Tech
Fine-tuning EfficientNetB0 for 104 flower classes: validation vs held-out test scores, honestly
I built a GPU transfer-learning workflow for 104-class flower recognition and tried to report it honestly, including the gap between validation and held-out test scores.
Repo: https://github.com/officialpm/flower-classification
This is an evaluated model workflow, not a deployed flower-identification product.
The approach
Verify TFRecord feature names, counts and that all 104 classes appear in training and validation.
Load an ImageNet-pretrained Efficien...
Read the full discussion on Dev.to
This article was aggregated from Dev.to. Click to join the conversation.
View on Dev.to