GitHub / zggg1p / fault-detect
This project is to classify the state of the welding chip. Considering the complexity of the problem, only two classifications are carried out, namely normal and abnormal. Through the test of fully connected network, convolutional neural network and Fine-tuning Of Google Net, we found that fine-tuning of Google Net had the best effect, reaching the highest score of 70 out of a full score of 80.
JSON API: http://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zggg1p%2Ffault-detect
PURL: pkg:github/zggg1p/fault-detect
Stars: 5
Forks: 1
Open issues: 0
License: None
Language: Python
Size: 38.1 KB
Dependencies parsed at: Pending
Created at: almost 4 years ago
Updated at: about 3 years ago
Pushed at: almost 4 years ago
Last synced at: over 1 year ago
Topics: deep-learning, fault-detection, neural-network, transfer-learning