I want to take a single Conv2D layer in Keras and give it a single image so I can see the output activations. (I'm doing some custom layer research)
In other words, I do not want to use the fit function, nor do back prop, and no batch of images.
How is this done.
You define a Model instance which has the layer of your interest as an output (a bit similar to what you would do with an autoencoder to get the encoding) and you call model.predict() with a single image.
Related
We want to train our model on varying input dimensions. Every input in a given batch and across batches has different dimensions.
We cannot resize our input (since we’ll lose our microscopic features). Now, since we cannot resize our input, converting them into batches of numpy array becomes impossible. In order to handle this now I have made the list for the input and each list of element contained (height, width, 1). Height is variable size and width is constant.
Sometime my input excessively large. In order to do that I have plan to use model.fit_generator(). In this, We find the max height and width of input in a batch and pad every other input with zeros so that every input in the batch has an equal dimension. Now we can easily convert it to a numpy array or a tensor and pass it to the fit_generator(). The model automatically learns to ignore the zeros and learns features from the intended portion from the padded input. This way we have a batch with equal input dimensions but every batch has a different shape (due to difference in max height and width of input across batches).
Now until here, I described the things what I have learned and what I have plan to do with variable input data. But I am stuck with the following confusions:
1- I have plan to use CNN first and then LSTM on that. I am using tensorflow keras. There, we have the facility of padding and masking . However, As for as I know that LSTM can work on masking and padding ignore 0-padded values. However, I am concerned about the CNN (does CNN ignores 0-padded values), because my padded input will first feed to CNN. I have seen some discussion in the following links:
How to apply masking layer to sequential CNN model in Keras?
https://github.com/keras-team/keras/issues/411
In these link, they mentioned that Unfortunately masking is not yet supported by the Keras Conv layers. However, now we can see alot of development and advancements specifically in the form of tensorflow Keras. So I am wondering that now tensorflow keras can support masking input?
2- To use the generator, we can use custom keras generator. For that I went through a vary good tutorial. I made the mind to use this. But I am wondering is there any advance built-in facility in tensorflow keras to use generator and save me to write custom keras generator?
❓Question
I'm trying to convert a pytorch model to coreml. The model was based on yolov5.
Here is a netron view our our exported coreml model.
Currently, the architecture has 3 outputs. You can see one of the outputs in the screenshot, number '740'.
However, we want a different output from coreml. We need to get the output before the reshapeStatic and transpose layers. So in this image you can see that we need the last convolution layer instead of 740.
Those reshapeStatic and transpose layers were added by the process which convert the net to coreML, they are not organic layers of yolov5.
Is there any way we can do the conversion to coreml differently in order to have more control over which layers are output? For example, can we have control over the output layers in the sample code below:
model = ct.convert(
traced_model,
inputs=[ct.ImageType(name="input_1", shape=example_input.shape)],
classifier_config = ct.ClassifierConfig(class_labels) )
Alternatively, is there a way where we can choose at runtime which values to pull out of the coreml model? For example, is there a way to specify in the code below which layers we want to output?
img = load_image(img_path, resize_to=(img_size, img_size))
//can we specify here which layers to output?
coreml_out_dict = model.predict({'image': img})
Thanks!
Could anyone explains for me the differences between Time-Distributed Layers (from Keras Wrapper) and ConvLSTM-2D (Convolutional LSTM), for purposes, usage, etc.?
Both applies to a sequence of data.
Time Distributed is a very straightforward layer wrapper which only applies a layer (usually dense layer) on each time point. You need it when you need to change the shape of output tensor, especially the dimension of features, instead of sample size and time step.
ConvLSTM2D, is much more complex. You need to understand cnn and rnn layer first, where LSTM is one of most popular rnn. LSTM itself is applied on a sequence of of tensor, which is used for NLP, time series and for each time step the input is 1-dimension. cnn, the conv part, is usually used to learn from image, which is 2-dimension but don't have a sequence (time step). Combined together, convLSTM is used to learn image in a sequence, like video.
I've implemented a neural network using Keras. Once trained and tested for final test accuracy, using a matrix with a bunch of rows containing features (plus corresponding labels), I have a model which I should be able to use for prediction.
How can I feed a single unseen example, meaning a feature vector to the model, to obtain a class prediction?
I've looked at their documentation here but could not find a method for it.
What you want is the predict method, it takes a batch of input samples and produces predictions, which are the outputs computer by your network. To feed a single example you can just put it inside a numpy ndarray wrapper.
I am looking for a way to implement the following network structure (currently using Keras, might be theano however):
Assume we're given some simple network, but it is not possible to compute the desired loss based on this output directly, instead another operation is needed and the loss will be defined based on the output of this operation. However, this operation does not only need the output of the network but the full network object (eg its gradient).
How can this be done? I think the operation could be performed either in a custom layer on top of the network or in a custom loss function - but for neither version I see a way to access the full network. Any suggestions?
Assume we're given some simple network, but it is not possible to compute the desired loss based on this output directly, instead another operation is needed and the loss will be defined based on the output of this operation. However, this operation does not only need the output of the network but the full network object (eg its gradient).
Say, you have the following model.
import keras.applications.vgg16 as vgg16
model = vgg16.VGG16(weights='imagenet')
model.summary()
For example, now you want to delete the last layer of this model which is actually predicts a category (a vector of length 1000 because imagenet has 1000 categories) for the input image.
# Remove last Linear/Dense layer.
model.layers.pop()
model.outputs = [model.layers[-1].output]
model.layers[-1].outbound_nodes = []
model.summary()
Now, lets add a linear layer (with output size 10) to this model and use the output of the modified neural network model.
model.add(Dense(10, activation='softmax'))
model.summary()
You will get a vector (of length 10) as an output from this model.
You can compile and train the model using model.compile() and model.fit() functions. You can set what type of loss function you want to use to train the model.