Faster_RCNN_for_Open_Images_Dataset_Keras
Faster_RCNN_for_Open_Images_Dataset_Keras copied to clipboard
RockyXu66
How to use different base network
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
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.
Can you give the original author github link Previous link is not working now
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
Thank you I can replace base network easily , can you tell the procedure for generating the pre train weights for that base network
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/
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.
can i train whole network without using transfer learning please reply
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/
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
