the case where a submission exceeds 20 minutes of time budget for a particular task (dataset), the submission handling process (ingestion program in particular) will be killed when time budget is used up and predictions made so far (with their corresponding timestamps) will be used for evaluation. In the other case where a submission exceeds the total compute time per day, all running tasks will be killed by CodaLab and the status will be marked 'Failed' and a score of -1.0 will be produced.

The time budget is too small, can you increase it?

No sorry, not for this challenge.

What metric are you using?

All problems are multi-label problems and we treat them as multiple 2-class classification problems. For a given dataset, all binary classification problems are scored with the ROC AUC and results are averaged (over all classes/binary problems). For each time step at which you save results, this gives you one point on the learning curve. The final score for one dataset is the area under the learning curve. The overall score on all 5 datasets is the average rank on the 5 datasets. For more details, go to 'Get Started' -> 'Instructions' -> 'Metrics' section.

Which version of Python are you using?

The code was tested under Python 3.5. We are running Python 3.5 on the server and the same libraries are available.

Can I use something else than Python code?

Yes. Any Linux executable can run on the system, provided that it fulfills our Python interface and you bundle all necessary libraries with your submission.

Do I have to use TensorFlow?

No. We use TFRecords to format the datasets in a uniform manner, but you can use other software to process the data, including PyTorch (included in the Docker, see the following question).

Which docker are you running on Codalab?

evariste/autodl:gpu, see the Dockerfile and some instructions on dockerhub.

How do I test my code in the same environment that you are using before submitting?

When you submit code to Codalab, your code is executed inside a Docker container. This environment can be exactly reproduced on your local machine by downloading the corresponding docker image. The docker environment of the challenge contains Anaconda libraries, TensorFlow, and PyTorch (among other things). 
Non GPU users, if you are new to Docker, follow these instructions to install docker. You may then use the docker evariste/autodl:cpu. See details in the Starting Kit that can be downloaded from the Instructions page. GPU users, follow these more detailed instructions.

What is meant by "Leaderboard modifying disallowed"?

Your last submission is shown automatically on the leaderboard. You cannot choose which submission to select. If you want another submission than the last one you submitted to "count" and be displayed on the leaderboard, you need to re-submit it.

Can I register multiple times?

No. If you accidentally register multiple times or have multiple accounts from members of the same team, please notify the ORGANIZERS. Teams or solo PARTICIPANTS with multiple accounts will be disqualified.

How can I create a team?

We have disabled Codalab team registration. To join as a team, just share one account with your team. The team leader is responsible for making submissions and observing the rules.

How can I destroy a team?

You cannot. If you need to destroy your team, contact us.

Can I join or leave a team?

It is up to you and the team leader to make arrangements. However, you cannot participate in multiple teams.

Can cheat by trying to get a hold of the evaluation data and/or future frames while my code is running?

No. If we discover that you are trying to cheat in this way you will be disqualified. All your actions are logged and your code will be examined if you win.

Can I give an arbitrary hard time to the ORGANIZERS?

ALL INFORMATION, SOFTWARE, DOCUMENTATION, AND DATA ARE PROVIDED "AS-IS". UPSUD, CHALEARN, IDF, AND/OR OTHER ORGANIZERS AND SPONSORS DISCLAIM ANY EXPRESSED OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR ANY PARTICULAR PURPOSE, AND THE WARRANTY OF NON-INFRIGEMENT OF ANY THIRD PARTY'S INTELLECTUAL PROPERTY RIGHTS. IN NO EVENT SHALL ISABELLE GUYON AND/OR OTHER ORGANIZERS BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF SOFTWARE, DOCUMENTS, MATERIALS, PUBLICATIONS, OR INFORMATION MADE AVAILABLE FOR THE CHALLENGE. In case of dispute or possible exclusion/disqualification from the competition, the PARTICIPANTS agree not to take immediate legal action against the ORGANIZERS or SPONSORS. Decisions can be appealed by submitting a letter to the CHALEARN president, and disputes will be resolved by the CHALEARN board of directors. See contact information.

Where can I get additional help?

For questions of general interest, THE PARTICIPANTS should post their questions to the forum.

Other questions should be directed to the organizers.

Credits

This challenge would not have been possible without the help of many people.

Main organizers:

  • Olivier Bousquet (Google, Switzerland)
  • André Elisseef (Google, Switzerland)
  • Isabelle Guyon (U. Paris-Saclay; UPSud/INRIA, France and ChaLearn, USA)
  • Zhengying Liu (U. Paris-Saclay; UPSud, France)

Other contributors to the organization, starting kit, and datasets, include:

  • Stephane Ayache (AMU, France)
  • Hubert Jacob Banville (INRIA, France)
  • Mahsa Behzadi (Google, Switzerland)
  • Kristin Bennett (RPI, New York, USA)
  • Hugo Jair Escalante (IANOE, Mexico and ChaLearn, USA)
  • Sergio Escalera (U. Barcelona, Spain and ChaLearn, USA)
  • Gavin Cawley (U. East Anglia, UK)
  • Baiyu Chen (UC Berkeley, USA)
  • Albert Clapes i Sintes (U. Barcelona, Spain)
  • Bram van Ginneken (Radboud U. Nijmegen, The Netherlands)
  • Alexandre Gramfort (U. Paris-Saclay; INRIA, France)
  • Yi-Qi Hu (4paradigm, China)
  • Julio Jacques Jr. (U. Oberta de Catalunya, Spain)
  • Meysam Madani (U. Barcelona, Spain)
  • Tatiana Merkulova (Google, Switzerland)
  • Adrien Pavao (U. Paris-Saclay; INRIA, France and ChaLearn, USA)
  • Shangeth Rajaa (BITS Pilani, India)
  • Herilalaina Rakotoarison (U. Paris-Saclay, INRIA, France)
  • Lukasz Romaszko (The University of Edinburgh, UK)
  • Mehreen Saeed (FAST Nat. U. Lahore, Pakistan)
  • Marc Schoenauer (U. Paris-Saclay, INRIA, France)
  • Michele Sebag (U. Paris-Saclay; CNRS, France)
  • Danny Silver (Acadia University, Canada)
  • Lisheng Sun (U. Paris-Saclay; UPSud, France)
  • Sebastien Treger (La Pallaisse, France)
  • Wei-Wei Tu (4paradigm, China)
  • Fengfu Li (4paradigm, China)
  • Lichuan Xiang (4paradigm, China)
  • Jun Wan (Chinese Academy of Sciences, China)
  • Mengshuo Wang (4paradigm, China)
  • Jingsong Wang (4paradigm, China)
  • Ju Xu (4paradigm, China)
  • Zhen Xu (Ecole Polytechnique and U. Paris-Saclay; INRIA, France)

The challenge is running on the Codalab platform, administered by Université Paris-Saclay and maintained by CKCollab LLC, with primary developers:

  • Eric Carmichael (CKCollab, USA)
  • Tyler Thomas (CKCollab, USA)

ChaLearn is the challenge organization coordinator. Google is the primary sponsor of the challenge. 4Paradigm donated prizes. Other institutions of the co-organizers provided in-kind contributions.

All datasets

Start: July 2, 2019, midnight

Description: Please make submissions by clicking on following 'Submit' button. Then you can view the submission results of your algorithm on each dataset in corresponding tab (Dataset 1, Dataset 2, etc).

Datasets:

Color Label Description Start
Dataset 1 This tab contains submission results of your algorithm on Dataset 1. July 2, 2019, midnight
Dataset 2 This tab contains submission results of your algorithm on Dataset 2. July 2, 2019, midnight
Dataset 3 This tab contains submission results of your algorithm on Dataset 3. July 2, 2019, midnight
Dataset 4 This tab contains submission results of your algorithm on Dataset 4. July 2, 2019, midnight
Dataset 5 This tab contains submission results of your algorithm on Dataset 5. July 2, 2019, midnight

Competition Ends

Aug. 20, 2019, midnight

You must be logged in to participate in competitions.

Sign In