I'm trying to implement an adversarial loss in keras.
The model consists of two networks, one auto-encoder (the target model) and one discriminator. The two models share the encoder.
I created the adversarial loss of the auto-encoder by setting a keras variable
def get_adv_loss(d_loss):
def loss(y_true, y_pred):
return some_loss(y_true, y_pred) - d_loss
return loss
discriminator_loss = K.variable()
L = get_adv_loss(discriminator_loss)
autoencoder.compile(..., loss=L)
and during training I interleave train_on_batch of discriminator and autoencoder to update discriminator_loss
d_loss = disciminator.train_on_batch(x, y_domain)
discriminator_loss.assign(d_loss)
a_loss, ... = self.segmenter.train_on_batch(x, y_target)
However, I found out that the value of these variables is frozen when the model is compiled. I tried to recompile the model during training but that raise the error
Node 'IsVariableInitialized_13644': Unknown input node
'training_12/Adam/Variable'
which I guess it means i cant recompile during training? any suggestion on how i can inject the discriminator loss in the autoencoder?
Keras model supports multiple outputs. So just include your discirminator into your keras model and freeze the discrminator layers, if the discriminator should not be trained.
The next question would be how to combine autoencoder loss and discriminator loss. Luckily keras model.compile supports loss weights. If autoencoder is your first output and discriminator is your second you could do something like loss_weights=[1, -1]. So a better discriminator is worse for the autoencoder.
Edit: Here is an example, how to implement an Adversary Network:
# Build your architecture
auto_encoder_input = Input((5,))
auto_encoder_net = Dense(10)(auto_encoder_input)
auto_encoder_output = Dense(5)(auto_encoder_net)
discriminator_net = Dense(20)(auto_encoder_output)
discriminator_output = Dense(5)(discriminator_net)
# Define outputs of your model
train_autoencoder_model = Model(auto_encoder_input, [auto_encoder_output, discriminator_output])
train_discriminator_model = Model(auto_encoder_input, discriminator_output)
# Compile the models (compile the first model and then change the trainable attribute for the second)
for layer_index, layer in enumerate(train_autoencoder_model.layers):
layer.trainable = layer_index < 3
train_autoencoder_model.compile('Adam', loss=['mse', 'mse'], loss_weights=[1, -1])
for layer_index, layer in enumerate(train_discriminator_model.layers):
layer.trainable = layer_index >= 3
train_discriminator_model.compile('Adam', loss='mse')
# A simple example how a training can look like
for i in range(10):
auto_input = np.random.sample((10,5))
discrimi_output = np.random.sample((10,5))
train_discriminator_model.fit(auto_input, discrimi_output, steps_per_epoch=5, epochs=1)
train_autoencoder_model.fit(auto_input, [auto_input, discrimi_output], steps_per_epoch=1, epochs=1)
As you can see there is no much magic behind building an Adversary Model with keras.
Unless you decide to go deep in the keras source code, I don't think you can do this easily. Before writing your own adversarial module, you should check the existing works carefully. As far as I know, keras-adversarial is still used by many people. Of course, it only supports old keras versions, e.g. 2.0.8.
Several other things:
be careful when you freeze your model weights. If you first compile a model and then freeze some weights, these weights are still trainable, because when the train function is generated during compiling. So you should freeze weights first then compile.
keras-adversarial does this job in a more elegant way. Instead of making two models, shared weights but freeze some weights in different ways, it creates two train functions, one for each player.
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.
I am training a CNN model for Image Classification using Keras. I am using VGG19 model and a custom dataset with 200 classes and uniformly distributed 90000 training images, 10000 Validation Images and 10000 test images. Even though the training is at 200 epochs, the accuracy is staying at a constant 0.0050. Same with the loss, 5.2988. I am using Kaggle's TPU instance to run this model.
How can I make the model more accurate? Can you suggest any different pretrained models for this purpose?
Your CNN model is behaving like a random model.
I know this because since there are 200 classes, the probability of getting a correct class at random is 1/200=0.0050 which is the accuracy that you have.
This happens when you use tensorflow/keras API instead of sequential()
Since you are using VGG19, if you are trying to use transfer learning, then maybe you have freezed the wrong layer.
If you are using API then you have to do
model = Model(inputs = input_layer, outputs = output_layer) #which is not required in sequential()
print(model.layers) # if you are using API or sequential() this is used to check your layers
Then you have to freeze the layer required as
model.layers[index_of_freeze_layer].trainable = False
If you are not freezing your model layers, then try to use lower learning rate since VGG19 is very sensitive to learning rate. (0.00001 or less depends)
I want to train a model in a sequential manner. That is I want to train the model initially with a simple architecture and once it is trained, I want to add a couple of layers and continue training. Is it possible to do this in Keras? If so, how?
I tried to modify the model architecture. But until I compile, the changes are not effective. Once I compile, all the weights are re-initialized and I lose all the trained information.
All the questions in web and SO I found are either about loading a pre-trained model and continuing training or modifying the architecture of pre-trained model and then only test it. I didn't find anything related to my question. Any pointers are also highly appreciated.
PS: I'm using Keras in tensorflow 2.0 package.
Without knowing the details of your model, the following snippet might help:
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Dense, Input
# Train your initial model
def get_initial_model():
...
return model
model = get_initial_model()
model.fit(...)
model.save_weights('initial_model_weights.h5')
# Use Model API to create another model, built on your initial model
initial_model = get_initial_model()
initial_model.load_weights('initial_model_weights.h5')
nn_input = Input(...)
x = initial_model(nn_input)
x = Dense(...)(x) # This is the additional layer, connected to your initial model
nn_output = Dense(...)(x)
# Combine your model
full_model = Model(inputs=nn_input, outputs=nn_output)
# Compile and train as usual
full_model.compile(...)
full_model.fit(...)
Basically, you train your initial model, save it. And reload it again, and wrap it together with your additional layers using the Model API. If you are not familiar with Model API, you can check out the Keras documentation here (afaik the API remains the same for Tensorflow.Keras 2.0).
Note that you need to check if your initial model's final layer's output shape is compatible with the additional layers (e.g. you might want to remove the final Dense layer from your initial model if you are just doing feature extraction).
This is my predict function. is there anything wrong with this? Predictions are not stable, everytime I run on same data, I get different predictions.
def predict(model, device, inputs, batch_size=1024):
model = model.to(device)
dataset = torch.utils.data.TensorDataset(*inputs)
loader = torch.utils.data.DataLoader(
dataset,
batch_size=batch_size,
pin_memory=False
)
predictions = []
for i, batch in enumerate(loader):
with torch.no_grad():
pred = model(*(item.to(device) for item in batch))
pred = pred.detach().cpu().numpy()
predictions.append(pred)
return np.concatenate(predictions)
As Usman Ali suggested, you need to set your model to eval mode by calling
model.eval()
before your prediction function.
What eval mode does:
Sets the module in evaluation mode.
This has any effect only on certain modules. See documentations of particular modules for details of their behaviors in training/evaluation mode, if they are affected, e.g. Dropout, BatchNorm, etc.
When you finish your prediction and wish t continue training, don't forget to reset your model to training mode by calling
model.train()
There are several layers in models that may introduce randomness into the forward pass of the net. One such example is the dropout layers. A dropout layer "drops" p percent of its neurons at random to increase model's generalization.
Additionally, BatchNorm (and possibly other adaptive normalization layers) keeps track of the statistics of the data and therefore has a different "behavior" in train mode or in eval mode.
You have defined the function, but you haven't trained the model. The model randomizes predictions before it is trained, which is why yours are inconsistent. If you set up an optimizer with a loss function, and run over multiple epochs the predictions will stabilize. This link may help: https://pytorch.org/tutorials/beginner/blitz/cifar10_tutorial.html. Look at sections 3 and 4
I'm quite new to Neural Networks, which is why I've decided to use Tflearn because it is quite intuitive.
However I couldn't find an answer to my question. The tflearn documentation gives the following example for letting a deep neural network predict something:
network = ...
model = DNN(network)
model.load('model.tflearn')
model.predict(X)
I've inserted some batch normalization layers inside the network because my model seemed to be overfitting. Will model.predict() automatically "tell" the batch normalization layer not to behave like in a training phase? Or do I have to specify this somehow with
tflearn.config.is_training (is_training=False, session=None)?
If yes, do you know where I should put this line? And how do I create my session so that it does the same like my code. At the moment it basically looks like the example at tflearn.org:
net = tflearn.input_data(shape=[None, 784])
net = tflearn.fully_connected(net, 64)
net = tflearn.dropout(net, 0.5)
net = tflearn.fully_connected(net, 10, activation='softmax')
net = tflearn.regression(net, optimizer='adam',
loss='categorical_crossentropy')
model = tflearn.DNN(net)
model.fit(X, Y)
except that I use a batch normalization layer and I use the neural network for function approximation. Unfortunately I cannot post my code right now,since it's on another Computer but it really is basically the same.
Could someone help me with this question?
Thanks in advance!
You need to set tflearn.is_training to True or False when you are training and predicting, and tflearn will take care of the rest. Once you define your model, you can train it by:
with tf.Session() as sess:
tflearn.is_training(True, session=sess)
model.fit(X, Y)
and then predict using:
with tf.Session as sess:
tflearn.is_training(False, session=sess)
model.predict(X)