How to use different base network

[achintacsgit]

Sir , i want to use different base network, can you please tell me the procedure I know you use transfer learning , but can i use pre train weights of a simple image classification model

[StephenRUK]

Hi, you should look at the author's article on Medium and the notebook for training. You can replace the base network with your own easily, see nn_base in the training notebook.

[achintacsgit]

Can you give the original author github link Previous link is not working now

[StephenRUK]

You can find the notebook in this repository. https://github.com/RockyXu66/Faster_RCNN_for_Open_Images_Dataset_Keras/blob/master/frcnn_train_vgg.ipynb

[achintacsgit]

Thank you I can replace base network easily , can you tell the procedure for generating the pre train weights for that base network

[StephenRUK]

You can use pretrained weights for common models e.g. VGG16, ResNet or such. See the Keras docs for available models with ImageNet weights, if you wish to use them https://keras.io/applications/

[achintacsgit]

Can i use pre train weights of other than these network

[StephenRUK]

You can use any network you want. I think you need to do some research in general about transfer learning or finetuning of existing networks. It is not specific to this model or GitHub repository.

[achintacsgit]

can i train whole network without using transfer learning please reply

[StephenRUK]

Yes you can train the whole network, but it makes no sense to train a whole VGG or ResNet model from scratch. This isn't a support forum & I'm not even part of this repo 😉 do check out an article such as this https://www.learnopencv.com/keras-tutorial-transfer-learning-using-pre-trained-models/

[achintacsgit]

Thank you sir

[DTW1004]

can you please tell me how to get these four file for train?

[devendraswamy]

can you please tell me how to get these four file for train?

you just create a "model" folder in base_path then reaming files are automatically stored