conv-neural-network

问题 I have please two questions concerning the ImageDataGenerator: 1) Are the same augmentations used on the whole batch or each image gets its own random transformation? e.g. for rotation, does the module rotates all the images in the batch with same angle or each image get a random rotation angle ? 2) The data in ImageDataGenerator.flow is looped over (in batches) indefinitely. Is there a way to stop this infinite loop, i.e. doing the augmentation only for n number of time. Because I need to

问题 In order to learn tensorflow, I executed this tensorflow official mnist script (cnn_mnist.py) and displayed the graph with tensorboard. The following is part of the code. This network contains two conv layers and two dense layers. conv1 = tf.layers.conv2d(inputs=input_layer,filters=32,kernel_size=[5, 5], padding="same",activation=tf.nn.relu) pool1 = tf.layers.max_pooling2d(inputs=conv1, pool_size=[2, 2], strides=2) conv2 = tf.layers.conv2d(inputs=pool1,filters=64,kernel_size=[5, 5], padding=

问题 I want to use HDF5 file to input my data and labels in my CNN. I created the hdf5 file with matlab. Here is my code: h5create(['uNetDataSet.h5'],'/home/alexandra/Documents/my-u-net/warwick_dataset/Warwick_Dataset/train/image',[522 775 3 numFrames]); h5create(['uNetDataSet.h5'],'/home/alexandra/Documents/my-u-net/warwick_dataset/Warwick_Dataset/train/anno',[522 775 3 numFrames]); h5create(['uNetDataSet.h5'],'/home/alexandra/Documents/my-u-net/warwick_dataset/Warwick_Dataset/label',[1 numFrames

问题 I have a list of numpy arrays which are actually input images to my CNN. However size of each of my image is not cosistent, and my CNN takes only images which are of dimension 224X224. How do I reshape each of my image into the given dimension? print(train_images[key].reshape(224, 224,3)) gives me an output ValueError: total size of new array must be unchanged I would be very grateful if anybody could help me with this. 回答1: New array should have the same amount of values when you are

问题 I am currently working on a CNN network, in which i want to apply a 2d kernel on a image, but it only has to perform 1d convolution, meaning that it only has to move along one axis (x-axis in this case). The shape of the kernel is same as the y-axis of the image. The number of filters applied is not a concern at the moment. An example: Given a image of size (6,3,3) = (rows, cols, color_channel) How should i perform a 1d convolution given a 2d filter? Tried what was suggested by @Marcin

问题 For research at university I am examining the oxford 17 flowers alexnet example. The example uses the API tflearn based on tensorflow. Training is working very well on my GPU, reaching an accuracy of ~ 97% after a while. Unfortunately evaluating single images isn't working yet in tflearn, I would have to use model.predict(...) to predict all my data per batch, and loop over all my test set and calculate accuracy by myself. My training code so far: ... import image_loader X, Y = image_loader

问题 When using Inception v3 model in Keras, nor the graph of the network nor the model.summary() indicate the presence of the auxiliary classifiers (as in Szegedy et al.. Why is it so ? Is Keras still using the right architecture but hiding this specificity from the user ? If so, how can we then customize upper layers from the network ? Indeed, we may want the 3 classifiers to have distinct architectures. Thank you ! 来源： https://stackoverflow.com/questions/44906653/why-is-there-no-trace-of

问题 In image processing and classification networks, a common task is the convolution or cross-correlation of input images with some fixed filters. For example, in convolutional neural nets (CNNs), this is an extremely common operation. I have reduced the general version task to this: Given : a batch of N images [N,H,W,D,...] and a set of K filters [K,H,W,D,...] Return : a ndarray that represents the m-dimensional cross-correlation (xcorr) of image N_i with filter K_j for every N_i in N and K_j

问题 I have two images , image 1 of dimension (32,43,3) and image2 of dimension (67,86,3) . How can i store this in a numpy array , Whenever i try to append the array image=cv2.imread(image1,0) image=cv2.resize(image,(32,43)) x_train=np.array(image.flatten()) x_train=x_train.reshape(-1,3,32,43) X_train =np.append(X_train,x_train) #X_train is my array image=cv2.imread(image2,0) image=cv2.resize(image,(67,86)) x_train=np.array(image.flatten()) x_train=x_train.reshape(-1,3,67,86) X_train =np.append(X

问题 I am working on implementing Hinton's Knowledge distillation paper. The first step is to store the soft targets of a "cumbersome model" with a higher temperature (i.e. I don't need to train the network, just need to do forward pass per image and store the soft targets with a temperature T ). Is there a way I can get the output of Alexnet or googlenet soft targets but with a different temperature? I need to modify the soft-max with pi= exp(zi/T)/sum(exp(zi/T) . Need to divide the outputs of