I have an image with 8 channels.I have a conventional algorithm where weights are added to each of these channels to get an output as '0' or '1'.This works fine with several samples and complex scenarios. I would like implement the same in Machine Learning using CNN method.
I am new to ML and started looking out the tutorials which seem to be exclusively dealing with image processing problems- Hand writing recognition,Feature extraction etc.
http://cv-tricks.com/tensorflow-tutorial/training-convolutional-neural-network-for-image-classification/
https://leonardoaraujosantos.gitbooks.io/artificial-inteligence/content/neural_networks.html
I have setup the Keras with Theano as background.Basic Keras samples are working without problem.
What steps do I require to follow in order achieve the same result using CNN ? I do not comprehend the use of filters,kernels,stride in my use case.How do we provide Training data to Keras if the pixel channel values and output are in the below form?
Pixel#1 f(C1,C2...C8)=1
Pixel#2 f(C1,C2...C8)=1
Pixel#3 f(C1,C2...C8)=0 .
.
Pixel#N f(C1,C2...C8)=1
I think you should treat this the same way you use CNN to do semantic segmentation. For an example look at
https://people.eecs.berkeley.edu/~jonlong/long_shelhamer_fcn.pdf
You can use the same architecture has they are using but for the first layer instead of using filters for 3 channels use filters for 8 channels.
For the loss function you can use the same loos function or something that is more specific for binary loss.
There are several implementation for keras but with tensorflow
backend
https://github.com/JihongJu/keras-fcn
https://github.com/aurora95/Keras-FCN
Since the input is in the form of channel values,that too in sequence.I would suggest you to use Convolution1D. Here,you are taking each pixel's channel values as the input and you need to predict for each pixel.Try this
eg :
Conv1D(filters, kernel_size, strides=1, padding='valid')
Conv1D()
MaxPooling1D(pool_size)
......
(Add many layers as you want)
......
Dense(1)
use binary_crossentropy as the loss function.
Related
ist there a code example on how to do linear regression on a custom image dataset? I have only found examples using the CIFAR dataset...
Here's a guide as to how you can make minor modifications to the MNIST example to suit your needs. There may be some fiddling.
Store your data locally as images in a directory under different categories:
train/cats/abc.jpg
train/cats/def.jpg ...
train/dogs/ghi.jpg ...
train/mouse/jkl.jpg ...
analogously for validation
val/cats/...
val/dogs/...
The filenames don't matter, just the directories as these will be use to identify the category.
Update the MNIST example to use the ImageFolderDataset for your test and train data
train_data = mx.gluon.data.vision.datasets.ImageFolderDataset(training_path)
val_data = mx.gluon.data.vision.datasets.ImageFolderDataset(val_path)
Note, you may need to apply a transform to your images.
Replace the network with a single dense layer with no activation and an L2 loss for a linear regression.
net = Dense(number_of_outputs) # activation=None, use_bias=True by default
(In the code it's lenet instead of net.)
More docs: https://mxnet.incubator.apache.org/versions/master/tutorials/gluon/datasets.html
Hope that helps!
Since two operations Conv2DBackpropFilter and Conv2DBackpropInput count most of the time for lots of applications(AlexNet/VGG/GAN/Inception, etc.), I am analyzing the complexity of these two operations (back-propagation) in TensorFlow and I found out that there are three implementation versions (custom, fast and slot) for Conv2DBackpropFilter (https://github.com/tensorflow/tensorflow/blob/master/tensorflow/core/kernels/conv_grad_filter_ops.cc ) and Conv2DBackpropInput (https://github.com/tensorflow/tensorflow/blob/master/tensorflow/core/kernels/conv_grad_input_ops.cc). While I profile, all computations are passed to "custom" version instead of "fast" or "slow" which directly calls Eigen function SpatialConvolutionBackwardInput to do that.
The issue is:
Conv2DBackpropFilter uses Eigen:“TensorMap.contract" to do the tensor contraction and Conv2DBackpropInput uses Eigen:"MatrixMap.transpose" to do the matrix transposition in the Compute() function. Beside these two functions, I didn't see any convolutional operations which are needed for back-propagation theoretically. Beside convolutions, what else would be run inside these two operations for back-propagation? Does anyone know how to analyze the computation complexity of "back propagation" operation in TensorFlow?
I am looking for any advise/suggestion. Thank you!
In addition to the transposition and contraction, the gradient op for the filter and the gradient op for the input must transform their input using Im2Col and Col2Im respectively. Approximately speaking, these transformations enable the convolution operation to be implemented using tensor contraction. For more information, see the CS231n page on Convolutional Networks (specifically, the paragraphs titled "Implementation as Matrix Multiplication" and "Backpropagation").
mrry, I got it. It means that Conv2D, Conv2DBackpropFilter and Conv2DBackpropInput use the same way by using "GEMM" to work for convolution by Im2Col/Col2Im. An other issue is that while I do the profile of GAN in TensorFlow, the execution time of Conv2DBackpropInput and Conv2DBackpropFilter are around 4-6 times slower than Conv2D with the same input size. Why?
I'm looking to do some image classification on PDF documents that I convert to images. I'm using tensorflow inception v3 pre trained model and trying to retrain the last layer with my own categories following the tensorflow tuto. I have ~1000 training images per category and only 4 categories. With 200k iterations I can reach up to 90% of successful classifications, which is not bad but still need some work:
The issue here is this pre-trained model takes only 300*300p images for input. Obviously it messes up a lot with the characters involved in the features I try to recognize in the documents.
Would it be possible to alter the model input layer so I can give him images with better resolution ?
Would I get better results with a home made and way simpler model ?
If so, where should I start to build a model for such image classification ?
If you want to use a different image resolution than the pre-trained model uses , you should use only the convolution blocks and have a set of fully connected blocks with respect to the new size. Using a higher level library like Keras will make it a lot easier. Below is an example on how to do that in Keras.
import keras
from keras.layers import Flatten,Dense,GlobalAveragePooling2D
from keras.models import Model
from keras.applications.inception_v3 import InceptionV3
base_model = InceptionV3(include_top=False,input_shape=(600,600,3),weights='imagenet')
x = base_model.output
x = GlobalAveragePooling2D()(x)
x = Dense(1024,activation='relu')(x)
#Add as many dense layers / Fully Connected layers required
pred = Dense(10,activation='softmax')(x)
model = Model(base_model.input,pred)
for l in model.layers[:-3]:
l.trainable=False
The input_top = False will give you only the convolution blocks. You can use the input_shape=(600,600,3) to set the required shape you want. And you can add a couple of dense blocks/Fully connected blocks/layers to the model.The last layer should contain the required number of categories .10 represent the number of classes.By this approach you use all the weights associated with the convolution layers of the pre trained model and train only the last dense layers.
Which methods/algorithms that can be used to extract the features from this image
Where the previous image is a linear combination of several images with different weights
i.e., image= w1×LP01 + w2×LP02 + w3×LP03 + w4×LP11 + w5×LP12 ...etc
The LPmn images are something like this,
w is the weight.
I am looking for other methods except linear regression based methods, e.g., PCA, LDA, SVD ...
I have tried to use wavelet transform but it doesn't work. Any suggestions?
I would have played by reshaping the image to a vector and use the entire vector as your feature. And use a simple neural network to see how that works out. For a start!
Finding feature is an iterative process. It is not always obvious!
First of all: I'm completely new to Machine Learning and TensorFlow - I'm just playing around with this technology for a few weeks - and I really like it.
But I have (maybe a simple) question about the MNIST data set in combination with TensorFlow: I'm currently working through the "MNIST for ML Beginners" tutorial (https://www.tensorflow.org/versions/r0.11/tutorials/mnist/beginners/index.html#mnist-for-ml-beginners). I fully understand how the whole thing works, and what I accomplish with the source code.
My question is now the following:
Is it possible to see the individual weights parameters for each pixel? As far as I understand I can't access the individual weight parameters directly for each pixel, because the tf.matmul() operation returns me the sum over all weight parameters for a given class.
I want to access the individual weight parameters, because I want to see how these values are changing through the training process of the Neural Network.
Thanks for your help,
-Klaus
You can get the actual weights by just doing something like:
w = sess.run(W, feed_dict={x: batch_xs, y_: batch_ys})
print w.shape
If you want the per pixel results, just do a element-wise multiply of batch_xs * w (reshaped appropriately.)