Message Boards Message Boards


Application of ResNet-50 to 17 category flower data set

Posted 1 month ago
0 Replies
2 Total Likes

Aim: Is to apply ResNet-50 to classify different categories of flowers Image Collage of flower data set

Methods: This data set of the University Oxford ( contains n = 1360 flowers of 17 categories of various images sizes. We apply the ResNet-50 network architecture and evaluate accuracy with and without using a rejection rate. Training data set contains 1088 flowers and the test set 271 flowers.

Results: An illustration of the performance of this network architecture is given here:Comparison of actual and predicted flowers

The accuracy without a rejection threshold is 91.5% (+/- 1.7%) and increases to 96.6% (+/-1.2%) with a rejection threshold of 14.4%. Classifier measurements without and with rejection rate

Discussion: This network architecture achieves a high accuracy, other architectures like Inception V3, Squeeze-and-Exitation, VGG 16 may even increase performance. Training was done on a notebook without a GPU and is fast for ResNet-50. More complex network architectures with larger amount of parameters may perform better, in this case we suggest to use a GPU. A MATHEMATICA 12 notebook with more details is attached.

Reply to this discussion
Community posts can be styled and formatted using the Markdown syntax.
Reply Preview
or Discard

Group Abstract Group Abstract