I am trying to dynamically modify the neural network architecture(e.g, add/delete layer...) and hyperparameter during the training period on Tensorflow.(e.g.,control_func(#layer,#neuron,learning_rate...)) However, I have no idea how to implement it in the code. Could anyone can provide some reference, insight, or tutorial? Thanks a lot!
Related
I want to retrain a pre-trained model with two classes of the same object with and without an extra part on the object. So it has to recognize a detail.
I am a beginner in this area and couldn't find a solution, maybe you even know a better solution than working with TensorFlow.
I hope you can help me and I am happy about any idea. Thank you in advance.
I'm a user of Tensorflow Object Detection API. I use it a lot to train models like Faster-RCNN on my images. From what I understand, there is a backbone network (in my experiences, ResNet) used to extract features.
I would like to re-use the weight of this specific network, but when I save my model, it's a Faster RCNN model and, even after hours in the documentation and in the source files, I don't see how to isolate the weight of the backbone network.
Is something somebody else already has realized before ? Or is Tensorflow OD API not the right tool for what I need ?
Thank you for your help or advises !
I have a problem where I need to record function trace for a neural network model.
I need to create a task graph of a neural network model written in tensorflow. I think adding logs in a tensorflow code first can solve my problem. However it is very time consuming. What can be the best way to solve this. Does tensorflow provide any facility to accomplish this task Please help.
You can use the tensorboard. I strongly recommend it. Because you can find the very detail of your model.
writer = tf.summary.FileWriter(your-dir, sess.graph)
And open it in the Chrome.
Here is the result from tensorboard. hyperlinks.
As we saw, the loss has decreased and the Accuracy (both train and test) has increased. Hence, the model has already been trained successfully.
However, Distribution of parameters, weights/bias doesn't change (might change little), while the bias change a lot.
Could someone help me to explain what causes this ?
I knew this is normal result but why?
Thank you!
Edition: Could someone share the experience of training Deep Neural network?
what will be the real expectation of changing for parameters in successful trained model?
Thank you.
I recently followed this tutorial to train my own image classifier
https://codelabs.developers.google.com/codelabs/tensorflow-for-poets/?utm_campaign=chrome_series_machinelearning_063016&utm_source=gdev&utm_medium=yt-desc#0
for those who don't know it allows the retraining of a MobileNet network own your own custom images/categories. I have had sucess training networks on my own images using tensorflow but would like to go further now.
I now would like to generate a class activation map (CAM) for images inputted into the model. I have read you need your convolution neural network to have a Global Average Pooling layer for CAM's to work and am thinking the MoblieNet network does not have that. Is it possible to generate CAM's from the network I have already trained or will I need to retrain using a different network like VGG16??
If it is possible could someone point me in the right direction on how to generate CAM's? If not could someone point me in the right direction on how to retrain a different network with my own images that will allow for CAM's and how to creat CAM's on these networks??
Sorry for the vague nature of the question. I am by no means that familiar and/or trained regarding computer science but am interested to learn more. Your help would be greatly appreciate. Please contact me with further inquires about my question if needed. Hope to hear from you soon.
Thanks!