Loading
0 Follower
0 Following
eric_a_scuccimarra
Eric Scuccimarra

Lausanne, CH

4
2
1

Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
Dec
Jan
Feb
Mar
Mon
Wed
Fri

Loading...

Loading...

Challenges Entered

Food Recognition Benchmark 2022
By Seerave Foundation

A benchmark for image-based food recognition

Latest submissions

 graded 177364 Wed, 23 Mar 2022 15:02:29 graded 177282 Tue, 22 Mar 2022 15:00:29 graded 177278 Tue, 22 Mar 2022 13:49:19
ADDI Alzheimers Detection Challenge
By ADDI

Machine Learning for detection of early onset of Alzheimers

Latest submissions

No submissions made in this challenge.
Learn-to-Race: Autonomous Racing Virtual Challenge
By Carnegie Mellon University Arrival

The first, open autonomous racing challenge.

Latest submissions

No submissions made in this challenge.
Music Demixing Challenge ISMIR 2021
By Sony Group Corporation

Latest submissions

No submissions made in this challenge.
Food Recognition Challenge
By Seerave Foundation

A benchmark for image-based food recognition

Latest submissions

 graded 124065 Sun, 28 Feb 2021 19:36:31 failed 124043 Sun, 28 Feb 2021 17:35:17 graded 124025 Sun, 28 Feb 2021 15:22:08
Participant Rating
Participant Rating

Detectron2 GPU

About 2 years ago

I have an image for Detectron2 - the latest version as of a few months ago - with PyTorch 1.7, CUDA 10.1, torchvision 0.8.1, that I have verified as working for submissions. If I remember correctly you may need to set a flag when installing

• skooch/detectron2

Docker Containers for Submission with mmdetection

About 2 years ago

They are upload to DockerHub, so you can retrieve them with

docker pull skooch/mmdet-aicrowd-latest


Or you can reference them in your Dockerfile :

FROM skooch/mmdet-aicrowd-latest

Incorrect Bboxes

Over 2 years ago

While the masks seem to be correct, it seems that many of the images in the train dataset have bboxes that do not match the masks. While some of the bboxes are merely slightly off, many are drastically off, as we can see in the examples below.

If you are using the bboxes in training, this may cause problems as the model will be attempting to learn using incorrect bboxes. I wrote the following code to recreate the bboxes based on the masks :

import json
from pycocotools.coco import COCO

def create_new_bboxes(item, coco_ds):
try:
# convert the item to a binary mask
bin_mask = coco_ds.annToMask(item)

# sum the rows and cols
row_sums = bin_mask.sum(axis=1)
col_sums = bin_mask.sum(axis=0)

# find the first non-zero row
for ty, row in enumerate(row_sums):
if row > 0:
break

# find the first non-zero col
for tx, col in enumerate(col_sums):
if col > 0:
break

# find the first non-zero row from the end
for by in range(len(row_sums) - 1, 0, -1):
if row_sums[by] > 0:
break

# find the first non-zero col from the end
for bx in range(len(col_sums) - 1, 0, -1):
if col_sums[bx] > 0:
break

item['bbox'] = [tx, ty, bx-tx, by-ty]
except Exception as e:
print("Error with image", item['image_id'])
print(e)
return item

def rebbox_dataset(annotations):
# create our coco object
coco_ds = COCO(annotations)

# load the data
with open(annotations) as f:
data = json.loads(f.read())

for i, item in enumerate(data['annotations']):
data[i] = create_new_bboxes(item, coco_ds)

return data


In the images below, the red box is the bbox from the annotation and the blue bbox is a box derived from the mask.

Docker Containers for Submission with mmdetection

Over 2 years ago

I also have an image for Detectron2 - the latest version - with PyTorch 1.7, CUDA 10.1, torchvision 0.8.1. Note that the starter notebook uses an older version of Detectron and PyTorch which I have not checked for compatibility.

• skooch/detectron2

This image is based on the official Detectron2 Docker image, you would need to copy your code into it and install aicrowd tools like coco, pycocotools, aicrowd_api, and aicrowd-repo2docker.

Docker Containers for Submission with mmdetection

Over 2 years ago

When I first started working on this challenge I spent a lot more time trying to get the submissions working without errors than I did on training the models. Much of this time was spent trying to debug the building and execution of the Docker containers.

To avoid this problem I have created two Docker images for mmdetection :

• skooch/mmdet-aicrowd - contains PyTorch 1.2, CUDA 10.0, and mmdet v1.0rc1
• skooch/mmdet-aicrowd-latest - contains PyTorch 1.6, CUDA 10.1, and the latest version of mmdet

If you are using mmdetection, you can build your containers from these images and your submissions will run faster (since the images are already built) and hopefully your submissions will fail less.

Images with Incorrect Annotations

Over 2 years ago

In the starter Detectron notebook we have seen that some of the images have incorrect sizes in the annotation file. It turns out that these images also have rotated masks, as we can see in this notebook :

Visualisation of Bad Annotations

While the number of images with this problem is relatively small, we can prevent these errors from being included in the training data by either rotating the masks or removing the images from the training set.

Erroneous annotations

Over 2 years ago

Image id 8619 is one of the ones that has it’s width and height transposed in the annotations.json file. I suspect these errors are related.

eric_a_scuccimarra has not provided any information yet.