search

asmaa4may / DeTraC_COVId19

Classification of COVID-19 in chest X-ray images using DeTraC deep convolutional neural network
MIT License
2 stars 0 forks source link

where is the convo5_block3_1_conv file #8

Open mprabhakar1744 opened 2 years ago

mprabhakar1744 commented 2 years ago

i am interested to your code and run your code but i m not found the convo5_block3 file please give me this file ,

from tensorflow.keras.models import load_model

loading the fine-tuning model

model=load_model('..................../conv5_block3_1_conv.hdf5')

asmaa4may commented 2 years ago

this code is for training the based model based on fine-tuning strategy, which means gradually train more layers by tuning the learning parameters until a significant performance boost is achieved Here, I select Resnet50 as a pre-trained model and define some top layers to train #define the fine-tuning layers fine_tuning_layers=[176,171,168,165] At the checkpoint, I save the best model 'hdfs' with the significant weights for later use to evaluate the model in a new task. in the for loop, for i in fine_tuning_layers: the model using the first fine_tuning_layers= 176 which is a dense layer and saving the model with the name of its layer, after completing 100 eps, the training is transferred to the next number in the list (171) and so on. you ask where is conv5_block3_1_conv.hdf5 ? You have to train the model up to layer [165] to save the model with its name

mprabhakar1744 commented 2 years ago

Thx for the shareing information

On Tue, 11 Jan, 2022, 6:40 PM Asmaa Abbas, @.***> wrote:

this code is for training the based model based on fine-tuning strategy, which means gradually train more layers by tuning the learning parameters until a significant performance boost is achieved Here, I select Resnet50 as a pre-trained model and define some top layers to train

define the fine-tuning layers fine_tuning_layers=[176,171,168,165]

At the checkpoint, I save the best model 'hdfs' with the significant weights for later use to evaluate the model in a new task. in the for loop, for i in fine_tuning_layers: the model using the first fine_tuning_layers= 176 which is a dense layer and saving the model with the name of its layer, after completing 100 eps, the training is transferred to the next number in the list (171) and so on. you ask where is conv5_block3_1_conv.hdf5 ? You have to train the model up to layer [165] to save the model with its name

— Reply to this email directly, view it on GitHub https://github.com/asmaa4may/DeTraC_COVId19/issues/8#issuecomment-1009950012, or unsubscribe https://github.com/notifications/unsubscribe-auth/ALMTV6ANGDPPTVI6TH5NEDDUVQT5TANCNFSM5LVKX73Q . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub.

You are receiving this because you authored the thread.Message ID: @.***>