Stack Overflow
Stack Overflow

Questions tagged [mscoco]

42 questions
1
vote
1 answer

What is the source of images in MS COCO dataset?

What is the source of images in the MS COCO dataset? Was it manually photographed for the very purpose of creating a dataset through some group of people? or crawled the web? or some image hosting site? Anybody know? Thanks
pandemonium
  • 13
  • 2
1
vote
0 answers

How can I use COCOAPI/PyCOCOTools to evaluate the performance of Tensorflow Lite models

I have used the Tensorflow Object Detection API to train models on a custom dataset. The tensorflow object detection API also allows evaluating the trained models on a test set and gives results in the COCO eval format. An example output from the…
Aviral Jain
  • 21
  • 4
1
vote
0 answers

About MS COCO dataset Evaluation! Image Size! (question about COCO dataset.)

I am a student currently studying object detection! I have a question about COCO dataset. I'm currently experimenting with COCO datasets, and there's APs APm APL in the performance evaluation metrics. 32X32 or less for APs, 32x32 to 96×96 for APm,…
jhLee
  • 11
  • 1
1
vote
1 answer

Rotating image with its bounding boxes yielding worse boxes at 45 degrees with opencv2 and numpy

I have some code, largely taken from various sources linked at the bottom of this post, written in Python, that takes an image of shape [height, width] and some bounding boxes in the [x_min, y_min, x_max, y_max] format, both numpy arrays, and…
IntegrateThis
  • 853
  • 2
  • 16
  • 39
1
vote
0 answers

How to use a class from MS-COCO and add 2 new classes with Mask RCNN?

I want my model to detect only 3 classes i.e. Person, Tyre and Road. I'm using the pretrained MS COCO weights which are already trained on the 'Person' class. How do I use this already present 'Person' class and further train my model for 2 new…
Trollsors
  • 492
  • 4
  • 17
1
vote
1 answer

COCO object detection evaluation metrics vs Kitti evaluation

For my validation dataset (own data), I evaluate using both COCO and Kitti evaluation metrics. I expect a similar score for COCO AP (0.5) value and Kitti 2D AP (with iou=0.5). But I am not sure if they are comparable, inspite the logic behind them…
Apoorva Suresh
  • 11
  • 1
1
vote
1 answer

How to save an image from a custom COCO dataset with its annotations overlaid on top of it

I created a custom COCO dataset. Now suppose I have valid image metadata in image_data. I can display the image and the annotation with import skimage.io as io import matplotlib.pyplot as plt image_directory ='my_images/' image =…
DeltaIV
  • 4,773
  • 12
  • 39
  • 86
1
vote
2 answers

Add new class to dataset mscoco, object detection tensorflow

I would like to add a new class(example: Handgun) to the coco dataset(90 classes) so I would detect 91 different classes. I have this: dataset: 300 image about Handgun labelmap.pbtxt: item { id: 1 name:…
Knowledge
  • 41
  • 2
1
vote
1 answer

How to change the sample image in MS-COCO demo (Image captioning)

I am working on Image captioning, and I found this great tutorial for MS-COCO challenge. MS_COCO Image captioning demo Anyway, I ran the demo and everything went well. Except, when I try to change the sample image (I want to run another images), I…
ananya
  • 879
  • 1
  • 7
  • 14
1
vote
1 answer

Getting a classification on a croped image from tensorflow with inceptionV3 Model

I have a pretrained CocoModel from Tensorflow OD, and retrained it on a kitti dataset. I just wanted to try a classification on a croped Image, but there is no clear documentation what er the names of the tensors. When I tried to use the classify…
Sinksar Wolday
  • 11
  • 2
1
vote
0 answers

Adding a new class to the existing class of Tensorflow Object Detection Model

I'm trying to add a new class to the ms_coco_model (having 90 classes) in tensorflow object detection model and run the training set for the same. I'm using the pre-trained model checkpoint: "ssd_mobilenet_v1_coco_checkpoint" to speed up the…
Ashwini Chhipa
  • 31
  • 4
1
vote
1 answer

Extracting bounding boxes and category labels in MS-COCO dataset

I am working with MS-COCO dataset and I want to extract bounding boxes as well as labels for the images corresponding to backpack (category ID: 27) and laptop (category ID: 73) categories, and store them into different text files to train a neural…
Rahul Bohare
  • 762
  • 2
  • 11
  • 31
0
votes
0 answers

Is it normal to have a higher mean average precision but lower confusion matrix precision-recall in TensorFlow object detection?

I need an explanation about. It is normal to have mean average precision of 0.991 using the TensorFlow object detection evaluation tool with IoU 0.5 and metrics_set: "coco_detection_metrics" in a config file. But I got 0.97 in precision and 0.96 in…
analyZ
  • 11
  • 1
0
votes
0 answers

Modify coco evaluation code to generate class wise accuracies

The cocoeval is a goto evaluation script for calculating mAP across various IoUs. However, it doesn't provide class-wise accuracies. I'd like to use another repository for performing evaluation. However, the code expects two flat files. One with…
theodre7
  • 125
  • 4
0
votes
1 answer

custom load datset error with MSCOCO2017 data

I made my own dataset loader python file to load MSCOCO2017 with caption data this is my coco.py _CITATION = """\ @article{DBLP:journals/corr/LinMBHPRDZ14, author = {Tsung{-}Yi Lin and Michael Maire and Serge J.…
leila_7im
  • 19
  • 2
1
2
3