The setting uses GPU, but there is no change in computing speed, and gpu utilization is extremely low. here is part of the code: < hr > from tensorflow.python.framework import ops ops.reset_default_graph() config = tf.ConfigProto() config.gpu_optio...

because there is no PyTorch tag at present, so TensorFlow is used. Would you like to add this tag to those with high reputation? Thanks tags () recently, I m going to use the VGG model to train the data, and then I want to use GPU, but I always repor...

when using Tensorflow for multiple linear regression, we encounter the problem of parameter non-convergence. The problem lies in the choice of optimization methods: if you use tf.train.AdamOptimizer , the parameters will converge and the loss function ...

I am a rookie. I just started to learn tensorflow,. When I used tensorflow to implement RNN, init = tf.global_variables_initializer () reported an error. I am so ignorant-- pray for God! Thank you! import tensorflow as tf from tensorflow.exampl...

running a simple CNN model, the picture shows 64X64 the first layer convolution is 8X5X5, pooled into 5X5, step size is 2; second layer convolution is 16X5X5, pooled is 5X5, step size is 2; third layer convolution is 32X1X1, pooled into global pooled...

Does session.run ([op1,op2]) in tensorflow give priority to the allocation of cpu and gpu when fetch has multiple op? Because if op1 is to add 1 to a variable x and then assign to assign op2 to the same x minus 1, then the value of x is uncertain. imp...

from PIL import Image, ImageFont, ImageDraw im = Image.open ( . realcap captcha (4) .gif ) % matplotlib inline the matlotlib liline behind the% here is now like machine learning a lot of expressions I don t quite understand, I don t know what ...

whether you enter token, above or below, you cannot log in. When you open the chrom development tool, you will find that there is something wrong with the page. How to solve this problem? ...

since python2, is installed by default in mac, now I want to use python3, , so I installed a python3, prompt Installed kernelspec python3 in usr local share jupyter kernels python3 on the terminal, indicating that the core installation of python3 is...

I just tried to install tensorflow, in accordance with the way taught on the official website of tf. The installation method is Virtualenv. The installation is successful. When I enter the virtual environment and import tensorflow, I report an error. Th...

it seems to say on the Internet that accuracy in TF is calculated according to batch_size (denominator batch_size). Why is it that when batch_size = 4 is set, the output accuracy of each batch_size after updating the model parameters is not one of 0meme ...

after several iterations, the loss function remains unchanged, and the learning rate is still changed. I hope the great god will guide you what the problem is this is the code https: github.com yaoqinchua. uses multi-perspective CNN (mvcnn) . ...

1 I installed tensorflow, on ubuntu16.04LTS, python version 2.7 3.5.2 with pip. The result indicates that piping is too old, and it is useless for me to update pip. The following is the error message yc_qian@QYC:~$ sudo-H pip install tensorflow-- up...

Hello, everyone. I just learned neural network. I want to do a regression experiment to test whether neural networks can learn this special case. This is a simple experiment, training data is randomly generated 10000 pieces of data, each data feature ve...

problem description Pip can be used normally in jupyterNotebook after Tensorflow is installed normally, but when importing from normal command line and pycharm, it is found that the imported package is not a normal package (you can import the package ...

1 problem description the actual combat is to use the code in the slim framework to use inception_resnet_v2 s pre-training network to train their own data sets for classification. But there is . InvalidArgumentError (see above for traceback): Assign...

when customizing the layer through keras, if you use the py_func function of tensorflow to customize the action, it will cause AttributeError: NoneType object has no attribute _ inbound_nodes to be prompted when creating the model. the test ...

the use of GPU in the Tensorflow framework will only affect speed and why it will also affect the running results. when you close GPU, the result will be blank. Using GPU is normal https: pan.baidu.com s 1mfA7. Code as above, can be run directly ...

now that I have finished classifying my photo collection using Alexnet network, I now see that the function of embedding in tensorBoard feels very cool, and I especially hope to see the effect of my network classification through that kind of visual int...

1. Question: tensorflow error the Tensor printed in blue before is the variable I want to force assignment to Code: def alexnet(image, keepprob=0.5): ... fc3 = tf.nn.sigmoid(tf.matmul(dropout2, weight3)) return fc3 is the...