Questions tagged [mscoco]

42 questions
20
votes
2 answers

Understanding COCO evaluation "maximum detections"

I started using the cocoapi to evaluate a model trained using the Object Detection API. After reading various sources that explain mean average precision (mAP) and recall, I am confused with the "maximum detections" paramter used in the…
mincos
  • 401
  • 1
  • 4
  • 13
13
votes
4 answers

Create MS COCO style dataset

How to create a MS COCO style dataset to use with TensorFlow? Does anyone have an experience with this? I have images, and annotations, as well as ground truth masks. I need to convert them to be compatible with MS COCO and any help is appreciated.…
user20112015
  • 307
  • 1
  • 3
  • 9
10
votes
2 answers

COCO api evaluation for subset of classes

I'm using the python coco api to run evaluation for object detection. I have two files, a ground truth json, and a results json. The coco notebook demo only shows running eval for all classes. How can I run it for only one specific class or a subset…
Austin
  • 6,921
  • 12
  • 73
  • 138
7
votes
6 answers

How to install COCO PythonAPI in python3

It seems the COCO PythonAPI only support python2. But peoples do use it in python3 environment. I tried possible methods to install it, like python3 setup.py build_ext --inplace python3 setup.py install But python3 setup.py install will fail due…
Panfeng Li
  • 3,321
  • 3
  • 26
  • 34
5
votes
2 answers

How can I use MS COCO test-dev dataset for instance segmentation?

Now I'm reproducing the Mask R-CNN(Instance segmentation task.) I can't figure out how to use the MS COCO test dataset. There exists 'instances_train2014', 'instances_val2014' which have specific annotations. But in testing data, there are only…
Kim
  • 61
  • 1
  • 3
4
votes
1 answer

"Error while extracting" from tensorflow datasets

I want to train a tensorflow image segmentation model on COCO, and thought I would leverage the dataset builder already included. Download seems to be completed but it crashes on extracting the zip files. Running with TF 2.0.0 on a Jupyter Notebook…
4
votes
1 answer

Generic Loader Function for MS COCO Style Dataset

I am working with Mask-RCNN and want to train my own coco-style dataset with few categories. For the start, I have only 2 classes (apart from the background). Although Mask-RCNN comes with sample dataset, they either contain only one class or they…
Schütze
  • 1,044
  • 5
  • 28
  • 48
3
votes
1 answer

How can i get person class and segmentation from MSCOCO dataset?

I want to download only person class and binary segmentation from COCO dataset. How can I do it?
3
votes
1 answer

How can I load a pre-trained model on COCO dateset for image segmentation?

I want to do semantic segmentation of objects in my video file. I prefer to use a pre-trained model on the COCO dataset (or COCO stuff dataset) and start using it for semantic segmentation and object detection on my own video files. Most of the…
2
votes
0 answers

Problems about how to process coco's test dataset

In coco, we know that both the training set and validation set correspond to particular annotation files, i.e., instances_train2017.json and instances_val2017.json. However, the coco's test set does not have such a annotation file. Maybe the…
George27
  • 21
  • 3
2
votes
1 answer

Pytorch List object has no attribute ‘to’

I am new to Pytorch. I am using a pre-trained model (RESNET-50). And i am trying to train this model on MS-COCO dataset using cocoapi. I have loaded my dataset images and annotations in train loader. for images,labels in train_loader: …
Amr Ahmed
  • 31
  • 1
  • 4
2
votes
0 answers

What is the difference between mAP from Mask R-CNN utils.py and mAP from (MS)COCO?

I trained my Mask R-CNN Network with my own data, which i transformed into COCO Style for my Thesis and now i want to evaluate my results. I found two methods to do that. One method is the evaluation from COCO itself. Mask R-CNN itself shows how to…
Mob
  • 409
  • 1
  • 5
  • 14
2
votes
0 answers

COCO API displaying instance labels and scores

I've been looking COCO API Jupyter notebook examples like this one. This is a simple example that shows how instance annotations can be overlaid. However, it doesn't show how to display labels (in multi-class cases) and scores (for predictions) on…
Austin
  • 6,921
  • 12
  • 73
  • 138
2
votes
1 answer

How to use mscoco stuff dataset with "counts" in binary?

I would like to train my model on MSCOCO semantic segmentation (only stuff) by using the json file but the key "counts" contains binary characters. Did I miss something? I'm using MXNet and the dataloader is directly looking for the json files. Not…
dhassault
  • 91
  • 6
1
vote
0 answers

COCO API evaluation for subsets of key points classes

I'm using the python coco API to run evaluation for Key points estimation. I have two files, a ground truth json, and a results json. My goal is to evaluate KP estimation performance for ALL KP classes. For example, for category 'person', I want…
Alex Goft
  • 1,114
  • 1
  • 11
  • 23
1
2 3