This task requires you to do some binary classification on a set of testing images (sunny images vs not sunny images). You will be provided with:
- 259 labelled training data
- 2818 of test data, which are not labelled.
Each data instance is represented as a 4608 dimensional feature vector. This vector is a concatenation of 4096 dimensional deep Convolutional Neural Networks (CNNs) features extracted from the fc7 activation layer of Caf-feNet 1 and 512 dimensional GIST 2 features
The task is to develop a binary-class classifier that predicts the labels for the test data set.
Additionally, you are also provided with three types of information that might be useful when building your classifier:
a) additional 2331 labelled training data which is incomplete as it has missing feature values
b) confidence of the label annotation for each training data point (259 labelled training data and additional but incomplete 2331 labelled training data)
c) the proportion of positive (sunny) data points and the proportion of not sunny data points in the test set.
You can choose to incorporate or to ignore these additional data.
The report will consist of 3 stages, approach, method, results and discussions. More information will be given in a pdf when speaking to the chosen freelancer
24 freelancer menawar dengan rata-rata £121 untuk pekerjaan ini
Hi, I am an expert in Image classification. I am very familiar with binary classifier of images. I can do your project perfectly. Waiting for your response. Thanks.
Hi. I am an expert in image processing. I have many experiences in Image classification. I am sure I can do it. We can discuss details via chat. I wait for you now. Thanks.
Hi there, I have done several projects in Computer vision and object detection using Deep learning techniques. I can do this one too. Please inbox me any time so that we can discuss further.
I am a PhD student and my research areas Machine Learning, Deep Learning and Big Data. I have completed Adrian Rosebrocks courses. We can talk about details Have a nice day