neural-network

问题 I've been going through a few tutorials on using neural networks for key points detection. I've noticed that for the inputs (images) it's very common to divide by 255 (normalizing to [0,1] since values fall between 0 and 255). But for the targets (X/Y) coordinates I've noticed it's more common to normalize to [-1,1]. Any reason for this disparity. Example: http://danielnouri.org/notes/2014/12/17/using-convolutional-neural-nets-to-detect-facial-keypoints-tutorial/ X = np.vstack(df['Image']

问题 I can't run pretrained models of Pixel Objectness published by Suyog Dutt Jain et al in 2017. I referred section Using the pretrained models in README.md on GitHub, but couldn't understand the following procedures well. ・Setup: Download and install Deeplab-v1 from here ・Refer to demo.py for step-by-step instruction on how to run the code. I tryed to install and run "demo.py", but I got some errors. Though I referred solutions on Website, unsolvable error remained. /usr/bin/python2.7 /mnt/C6BF

问题 I had the Caffe C++ example program working on my computer, but after recently recompiling Caffe, I've encountered this error when I try to run the program: [libprotobuf ERROR google/protobuf/text_format.cc:245] Error parsing text-format caffe.NetParameter: 2:4: Message type "caffe.NetParameter" has no field named "net". upgrade_proto.cpp:928] Check failed: ReadProtoFromTextFile(param_file, param) Failed to parse NetParameter file: /home/jack/Desktop/beeshiny/deploy.prototxt Am I missing

问题 In this blog on Recurrent Neural Networks by Denny Britz. Author states that, " The above diagram has outputs at each time step, but depending on the task this may not be necessary. For example, when predicting the sentiment of a sentence we may only care about the final output, not the sentiment after each word. Similarly, we may not need inputs at each time step. " In the case when we take output only at the final timestep: How will backpropogation change, if there are no outputs at each

问题 I'm trying to install Tensorflow with CUDA support. Here are my specs: NVIDIA GTX 1070 CUDA 7.5 Cudnn v5.0 I have installed Tensorflow via the pip installation -- so I'm picturing your answer being to install from source, but I want to make sure there isn't a quick fix. The error is: volcart@volcart-Precision-Tower-7910:~$ python Python 2.7.10 (default, Oct 14 2015, 16:09:02) [GCC 5.2.1 20151010] on linux2 Type "help", "copyright", "credits" or "license" for more information. >>> import

问题 This is a higher-level question about the performance of a neural network. The issue I'm having is that with larger numbers of neurons per layer, the network has frequent rounds of complete stupidity. They are not consistent; it seems that the probability of general success vs failure is about 50/50 when layers get larger than 60 neurons (always 3 layers). I tested this by teaching the same function to networks with input and hidden layers of sizes from 10-200. The success rate is either 0-1%

问题 Closed. This question is off-topic. It is not currently accepting answers. Want to improve this question? Update the question so it's on-topic for Stack Overflow. Closed 2 years ago . I have programmed a multi-layer neural network but I'm getting an error while feeding my dimension into it. I'm getting a Value Error. Here is The Code: import pandas as pd import tensorflow as tf import matplotlib.pyplot as plt import numpy as np from sklearn import datasets from sklearn import metrics from

问题 I'm new to Theano, just learning it. I have a ANN in python that I'm implementing in Theano as learning process. I'm using Spyder. And Theano throws out an error: TypeError: Unknown parameter type: class 'numpy.ndarray' I'm not sure where the error is. Is it in the cost function or in the gradient descent? And what is the typical reason for it? Here is my code: X = T.dmatrix() y = T.dmatrix() X_input = np.genfromtxt('X.csv',delimiter=',') #5000x195 y_input = np.genfromtxt('y.csv',delimiter=',

问题 I get the error above when running my Neural net: print('Checking the Training on a Single Batch...') with tf.Session() as sess: # Initializing the variables sess.run(tf.global_variables_initializer()) # Training cycle for epoch in range(epochs): batch_i = 1 for batch_features, batch_labels in (input_data, input_labels): train_neural_network(sess, optimizer, keep_probability, batch_features, batch_labels) print('Epoch {:>2}, Batch {}: '.format(epoch + 1, batch_i), end='') print_stats(sess,

问题 I'm trying to find the best parameters for NN regression model using GridSearchCV with following code: param_grid = dict(optimizer=optimizer, epochs=epochs, batch_size=batches, init=init grid = GridSearchCV(estimator=model, param_grid=param_grid, scoring='neg_mean_squared_error') grid_result = grid.fit(input_train, target_train) pred = grid.predict(input_test) As I understand, grid.predict(input_test) uses best parameters to predict the given input set. Is there any way to evaluate