conv-neural-network

问题 I can calculate the receptive field size of 500 x 500 input image for VGGNet. The receptive field sizes are as follow. Layer Name = conv1, Output size = 500, Stride = 1, RF size = 3 Layer Name = relu1_1, Output size = 500, Stride = 1, RF size = 3 Layer Name = conv1_2, Output size = 500, Stride = 1, RF size = 5 Layer Name = relu1_2, Output size = 500, Stride = 1, RF size = 5 Layer Name = pool1, Output size = 250, Stride = 2, RF size = 6 Layer Name = conv2_1, Output size = 250, Stride = 2, RF

问题 How can I get both the 4096 dim feature layer and the 1000 dim class layer in caffe after one forward pass using C++? I tried to look it up in extract_features.cpp but it uses some weird datum object, so I cannot really understand how it works. So far I was simply cropping my prototxt files up to the layer that I wanted to extract and used [...] net->ForwardPrefilled(); Blob<float> *output_layer = net->output_blobs()[0]; const float *begin = output_layer->cpu_data(); const float *end = begin

问题 In Neural Networks and Deep Learning, there's an object called network3 (which is a PY file, written for python 2.7 and theano 0.7). I modified it to run with python 3.6 and theano 1.0.3. However, when I run the following code: import network3 from network3 import Network from network3 import ConvPoolLayer , FullyConnectedLayer , SoftmaxLayer training_data , validation_data , test_data = network3.load_data_shared() mini_batch_size = 10 net = Network([FullyConnectedLayer(n_in=784, n_out=100),

问题 At the moment I'm trying to run a ConvNet. Each image, which later feeds the neural net, is stored as a list. But the list is at the moment created using three for-loops. Have a look: im = Image.open(os.path.join(p_input_directory, item)) pix = im.load() image_representation = [] # Get image into byte array for color in range(0, 3): for x in range(0, 32): for y in range(0, 32): image_representation.append(pix[x, y][color]) I'm pretty sure that this is not the nicest and most efficient way.

问题 I am trying to implement a median pooling layer in tensorflow. However there is neither tf.nn.median_pool and neither tf.reduce_median . Is there a way to implement such pooling layer with the python api ? 回答1: You could use something like: patches = tf.extract_image_patches(tensor, [1, k, k, 1], ...) m_idx = int(k*k/2+1) top = tf.top_k(patches, m_idx, sorted=True) median = tf.slice(top, [0, 0, 0, m_idx-1], [-1, -1, -1, 1]) To accommodate even sized median kernels and multiple channels, you

问题 main_model = Sequential() main_model.add(Conv3D(32, 3, 3,3, input_shape=(20,50,50,1)))' main_model.add(Activation('relu')) main_model.add(MaxPooling3D(pool_size=(2, 2,2)) main_model.add(Conv3D(64, 3, 3,3)) main_model.add(Activation('relu')) main_model.add(MaxPooling3D(pool_size=(2, 2,2))) main_model.add(Dropout(0.8)) main_model.add(Flatten()) #lower features model - CNN2 lower_model1 = Sequential() lower_model1.add(Conv3D(32, 3, 3,3, input_shape=(20,50,50,1))) lower_model1.add(Activation(

问题 I'm trying to use the SSD between two images as loss function for my network. # h_fc2 is my output layer, y_ is my label image. ssd = tf.reduce_sum(tf.square(y_ - h_fc2)) train_step = tf.train.GradientDescentOptimizer(0.01).minimize(ssd) Problem is, that the weights then diverge and I get the error ReluGrad input is not finite. : Tensor had Inf values Why's that? I did try some other stuff like normalizing the ssd by the image size (did not work) or cropping the output values to 1 (does not

问题 I know when we are using convolution layers in a neural net we usually use padding and mainly constant padding(e.g. zero padding). And there are different kinds of padding(e.g. symmetric, reflective, constant). But I am not sure what are the advantages and disadvantages of using different padding methods and when to use which one. 回答1: it really depends on the situation for what the neural network is intended. I would not tell it pros and cons. This time the world cannot put into a binary

问题 For example, I have CNN which tries to predict numbers from MNIST dataset (code written using Keras). It has 10 outputs, which form softmax layer. Only one of outputs can be true (independently for each digit from 0 to 9): Real: [0, 1, 0, 0, 0, 0, 0, 0, 0, 0] Predicted: [0.02, 0.9, 0.01, 0.01, 0.01, 0.01, 0.01, 0.01, 0.01, 0.01] Sum of predicted is equal to 1.0 due to definition of softmax. Let's say I have a task where I need to classify some objects that can fall in several categories: Real

问题 I'm new to Caffe. I am trying to implement a Fully Convolution Neural Network (FCN-8s) for semantic segmentation. I have image data and label data, which are both images. This is for pixel-wise predictions. I tried using ImageData as the data type, but it asks for an integer label, which is not applicable to this scenario. Kindly advise as how to I can give Caffe a 2D label. Should I prefer LMDB instead of ImageData? If so, how do I proceed? I could not find any good tutorial/documentation