0

I have class which has slightly different features from the other class: ex - This image has buckle in it (consider it as a class) https://6c819239693cc4960b69-cc9b957bf963b53239339d3141093094.ssl.cf3.rackcdn.com/1000006329245-822018-Black-Black-1000006329245-822018_01-345.jpg

But This image is quite similar to it but has no buckle : https://sc01.alicdn.com/kf/HTB1ASpYSVXXXXbdXpXXq6xXFXXXR/latest-modern-classic-chappal-slippers-for-men.jpg

I am little confused about which model to use in these kind of cases which actually learns pixel to pixel values.

Any thoughts will be appreciable. thanks !!

I have already tried Inception,Resnet etc models.

With a less volume train data (300-400 around each class) can we reach a good recall/precision/F1 score.

Gaurav Gola
  • 123
  • 1
  • 1
  • 10

1 Answers1

0

You might want to look into transfer learning due to the small dataset, what you can do is use a transferred ResNet model to work as a feature extractor and try a YOLO(You only look once) algorithm on it, look through each window(Look Sliding window implementation using ConvNets) to obtain a belt buckle and based on that you can classify the image.

Based on my understanding of your dataset, to do the above approach though you will need to re-annotate your dataset as per the requirements of YOLO algorithm.

To look at an example of the above approach, visit https://mc.ai/implementing-yolo-using-resnet-as-feature-extractor/

Edit If you have XML annotated Dataset and need to convert it to csv to follow the above example use https://github.com/datitran/raccoon_dataset

Happy modelling.

anand_v.singh
  • 2,768
  • 1
  • 16
  • 35
  • Hey, Is their any way to train the model with xml files that were generated while training yolov3. – Gaurav Gola Jan 29 '19 at 05:43
  • Pandas can read XML, but what exactly is it that you are looking for, your comment is a bit unclear @GauravGola ? – anand_v.singh Jan 29 '19 at 06:19
  • I have xml file prepared for yolo model. Can i use the same xml files for training resnet yolo? – Gaurav Gola Jan 29 '19 at 19:55
  • If you have annotated it for yolo, then yes you can use it for resnet YOLO, In the link that I provided they are using the dataset that was annotated for YOLO and have trained there Resnet YOLO model on it. – anand_v.singh Jan 30 '19 at 03:24
  • As far as my understanding of the repo they have not given any direct way of training model from xml files as given my yolo something like this : flow --model cfg/tiny-yolo-voc-3c.cfg --load bin/tiny-yolo-voc.weights --train --annotation train/Annotations --dataset train/Images – Gaurav Gola Jan 30 '19 at 06:07
  • So your problem is that you have XML's and the above model requires CSV, use this [xml_to_csv](https://github.com/datitran/raccoon_dataset) and find xml_to_csv.py that should sort you out. – anand_v.singh Jan 30 '19 at 06:27
  • Thanks! i got it. Although it requires high computation power. I am unable to train it on local or colab. If possible, please suggest any other method. – Gaurav Gola Jan 30 '19 at 10:54
  • @GauravGola It is always a tradeoff between accuracy, computation and speed, you have to choose what works for you, If you want more complex feature detection, you will need more parameters thus more computation. – anand_v.singh Jan 30 '19 at 10:59
  • Yes,Thats true. Thanks for your help. :) – Gaurav Gola Jan 30 '19 at 11:03