Activity
Ratings Progression
Challenge Categories
Challenges Entered
A benchmark for image-based food recognition
Latest submissions
What data should you label to get the most value for your money?
Latest submissions
Behavioral Representation Learning from Animal Poses.
Latest submissions
Airborne Object Tracking Challenge
Latest submissions
Training sample-efficient agents in Minecraft
Latest submissions
Multi-Agent RL for Trains
Latest submissions
Machine Learning for detection of early onset of Alzheimers
Latest submissions
5 Puzzles 21 Days. Can you solve it all?
Latest submissions
See Allgraded | 172692 | ||
graded | 172688 | ||
graded | 172686 |
Measure sample efficiency and generalization in reinforcement learning using procedurally generated environments
Latest submissions
Self-driving RL on DeepRacer cars - From simulation to real world
Latest submissions
Robustness and teamwork in a massively multiagent environment
Latest submissions
See Allgraded | 150842 | ||
graded | 150841 | ||
graded | 150839 |
3D Seismic Image Interpretation by Machine Learning
Latest submissions
5 Puzzles 21 Days. Can you solve it all?
Latest submissions
Latest submissions
Play in a realistic insurance market, compete for profit!
Latest submissions
5 Puzzles 21 Days. Can you solve it all?
Latest submissions
See Allfailed | 169017 | ||
graded | 149018 | ||
graded | 148506 |
A benchmark for image-based food recognition
Latest submissions
Sample-efficient reinforcement learning in Minecraft
Latest submissions
Latest submissions
5 Puzzles, 3 Weeks. Can you solve them all? π
Latest submissions
See Allgraded | 136936 | ||
graded | 135991 | ||
graded | 135988 |
Multi-agent RL in game environment. Train your Derklings, creatures with a neural network brain, to fight for you!
Latest submissions
Predicting smell of molecular compounds
Latest submissions
Classify images of snake species from around the world
Latest submissions
5 Problems 21 Days. Can you solve it all?
Latest submissions
See Allgraded | 122965 | ||
graded | 122961 | ||
graded | 122960 |
5 Puzzles 21 Days. Can you solve it all?
Latest submissions
See Allgraded | 128820 | ||
failed | 128427 | ||
failed | 126803 |
5 Puzzles, 3 Weeks | Can you solve them all?
Latest submissions
See Allgraded | 118013 | ||
graded | 117983 | ||
graded | 117917 |
5 PROBLEMS 3 WEEKS. CAN YOU SOLVE THEM ALL?
Latest submissions
Reinforcement Learning on Musculoskeletal Models
Latest submissions
Latest submissions
Latest submissions
A new benchmark for Artificial Intelligence (AI) research in Reinforcement Learning
Latest submissions
Predict Heart Disease
Latest submissions
Latest submissions
ACL-BioNLP Shared Task
Latest submissions
Latest submissions
See Allgraded | 117917 | ||
graded | 115153 |
Predict moves of a chess piece from video snippet
Latest submissions
Identify which side has least players
Latest submissions
Predict the winner through prior chess moves
Latest submissions
See Allgraded | 122965 | ||
graded | 122961 | ||
graded | 122960 |
Classify Stages of Mars Spacecraft
Latest submissions
Classify Mars Rover Images
Latest submissions
Latest submissions
Can you classify Research Papers into different categories ?
Latest submissions
See Allfailed | 141310 | ||
failed | 141307 | ||
failed | 141306 |
Deshuffle the Shuffled Text
Latest submissions
Latest submissions
Latest submissions
Can you detect Starship with unsupervised data ?
Latest submissions
Can you detect Icebergs in low visibility ?
Latest submissions
Can you remove clouds from an high altitude videos ?
Latest submissions
Can You Classify the Weather from the Images
Latest submissions
Semantic Segmentation of Self Driving Car Environment
Latest submissions
Predict Obstacles Around Self-Driving Cars
Latest submissions
Multi-Class Object Detection on Road Scene Images
Latest submissions
Can You Detect Cars Around You Using LiDAR Data?
Latest submissions
Train your RL agents
Latest submissions
Classifying 15 programming languages into different classes
Latest submissions
Can you identify who spoke these lines?
Latest submissions
Translate Crowd Talk (our new language) to English using Machine Translation
Latest submissions
A puzzle that explores the inner workings of NLP Pre-Processing
Latest submissions
See Allgraded | 169588 |
Detect products & calculate the bill for a self checkout machine
Latest submissions
See Allgraded | 190197 | ||
graded | 189460 | ||
graded | 189428 |
Group similar reviews together & perform sentiment analysis.
Latest submissions
See Allgraded | 187338 |
Participant | Rating |
---|---|
rdeggau | 153 |
vrv | 0 |
Participant | Rating |
---|---|
mohanty |
-
BaselineScore AI Blitz XIIIView
Mask Prediction
Face Recognition
Extract images from the main image
Almost 3 years agoYes! We have a function added in the Baseline notebook of Face Recognition Puzzle named get_target_face
which simply takes the target face_no
( which will be between β00β and β99β [ in string ] ) and target_image
.
def get_target_face(face_no, target_image):
# Top-Left x, y corrdinates of the specific face
x, y = (int(face_no[0]))*216, (int(face_no[1]))*216
target_face = target_image[x:x+216, y:y+216]
return target_face
# Showing a sample face from a sample target image
sample_target_face = get_target_face("96", sample_target)
You can find more about it in the baseline. I hope this helps!
Shubhamai
AI Blitz XIII
How to fine tune models
Almost 3 years agoHi @diego26dav
For these image-to-image translation tasks, I would really suggest you to check out this TensorFlow notebook on Image-to-image translation using GANs, they have some really good implementation on this for getting started. You can also check out this blog on the topic.
Shubhamai
π¨ AI Blitz 13 β‘ Faces [New Challenge Launch]
Almost 3 years agoHi @notnanton
Glad to hear that you liked the challenge And yes, you are allowed to use pre-trained networks, including the one you mentioned. You are also allowed to fine-tune its weights. The things that the rule doesnβt allow is using models that are not free to use and publically available. I hope this helps. Let me know if you have any more questions.
Shubhamai
Emotion Detection
Getting error while submitting the submission.csv
Almost 3 years agoHi, is this possible if you can share the notebook you used to make submissions in dms ? It will help us a lot to figure out the issue. In the meantime, you can also try looking at our Getting Started notebook for sentiment classification and see if thereβs any major difference in terms of what commands you are using to make a submission. I hope it helps.
Shubhamai
Getting error while submitting the submission.csv
Almost 3 years agoHi. Can you please share with us the steps to reproduce the error so that we can figure out the exact cause of this issue ?
Regards
Shubhamai
Getting error while submitting the submission.csv
Almost 3 years agoHi @mohd_saqib
Thanks for letting us know. We are looking into the issue, will get back to you asap.
Shubhamai
Sentiment Classification
Request for the original images
Almost 3 years agoWelcome back to blitz . I can understand but sadly we cannot provide the images because the challenge is based on using the embeddings to classify the sentiment. Adding images will change a whole lot to the original challenge.
Other than that I looked at your submissions and found out you were having some issues. So the exact submission format is that you first put your submission.csv
file and original_notebook.ipynb
( the notebook you generated the predictions from ) in a zip file. This is what the final zip
file should look like -
ββ submission.zip
βββ submission.csv
βββ original_notebook.ipynb
And then you can submit your submission.zip
in on the challenge page. I hope this help Let me know if you have any more questions.
Shubhamai
How embeddings were gotten?
Almost 3 years agoThe exact layer depends on the model you are using and what layer you want to extract the features from. Commonly, for transfer learning, it is the layer just before the fully connected layer. So for ex. in vgg16
, itβs the last max-pooling layer. Same with resnet18
, the features are extracted from the layer before the fully connected layer.
Hereβs another blog you can read if you want to learn more about vgg16 feature extraction. I hope this helps
Shubhamai
How embeddings were gotten?
Almost 3 years agoHi @vad13irt
So, to generate the embeddings, we first took all of the images which had their corresponding labels and put them into ( for ex. resnet18
) model, and then we extracted the features of the images from a certain layer of the model. This blog is also quite good if you want to understand the whole process.
Let me know if you have any questions. Enjoy Blitz
Shubhamai
AI Blitz XII
What's the definition of external data?
Almost 3 years agoHi youssef_nader3
Apologies for the late reply here. You can freely use publicly available pre-trained models & embeddings for submission in Blitz XII. But use of external raw data is not allowed. The challenge rule generally prohibits the use of other public/private datasets which you can use to train your model or improve the scores. I hope this helps. Let me know if you still have any doubts
Best
Shubhamai
Object Detection
Two questions to the " [Getting Started Notebook] Object Detection"
Over 3 years agoHi, itβs fixed now!
For the -
- Why score = 0 & Why " Generating Predictions" has the variable βnβ in two for-cycles ?
I looked into the issue and turns out there were few mistakes we made in our baselines such as -
-
Not loading the model weights after training it.
cfg.MODEL.WEIGHTS = os.path.join(cfg.OUTPUT_DIR, "model_final.pth")
-
Bounding boxes were in the wrong format
The right format for bounding boxes is(x, y, w, h)
instead of(x1, y1, x2, y2)
( which detectron2 outputted )
As for the -
- and βimage_idβ:n+1?
The image_id
helps the evaluator identify predictions for each image. So there are 1000 unique images ids because there are 1000 testing images.
To know what is the image_id
of each image, it is simply the file number ( for ex. 345
in 345.jpg
) + 1 because the image_id
starts from 1 in our ground truth file.
I hope this helps, the getting started notebook is also updated! let me know if you still had any doubts
Shubhamai
Two questions to the " [Getting Started Notebook] Object Detection"
Over 3 years agoThanks for letting us know I am looking into the notebook and will give you updates asap
Obstacle Prediction
505 Error everytime i open leaderboards
Over 3 years agoThanks for letting us know! We are looking into the issue
AI Blitz X
Submission Guidelines
Over 3 years agoYes, you can make submissions from your own/local machine, but the submission has to be a .ipynb
notebook. In case you want to import a custom python file, you can add that python file in the assets
directory and then import it in the .ipynb
notebook. I hope this helps :), let me know if you have any doubts!
Cheers
Shubhamai
Submission issue on google cloud platform
Over 3 years agoHi, can you please tell which specific puzzle you are having issues with ? We are looking into the issue however an another way you can make the submission is by wrapping up all necessary files in a zip file such such that the zip file contents tree looks something like this -
Using Docking ISS puzzle as an example
submission.zip
βββ assets
β βββ submission.csv
βββ original_notebook.ipynb
- The
original_notebook.ipynb
is the notebook you used to train & make the predictions. - The
submisison.csv
contains the predictions of the puzzle ( the format can be different for different puzzles ).
After that you can simply submit the zip file by running
aicrowd submission create -c docking-iss -f YOUR_ZIP_FILE_PATH
Starship Detection-ca47bb
0 score but submission evaluated
Over 3 years agoI tried looking into the issue and also re-runned the submission but I couldnβt able to find anything wrong from our side, can you please check and see if the bounding boxes were in the right format (x, y, w, h) or the ImageID
corresponding to bounding box is correct.
Shubhamai
Docking ISS-d5b4fb
ISS Docking leaderboard
Over 3 years agoThe same question was also replied in discord too but i will also send it here in case another participant also had the same question
Yep, so the Distance Loss is mainly taken into account, but in case, there was a same score in Distance Loss, the second Docking Port Loss is taken into account.
Iceberg Detection
Submission failed
Over 3 years agoSorry for a little late reply but I looked into the notebook & the output .mp4
predictions, and found out that the videos the gen_predictions
function is outputting contains only single frame.
And itβs because the predictions
variable, from the model.nn_module.predict(image_batch)
in gen_predictions
function, has shape torch.Size([1, 1, 128, 128])
which represents a single image, the image_batch
variable has also the same shape.
So i find out the main reason for this error is because you changed the batch size of test_loader
from 23 ( in getting started code ) to 1. The main reason of using batch size of 23 in getting started code was because that each batch will represent each video. So, you will change to change your batch size to 23 and hopefully it will all work.
Let me surely know if you have any more doubts.
Cheers
Shubhamai
Notebooks
-
[Getting Started Notebook] Semantic Segmentation A Getting Started notebook for Semantic Segmentation Puzzle of BlitzXI.ShubhamaicrowdΒ· Over 3 years ago
-
[Getting Started Notebook] Object Detection A Getting Started notebook for Object Detection Puzzle of BlitzXI.ShubhamaicrowdΒ· Over 3 years ago
-
[Getting Started Notebook] Environment Classification A Getting Started notebook for Environment Classification Puzzle of BlitzXI.ShubhamaicrowdΒ· Over 3 years ago
-
[Getting Started Notebook] Lidar Car Detection A Getting Started notebook for Car Detection using Lidar Puzzle of BlitzXI.ShubhamaicrowdΒ· Over 3 years ago
-
[Getting Started Notebook] Obstacle Prediction A Getting Started notebook for Obstacle Prediction Puzzle of BlitzXI.ShubhamaicrowdΒ· Over 3 years ago
-
[Minimal Submission] Iceberg Detection A minimal notebook for Iceberg Detection Puzzle of BlitzX.ShubhamaicrowdΒ· Over 3 years ago
-
[Getting Started Notebook] Iceberg Detection A Getting Started notebook for Icebeg Detection Puzzle of BlitzX.ShubhamaicrowdΒ· Over 3 years ago
-
[Random Submission] Cloud Removal A Random Submission notebook for Cloud Removal Puzzle of BlitzX.ShubhamaicrowdΒ· Over 3 years ago
-
[Getting Started Notebook] Starship Detection A Getting Started notebook for Starship Detection Puzzle of BlitzX.ShubhamaicrowdΒ· Over 3 years ago
-
[Getting Started Notebook] Trees Segmentation A Getting Started notebook for Trees Segmentation Puzzle of BlitzX.ShubhamaicrowdΒ· Over 3 years ago
-
[Getting Started Notebook] Docking ISS A Getting Started notebook for Docking ISS Puzzle of BlitzX.ShubhamaicrowdΒ· Over 3 years ago
-
[In Depth Code] Emotion Detection using spaCy This is a more In depth Code of the Emotion Detection for Blitz 9.ShubhamaicrowdΒ· Over 3 years ago
-
[Getting Started Code] Sound Prediction In this final challenge of Blitz 9, we need to predict the sentences spoken from sound.ShubhamaicrowdΒ· Over 3 years ago
-
[Getting Started Code] NLP Feature Engineering In this fourth challenge of Blitz 9, we are doing Feature Engineering on the Texts.ShubhamaicrowdΒ· Over 3 years ago
-
[Getting Started Code] De Scambling Text using Transformers In this third challenge, we are going to HuggingFace for Sequence to Sequence Prediction.ShubhamaicrowdΒ· Over 3 years ago
-
[Getting Started Code] Research Paper Classification In this second challenge of Blitz 9, we are going to use LSTM for multi class text classificationShubhamaicrowdΒ· Over 3 years ago
-
[Getting Started Code] Emotion Detection using spaCy In this first challenge, we are going to learn fundamentals of Natural Language Processing.ShubhamaicrowdΒ· Over 3 years ago
-
[Baseline] F1 Detection Baseline notebook for F1 Detection Challenge of Blitz 8ShubhamaicrowdΒ· Over 3 years ago
-
[Baseline] F1 Team Classification Baseline notebook for F1 Team Classification Challenge of Blitz 8ShubhamaicrowdΒ· Over 3 years ago
-
[Baseline] F1 Speed Recognition F1 Speed Recognition baseline notebook from F1 Speed Recognition Challenge of Blitz 8ShubhamaicrowdΒ· Over 3 years ago
-
[Baseline] F1 Car Rotation F1 Car Rotation baseline notebook from F1 Car Rotation Challenge of Blitz 8ShubhamaicrowdΒ· Over 3 years ago
-
[Baseline] F1 Smoke Elimination Remove Smoke baseline notebook from F1 Car Challenge of Blitz 8ShubhamaicrowdΒ· Over 3 years ago
-
[Baseline] Space Debris Detection A getting started code for the Space Debris Detection ChallengeShubhamaicrowdΒ· Over 3 years ago
-
[Baseline] Image Correction A getting started code for Image Correction Challenge.ShubhamaicrowdΒ· Over 3 years ago
-
[Baseline] Rover Stage Prediction A getting started code for the Rover Stage Prediction Challenge.ShubhamaicrowdΒ· Over 3 years ago
-
[Baseline] Mars Rotation Prediction A getting started code for the Mars Rotation Prediction Challenge.ShubhamaicrowdΒ· Over 3 years ago
-
[Baseline] Rover Classification A getting started code for the Rover Classification Challenge.ShubhamaicrowdΒ· Over 3 years ago
The mistakes in the dataset
Almost 3 years agoHi @anna_mrukwa
Thank you for your keen observation and for letting us know!
We will try our best to reduce these noise in future Blitz puzzles.
However, since the number of bad samples here is low and because the ongoing AI Blitz 13 is about to end, we think it would not be wise to update the dataset at this point.
Thank you again for reporting.
Regards,
Shubhamai