Detect the defect on the fabrics using CNNs
Published:
- Who: the group project (2 people including myself)
- I was in charge of writing proposal, all codes, writing final report, and making PPT slides.
- When: Jan. 2020 - Mar. 2020
- Where: ECE271B (Statistical Learning II) group project
- What: Building the deep learning model to classify the dataset as Pass/Fail - Binary classification
- Dataset: AITEX company open source dataset.
- How: Python. OpenCV. TensorFlow 2.x. TFRecord. Data augmentation (image flipping, rotation, translation). From vanilla CNNs to Inception-like CNN models without pre-trained weights.
- Learn: TensorFlow 2.x usage. TFRecord. Inception-like CNN structure building. Data augmentation (manually).
- The repository is now opened for the public.
- It will be back to the private in Aug. 2021. Please contact me if you want to see in detail.
- Featured slides
