ValueError: Cannot create group in read only mode. about brain-tumor-segmentation HOT 5 OPEN

You got any solution for ValueError? I am with same error please help.
Thanks

from brain-tumor-segmentation.

I got any solution for ValueError.
If you want to train the model from scratch, the parameter load_model_resume_training shoud be None.
If you train the model from the pretrained weights provided by @Issam28, the parameter load_model_resume_training shoud be pretrained weights filepath without extension and code

self.model =load_model(load_model_resume_training,custom_objects={'gen_dice_loss': gen_dice_loss,'dice_whole_metric':dice_whole_metric,'dice_core_metric':dice_core_metric,'dice_en_metric':dice_en_metric})

change to

self.model = self.load_model(load_model_resume_training)
sgd = SGD(lr=0.08, momentum=0.9, decay=5e-6, nesterov=False)
self.model.compile(loss=gen_dice_loss, optimizer=sgd, metrics=[dice_whole_metric,dice_core_metric,dice_en_metric])

from brain-tumor-segmentation.

I got any solution for ValueError.
If you want to train the model from scratch, the parameter load_model_resume_training shoud be None.
If you train the model from the pretrained weights provided by @Issam28, the parameter load_model_resume_training shoud be pretrained weights filepath without extension and code

self.model =load_model(load_model_resume_training,custom_objects={'gen_dice_loss': gen_dice_loss,'dice_whole_metric':dice_whole_metric,'dice_core_metric':dice_core_metric,'dice_en_metric':dice_en_metric})

change to

self.model = self.load_model(load_model_resume_training)
sgd = SGD(lr=0.08, momentum=0.9, decay=5e-6, nesterov=False)
self.model.compile(loss=gen_dice_loss, optimizer=sgd, metrics=[dice_whole_metric,dice_core_metric,dice_en_metric])

The load_model function needs '{ }.json', but I didn't find it

from brain-tumor-segmentation.

I got any solution for ValueError.
If you want to train the model from scratch, the parameter load_model_resume_training shoud be None.
If you train the model from the pretrained weights provided by @Issam28, the parameter load_model_resume_training shoud be pretrained weights filepath without extension and code

self.model =load_model(load_model_resume_training,custom_objects={'gen_dice_loss': gen_dice_loss,'dice_whole_metric':dice_whole_metric,'dice_core_metric':dice_core_metric,'dice_en_metric':dice_en_metric})

change to

self.model = self.load_model(load_model_resume_training)
sgd = SGD(lr=0.08, momentum=0.9, decay=5e-6, nesterov=False)
self.model.compile(loss=gen_dice_loss, optimizer=sgd, metrics=[dice_whole_metric,dice_core_metric,dice_en_metric])

The load_model function needs '{ }.json', but I didn't find it

Hello, hope it's not too late.
The json file can be produced by function save_model in object Train.

from brain-tumor-segmentation.

Hello, I used your solution(change self.model) and ran into this problem as well:No such file or directory: '*******/pretrained_weights/ResUnet.epoch_02.hdf5.json'
I don't understand you said "The json file can be produced by function save_model in object Train.", Can you elaborate a bit more on how to solve this problem?
Thank you very much! I am looking forward to your reply.

from brain-tumor-segmentation.