tensorflow

问题 from Config import Config from FaceDetection.MTCNNDetect import MTCNNDetect import cv2 import tensorflow as tf import keras from keras import backend as K from keras.layers import Input, Lambda, Dense, Dropout, Convolution2D, MaxPooling2D, Flatten, Concatenate, concatenate from keras.models import Model face_detect = MTCNNDetect(model_path=Config.MTCNN_MODEL) from FaceRecognition.TensorflowGraph import FaceRecGraph from src.FaceAlignment import AlignCustom from FaceRecognition.FaceFeature

问题 I have been trying to build RNN with Seq2Seq model from Udemy course called DeepLearning_NLP_Chatbot, and I followed him step by step, but I face when training an error: InvalidArgumentError : Received a label value of 8825 which is outside the valid range of [0, 8825). The dataset here. here is the data procesing dataset # Building a Chatbot with Deep NLP. # Importing the libraries. import numpy as np import tensorflow as tf import re import time # ---Data Processing---# #-------------------

问题 I'm doing some evaluation for my algorithm where I'm comparing some generated images to a ground truth image by computing 3 different types of loss between the two images. The logic of the code is: I loop over all ground truth images For each ground truth image, I loop over the relevant generated images and check each against the ground truth image by computing 3 losses The running time of the code is increasing for each iteration as seen below. This makes it so the code can't finish running

问题 When using tf.layers.conv2d , setting the initializer is easy, it can be done through its parameter. But what if I use tf.nn.conv2d ? I use this code. Is this equivalent to setting the kernel_initializer parameter in tf.layers.conv2d ? Although the program runs without errors, I don't know how to verify whether it does what it is expected do. with tf.name_scope('conv1_2') as scope: kernel = tf.get_variable(initializer=tf.contrib.layers.xavier_initializer(), shape=[3, 3, 32, 32], name='weights

问题 When using tf.layers.conv2d , setting the initializer is easy, it can be done through its parameter. But what if I use tf.nn.conv2d ? I use this code. Is this equivalent to setting the kernel_initializer parameter in tf.layers.conv2d ? Although the program runs without errors, I don't know how to verify whether it does what it is expected do. with tf.name_scope('conv1_2') as scope: kernel = tf.get_variable(initializer=tf.contrib.layers.xavier_initializer(), shape=[3, 3, 32, 32], name='weights

问题 I'm trying to restore the pretrained model provided here and continue training on a different dataset. The pretrained models available there are trained on tensorflow_gpu-1.1.0. But I have tensorflow_gpu-1.13.1 . When I try restoring the model, I get the below error. NotFoundError (see above for traceback): Restoring from checkpoint failed. This is most likely due to a Variable name or other graph key that is missing from the checkpoint. Please ensure that you have not altered the graph

问题 On Kaggle, I am making a classifier for the MNIST dataset. For that, I followed the instructions from here. import numpy as np # linear algebra import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv) import tensorflow as tf # Input data files are available in the "../input/" directory. # For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory from subprocess import check_output print(check_output(["ls", "../input"]).decode(

问题 I'm trying to restore the pretrained model provided here and continue training on a different dataset. The pretrained models available there are trained on tensorflow_gpu-1.1.0. But I have tensorflow_gpu-1.13.1 . When I try restoring the model, I get the below error. NotFoundError (see above for traceback): Restoring from checkpoint failed. This is most likely due to a Variable name or other graph key that is missing from the checkpoint. Please ensure that you have not altered the graph

问题 I have considered these two posts(this and this), but they are not my problem and solution. I have the following code to create a feed forward network in tf: step = 500 fromState = 0 toState = 5000000 numOfState = (toState - fromState) / step numOfAction = 11 tf.reset_default_graph() inputs1 = tf.placeholder(shape=[1,numOfState], dtype = tf.float32) W = tf.Variable(tf.random_uniform([numOfState,4],0,0.01),) Qout = tf.matmul(inputs1,W) predict = tf.argmax(Qout,1) However, I've got the

问题 the tensorflow serving build denpend on large tensorflow; but i already build tensorflow successfully. so i want to use it. I do these things: I change the tensorflow serving WORKSPACE(org: https://github.com/tensorflow/serving/blob/master/WORKSPACE) workspace(name = "tf_serving") # To update TensorFlow to a new revision. # 1. Update the 'git_commit' args below to include the new git hash. # 2. Get the sha256 hash of the archive with a command such as... # curl -L https://github.com