Issue There is no evaluation during training in the Google Colab Notebook for detectron2 as can be seen here: https://colab.research.google.com/drive/16jcaJoc6bCFAQ96jDe2HwtXj7BMD_-m5. It does not use the validation data while training a custom dataset. How should I add it? Reference Github repoContinue reading
[SOLVED] How to get nearest neighbor for every element of array A from array B
Issue I need to create function nearest_neighbor(src, dst), which accepts two arrays of 2D points, and for every point of array A calculates distance and index to closest neighbor from array B. Example input: src = np.array([[1,1], [2,2],[3,3],[4,4],[9,9]]) dst =Continue reading
[SOLVED] How to exaggerate color differences with OpenCV?
Issue I am trying to make it easier for Canny Edge detection to find edges by exaggerating differences in colors in an image. For example, giving it the following image: Canny returns: As you can see, Canny omits most ofContinue reading
[SOLVED] how to get camera calibration data from the TrueDepth Camera iOS?
Issue Goal: To obtain depth data & calibration data from the TrueDepth Camera for computer vision task. I am very confused because for example apple says, To use depth data for computer vision tasks, use the data in the cameraCalibrationDataContinue reading
[SOLVED] CNN – Image Resizing VS Padding (keeping aspect ratio or not?)
Issue While people usually tend to simply resize any image into a square while training a CNN (for example, resnet takes a 224×224 square image), that looks ugly to me, especially when the aspect ratio is not around 1. (InContinue reading
[SOLVED] How to draw Bigger bounding box and Crop Only bounding box Text Python Opencv
Issue I am using easyocr to detect the text in the image. The method gives the output bounding box. The input images are shown below Image 1 Image 2 The output image is obtained using the code below. But IContinue reading
[SOLVED] ValueError when loading model that uses lambda resize layer in keras
Issue So basically, I trained a model with a resize layer. Here is my model: model = Sequential() model.add(keras.layers.Lambda( lambda image: tf.image.resize( image, (470,470), method = tf.image.ResizeMethod.BICUBIC, preserve_aspect_ratio = True ) )) model.add(Conv2D(32, (3, 3), activation=’relu’, input_shape=shape)) model.add(MaxPool2D((2, 2))) model.add(Conv2D(64,Continue reading
[SOLVED] How to solve Graph execution error during my model training?
Issue I build the inception v3 model from scratch. When I tried to train my model with a popular data set, dogs and cats from Kaggle, I faced Graph execution error. The reason might be my data set; I guessContinue reading
[SOLVED] How to convert a csv dataset to a numpy array readable by opencv?
Issue I have a csv dataset namely sign language mnist dataset. It contains information of 28×28 images with its pixel information. I would like to convert this dataset into a numpy array that can be read by opencv3. A numpyContinue reading
[SOLVED] numpy with python: convert 3d array to 2d
Issue Say that I have a color image, and naturally this will be represented by a 3-dimensional array in python, say of shape (n x m x 3) and call it img. I want a new 2-d array, call itContinue reading