I am studying deep learning and trying to implement it using CAFFE- Python. can anybody tell that how we can assign the weights to each node in input layer instead of using weight filler in caffe?
There is a fundamental difference between weights and input data: the training data is used to learn the weights (aka "trainable parameters") during training. Once the net is trained, the training data is no longer needed while the weights are kept as part of the model to be used for testing/deployment.
Make sure this difference is clear to you before you precede.
Layers with trainable parameters has a filler to set the weights initially.
On the other hand, an input data layer does not have trainable parameters, but it should supply the net with input data. Thus, input layers has no filler.
Based on the type of input layer you use, you will need to prepare your training data.
Related
If the pretrained model such as Resnet101 were trained on ImageNet dataset, then I change some layers inside it. Can I still be able to use the pretrained model on different ABC dataset?
Lets say This is ResNet34 Model,
It is pretrained on ImageNet and saved as ResNet.pt file.
If I changed some layers inside it, lets say I made it more deeper by introducing some layers in conv4_x (check image)
model = Resnet34() #I have changes some layers inside this ResNet34()
optimizer = optim.Adam(model.parameters(), lr=0.00005)
model.load_state_dict(torch.load('Resnet.pt')['state_dict']) #This is pretrained model of ResNet before some changes
optimizer.load_state_dict(torch.load('Resnet.pt')['optimizer'])
Can I do this? or there are anyother method?
You can do anything you like - the question is: would it be better than training from scratch?
Here are a few issues you might encounter:
1. A mismatch between weights saved in ResNet.pt (the trained weights of the original ResNet18) and the state_dict of your modified model.
You would probably need to manually make sure that the old weights are correctly assigned to the original layers and only the new layer is not initialized.
2. Initializing the weights of the new layer.
Since you are training a resNet - you can take advantage of the residual connections and init the weights of the new layer such that it would initially make no contribution to the predicted value and only pass the input directly to the output via the residual link.
Say we train a multilayer NN in tensorflow for a regression task (i.e. multi input and multi output case). Then we have new instances and we apply the trained model and of course we get the corresponding outputs. Is there a way to backpropagate the outputs and reconstruct the inputs in tensorflow in an easy/efficient manner? What I am thinking is to then use the difference of the original and the reconstructed inputs of the new instances as a QC measure i.e. if the reconstructed inputs are not close enough to the originals then we have a problem etc. I hope I am making myself clear.
No, unfortunately you cannot take a trained model and try to get the corresponding input. The reason for this is that you have infinite possible solutions for each output.
Furthermore, backpropagation is not passing an output backwards through the network. Its the idea of determining what parameters in the model are contributing to what extent to loss function. This will not give the inputs to these hidden layers, but the extent at which the weights affected your decision.
I have trained a fully convolutional neural network with Keras. I have used the Functional API and have defined the input layer as Input(shape=(128,128,3)), corresponding to the size of the images in my training set.
However, I want to use the trained model on images of variable sizes (which should be ok because the network is fully convolutional). To do this, I need to change my input layer to Input(shape=(None,None,3)). The obvious way to solve the problem would have been to train my model directly with an input shape of (None,None,3) but I use a custom loss function where I need to specify the size of my training images.
I have tried to define a new input layer and assign it to my model like this :
from keras.engine import InputLayer
input_layer = InputLayer(input_shape=(None, None, 3), name="input")
model.layers[0] = input_layer
This actually changes the size of the input layers accordingly but the following layers still expect (128,128,filters) inputs.
Is there a way to change all of the inputs values at once ?
Create a new model, exactly the same, except for new input shape; and tranfer weights:
newModel.set_weights(oldModel.get_weights())
If anything goes wrong, then it might not be fully convolutional (ex: contains a Flatten layer).
Here is what I wanna do:
I want to use some transfer learning techniques to deal with sequence problems:
First use dataset_1 to train a lstm model,
Second insert another lstm layer before the output layer,
and then use dataset_2 to only train the newly adding layer, and the variables of other layers are imported from the first training stage and remain unchanged
here's the problem, the existing methods all require the variable name of weight/bias when restoring the pre-trained model. And I want to use the fuction tf.contrib.rnn.MultiRNNCell(*) in my code.However, the function is a black box and unable to obtain concrete variable names. How can I realize the idea?
I fine tunes vgg-16 for binary classification. I used sigmoidLoss layer as the loss function.
To test the model, I coded a python file in which I loaded the model with an image and got the output using :
out = net.forward()
My doubt is should I take the output from Sigmoid or SigmoidLoss layer.
And What is the difference between 2 layers.
My output will actually be the probability of input image being class 1.**
For making predictions on test set, you can create a separate deploy prototxt by modifying the original prototxt.
Following are the steps for the same
Remove the data layer that was used for training, as for in the case of classification we are no longer providing labels for our data.
Remove any layer that is dependent upon data labels.
Set the network up to accept data.
Have the network output the result.
You can read more about this here: deploy prototxt
Else, you can add
include {
phase: TRAIN
}
to your SigmoidWithLoss layer so that it's not used when testing the network. To make predictions, simply check the output of Sigmoid layer.
SigmoidWithLoss layer outputs a single number per batch representing the loss w.r.t the ground truth labels.
On the other hand, Sigmoid layer outputs a probability value for each input in the batch. This output does not require the ground truth labels to be computed.
If you are looking for the probability per input, you should be looking at the output of the Sigmoid layer