tensorflow

问题 I am having a problem with this NN regression model in keras. I am working on a cars dataset to predict the price based on 13 dimensions. In short, I have read it as pandas dataframe, converted numeric values to float, scaled the values, and then used one-hot encoding for categorical values, which has created a lot of new columns, but that does not concern me much at this point. What concerns me is that the accuracy is practically 0%, and I cannot figure out why. Dataset can be found here:

问题 I am building a deconvolution network. I would like to add a layer to it which is the reverse of a softmax. I tried to write a basic python function that returns the inverse of a softmax for a given matrix and put that in a tensorflow Lambda and add it to my model. I have no error but when I doing a predict I only have 0 at the exit. When I don't add this layer to my network I have output something other than zeros. This therefore justifies that they are due to my inv_softmax function which

问题 I am building a deconvolution network. I would like to add a layer to it which is the reverse of a softmax. I tried to write a basic python function that returns the inverse of a softmax for a given matrix and put that in a tensorflow Lambda and add it to my model. I have no error but when I doing a predict I only have 0 at the exit. When I don't add this layer to my network I have output something other than zeros. This therefore justifies that they are due to my inv_softmax function which

问题 I am building a deconvolution network. I would like to add a layer to it which is the reverse of a softmax. I tried to write a basic python function that returns the inverse of a softmax for a given matrix and put that in a tensorflow Lambda and add it to my model. I have no error but when I doing a predict I only have 0 at the exit. When I don't add this layer to my network I have output something other than zeros. This therefore justifies that they are due to my inv_softmax function which

问题 I am trying to build a customized ANN Model on Python. My method, where I have built the model, is as follows: def binary_class(x_train,nodes,activation,n): #Creating customized ANN Model model=Sequential() for i in range(len(nodes)): if(i==0): if(activation=='sigmoid'): model.add(Dense(units = nodes[i], kernel_initializer = 'glorot_uniform',activation='sigmoid',input_dim = len(x_train[1]))) if(activation=='relu'): model.add(Dense(units = nodes[i], kernel_initializer = 'he_uniform',activation

问题 Numpy load with allow_pickle=true old keras in tensorflow.keras Situation I have taken a course, where a Jupyter-notebook with a few example use-cases was provided. In order to save time and to have a clean working-environment, I've decided to use the Docker-image: jupyter/tensorflow-notebook:latest (see here). These are the pip list results for the relevant modules: [...] Keras-Applications 1.0.8 Keras-Preprocessing 1.1.0 [...] numpy 1.17.5 [...] tensorflow 2.1.0 [...] (a) The following

问题 I can't install TensorFlow in Windows 7, Python 3(32-bit, Lenovo ThinkPad X201s). When I type pip3 install tensorflow : Microsoft Windows [Version 6.1.7601] Copyright (c) 2009 Microsoft Corporation. All rights reserved. C:\Users\sjkim>pip3 install tensorflow Collecting tensorflow Could not find a version that satisfies the requirement tensorflow (from versions: ) No matching distribution found for tensorflow C:\Users\sjkim> And I also have 2 python versions. How can I install it? 回答1:

问题 Getting the following error message when setting up a 3D-GAN for ModelNet10: InvalidArgumentError: Input to reshape is a tensor with 27000 values, but the requested shape has 810000 [Op:Reshape] In my opinion the batch is not properly created and thereby the shape of the tensor is not valid. Tried different things but can´t get the batch set up.. I am more than thankful for any hints how to clean up my code! Thanks in advance! import time import numpy as np import tensorflow as tf np.random

问题 I have some code in TensorFlow which takes a base model, fine-tunes (trains) it with some data, and then uses the model to predict() using some other data. All this is encapsulated in a main() method of a module and works fine. When I run this code in a loop over different base models, however, I end up with an OOM after, e.g., 7 base models. Is this expected? I would expect that Python cleans up after each main() call. Does TensorFlow not do that? How can I force it to? Edit: here's an MWE

问题 I have some code in TensorFlow which takes a base model, fine-tunes (trains) it with some data, and then uses the model to predict() using some other data. All this is encapsulated in a main() method of a module and works fine. When I run this code in a loop over different base models, however, I end up with an OOM after, e.g., 7 base models. Is this expected? I would expect that Python cleans up after each main() call. Does TensorFlow not do that? How can I force it to? Edit: here's an MWE