Regression prediction of fabric density based on deep learning
In the actual process of fabric design and quality detection,manual detection of fabric density usually requires a lot of time and human resouce,and the efficiency is very low.In order to solve the problem,a research method based on deep learning for fabric dendity regression pre-diction was proposed.Firstly,based on transfer learning,the improved VGG19 was trained,and the convolutional layers and fully connected layers of the network were improved by adding SVD matrix decomposition to reduce the calculation time of the fully connected layers.Secondly,the classification layer was removed,and the output of the fully connected layer was used as the final model output result.During the training process,the mean square error loss function was selected,and a comparative experiment and result analysis were conducted using fabrics provided by a cer-tain textile enterprise as the dataset.The results show that compared to traditional methods,the proposed method is more intelligent,with a fabric density calculation error of about 5％and an accuracy of 95.5％,which has certain feasibility.
万方数据
维普
