machine-learning

How to get the location of all text present in an image using OpenCV?

by

Here’s a potential approach using morphological operations to filter out non-text contours. The idea is: Obtain binary image. Load image, grayscale, then Otsu’s threshold Remove horizontal and vertical lines. Create horizontal and vertical kernels using cv2.getStructuringElement() then remove lines with cv2.drawContours() Remove diagonal lines, circle objects, and curved contours. Filter using contour area cv2.contourArea() and … Read more

What are logits? What is the difference between softmax and softmax_cross_entropy_with_logits?

by

The softmax+logits simply means that the function operates on the unscaled output of earlier layers and that the relative scale to understand the units is linear. It means, in particular, the sum of the inputs may not equal 1, that the values are not probabilities (you might have an input of 5). Internally, it first … Read more

How to extract the decision rules from scikit-learn decision-tree?

by

I believe that this answer is more correct than the other answers here: from sklearn.tree import _tree def tree_to_code(tree, feature_names): tree_ = tree.tree_ feature_name = [ feature_names[i] if i != _tree.TREE_UNDEFINED else “undefined!” for i in tree_.feature ] print “def tree({}):”.format(“, “.join(feature_names)) def recurse(node, depth): indent = ” ” * depth if tree_.feature[node] != _tree.TREE_UNDEFINED: … Read more

What is the role of the bias in neural networks? [closed]

by

I think that biases are almost always helpful. In effect, a bias value allows you to shift the activation function to the left or right, which may be critical for successful learning. It might help to look at a simple example. Consider this 1-input, 1-output network that has no bias: The output of the network … Read more

How to split data into 3 sets (train, validation and test)?

by

Numpy solution. We will shuffle the whole dataset first (df.sample(frac=1, random_state=42)) and then split our data set into the following parts: 60% – train set, 20% – validation set, 20% – test set In [305]: train, validate, test = \ np.split(df.sample(frac=1, random_state=42), [int(.6*len(df)), int(.8*len(df))]) In [306]: train Out[306]: A B C D E 0 0.046919 … Read more

What function defines accuracy in Keras when the loss is mean squared error (MSE)?

by

There are at least two separate issues with your question. The first one should be clear by now from the comments by Dr. Snoopy and the other answer: accuracy is meaningless in a regression problem, such as yours; see also the comment by patyork in this Keras thread. For good or bad, the fact is … Read more