2023
DOI: 10.1016/j.compgeo.2022.105207
|View full text |Cite
|
Sign up to set email alerts
|

An efficient classification system for excavated soils using soil image deep learning and TDR cone penetration test

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
5
1

Relationship

0
6

Authors

Journals

citations
Cited by 9 publications
(2 citation statements)
references
References 29 publications
0
2
0
Order By: Relevance
“…The initial learning rate of VGG16 and ResNet18 are both 0.0001. 32 The VGG16 and ResNet18 model network architecture details are provided in the Supporting Information. Using the strategy of natural learning rate reduction, 33−35 it can be seen that the loss value of the VGG16 model basically remains stable after undergoing 60 epoch training with no significant increase in accuracy.…”
Section: Machine Learning Resultsmentioning
confidence: 99%
See 1 more Smart Citation
“…The initial learning rate of VGG16 and ResNet18 are both 0.0001. 32 The VGG16 and ResNet18 model network architecture details are provided in the Supporting Information. Using the strategy of natural learning rate reduction, 33−35 it can be seen that the loss value of the VGG16 model basically remains stable after undergoing 60 epoch training with no significant increase in accuracy.…”
Section: Machine Learning Resultsmentioning
confidence: 99%
“…As shown in Figure b, the change values of training loss and validation loss are in the model training process. The initial learning rate of VGG16 and ResNet18 are both 0.0001 . The VGG16 and ResNet18 model network architecture details are provided in the Supporting Information.…”
Section: Results and Discussionmentioning
confidence: 99%