2020欧洲杯时间表

Questions tagged [deep-learning]

Deep Learning is an area of machine learning whose goal is to learn complex functions using special neural network architectures that are "deep" (consist of many layers). This tag should be used for questions about implementation of deep learning architectures. General machine learning questions should be tagged "machine learning". Including a tag for the relevant software library (e.g., "keras", "tensorflow","pytorch","fast.ai" and etc) is helpful.

Filter by
Sorted by
Tagged with
0
votes
0answers
3 views

AttributeError: Tensor.op is meaningless when eager execution is enabled

I am trying to implement RESNET 50 from scratch. After accumulating all the layers, I call tf.keras.Model. It gives an error AttributeError: Tensor.op is meaningless when eager execution is enabled.. ...
0
votes
0answers
4 views

Cross Entropy Calculation in PyTorch tutorial

I'm reading the Pytorch tutorial of a multi-class classification problem. And I find the behavior of Loss calculation in Pytorch confuses me a lot. Can you help me with this? The model used for ...
0
votes
0answers
21 views

LSTM Training Loss and Val Loss not changing

I have been trying to create a LSTM RNN using tensorflow keras in order to predict whether someone is driving or not driving (binary classification) based on just Datetime and lat/long. However, when ...
0
votes
0answers
11 views

Passing a string to a deep learning/ machine learning models

Is there any possible way to passe a string (a hashed value) to a model like LSTM or anyother, because this column in my data is too important and I don't want to drop it. This the column in my data ...
-1
votes
0answers
5 views

LSTM Model for checking if two text have similar meanings

Let's say I have two sentences, A abd B. I want a Tensorflow Model that would ideally output wither or not the two sentences have similar meanings. Or, If the two sentences contradict with each other ...
0
votes
0answers
6 views

Is there any way to convert weight.pt model to weight.h5 or weight.weights to weight.h5 format

Is there any way to convert weight.pt model(weight files in pytorch format) to weight.h5(weight files in keras format) or weight.weights(weight files in darknet format) to weight.h5 format
0
votes
1answer
25 views

How to solve error: no match between expected input batch size and target batch size in PyTorch?

I attempting to create a logistic model on CIFAR10 dataset by PyTorch. However I am getting an error: ValueError: Expected input batch_size (900) to match target batch_size (300). What I think is ...
1
vote
1answer
17 views

Shapes of hidden 3d convolutional network layers, how to compute it?

I want to computer the shape of a given hidden layer output of a CNN, so suppose the input shape is (27,27,27,1) ie one image channe, the first convolutional layer is a 16X(3,3,3) kernels, stride is 1 ...
0
votes
0answers
12 views

tensorflow.python.keras.engine.sequential.Sequential vs keras.engine.training.Model

I've just started to learn Tensorflow (2.1.0), Keras (2.3.1) and Python 3.7.7. I'm following this Tensorflow's tutorial: "Custom training: walkthrough". This is my model, with all of its imports: ...
-2
votes
0answers
9 views

The deviation of the results of the lstm model is very large

http://colab.research.google.com/drive/1_YW_Afi0yZS5wJQxJbHXddezIppZFUL_?usp=sharing As you can see in the link, the result will be different every time you run. It is natural that the results will ...
0
votes
0answers
6 views

Using UNet to do segmentation on Cityscapes

I used the UNet to do segmentation on cityscapes dataset, but the output of the model is not very good. enter image description here How can I make the predict output better?
-2
votes
0answers
20 views

neural network in deep learning

I saw many videos about neural network and backpropagation but I have a question: is there any general algorithm to use in python to implement any neural network even if they have different forms (...
-2
votes
0answers
9 views

Different types of object detectors [closed]

I'm working on my research project where i'm tracing the object detector types starting from Viola jones and ending by Yolov4. Therefore I've created a table that lists the different types of ...
1
vote
0answers
11 views

Multi-branch network using tf.data.Dataset

I am trying to build a multi-stream network in TF 2.0 using pre-trained sub-models on different physical features of the face. I have 3 different models trained on LeftEye, RightEye and Mouth regions. ...
1
vote
1answer
23 views

Error when using Vgg16 output and adding extra custom layers. ValueError: Error when checking input

I am trying to take the outputs of images (train and validation) passed through a Vgg16 network with include_top = false , and then adding the final few layers as can be seen in the code below. I ...

15 30 50 per page
1
2 3 4 5
1159