coursera-ai-for-medicine-specialization/AI for Medical Diagnosis/Week 3

Course Q&A AI For Medicine AI for Medical Diagnosis
1

In the final assignment of week 3, how did he preprocess the data and convert it into .h5 file?

2

@ANKUR_DHANGAR

The convertion of saved model to h5 format is done by calling model.save_weights() and passing in the path and file name to save the weights to with an h5 extension.

Regards
DP

3

@Deepti_Prasad
base_dir = HOME_DIR + “processed/”
with open(base_dir + “config.json”) as json_file:
config = json.load(json_file)

Get generators for training and validation sets

train_generator = util.VolumeDataGenerator(config[“train”], base_dir + “train/”, batch_size=3, dim=(160, 160, 16), verbose=0)
valid_generator = util.VolumeDataGenerator(config[“valid”], base_dir + “valid/”, batch_size=3, dim=(160, 160, 16), verbose=0)

We need to perform these line of codes first before saving right? so what will be in json file ? I can’t save the weights before fitting the data into the model. If you could provide me the code, it will be of great help.

Thanks,
Ankur