June 2019
Intermediate to advanced
308 pages
7h 21m
English
We used MobileNet v1 for the second use case. The following diagram presents the architecture of the model:

To train and validate the model on the acne dataset, we need to run the retrain_CNN.py file available in the chapter's code folder named use-case-2 subfolder. To train and test the model, we need to just run the following in the Command Prompt.
python retrain_CNN.py \--output_graph=trained_model_mobilenetv1/retrained_graph.pb \--output_labels=trained_model_mobilenetv1/retrained_labels.txt \--architecture mobilenet_1.0_224 \--image_dir= dataset-Acne-reduced
The final two parameters of MobileNet v1 training are compulsory, ...
Read now
Unlock full access