365体育足球滚球比分

How are we doing? Please help us improve Stack Overflow. Take our short survey

Questions tagged [keras]

Keras is a neural network library providing a high-level API in Python and R. Use this tag for questions relating to how to use this API. Please also include the tag for the language/backend ([python], [r], [tensorflow], [theano], [cntk]) that you are using. If you are using tensorflow's built-in keras, use the [tf.keras] tag.

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

with tensorflow and keras how to find the “category” of a given string

Hello ML/AI newbie here, I'm asking this question because I've no idea about machine learning, ai, e.t.c and I've no idea how to continue, what questions to ask. Even if I accidentally find the ...
1
vote
0answers
5 views

AttributeError: 'NoneType' object has no attribute '_inbound_nodes' Keras

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, ...
0
votes
0answers
5 views

Keras Library OR shall i choose neural network from Scratch

I am new to Deep learning. We already have good libraries like Keras etc., to Develop neural network application. To Develop deep learning models (Apart from Keras) Shall I also need to learn more ...
1
vote
0answers
12 views

How to train your own(w/o YOLO etc.) object detector in tf/keras

I successfully trained multi-classificator model, that was really easy with simple class related folder structure and keras.preprocessing.image.ImageDataGenerator with flow_from_directory (no one-hot ...
0
votes
0answers
5 views

Is there any pre-fitted Keras tokenizer?

In Text data preprocessing in keras, we use Tokenizer class. But if we fit the training data in the Tokenizer, then any new word in the testing set does not get identified when generating sequences. ...
0
votes
0answers
21 views

How does one format their data to be like the MNIST dataset?

I was following along with the tutorial for DCGAN's and I had trouble with training my model, since I had my own dataset, a different dataset than MNIST. Although I had successfully loaded my dataset, ...
0
votes
0answers
4 views

I'm getting “Tensor.op is meaningless when eager execution is enabled.” in my simple encoder model. (TF 2.0)

The code of my encoder model is given below, I have made it using functional API(TF 2.0) embed_obj = EndTokenLayer() def encoder_model(inp): input_1 = embed_obj(inp) h = Masking([(lambda x: x*0)(...
0
votes
0answers
13 views

KerasLayer trainable=false seems to have no effect

Setting trainable=False seems to have no effect. Minimal example: layer = tf.keras.layers.Dense( units=1, kernel_initializer=tf.keras.initializers.Constant([[1.0]]), ...
0
votes
0answers
14 views

How to avoid overfitting in CNN?

I'm making a model for predicting the age of people by analyzing their face. I'm using this pretrained model, and maked a custom loss function and a custom metrics. So I obtain discrete result but I ...
0
votes
2answers
20 views

keras rnn make method like cnn, can you give me sample code?

as you know, we make mlp, CNN etc.. to use keras for example) 1)3 hidden Layer MLP 1st layer : 256 unit 2nd layer : 512 unit 3rd layer : 1024 unit batchsize : 128 iteration : 5000 from keras....
0
votes
0answers
10 views

Using the Tensorflow Dataset map function to retrieve multiple sentences for a single image

I am trying to implement the Neural Image Caption generator with visual attention proposed in the "Show, Attend and Tell" paper. For validation, I want to compute the Bleu score. For this, I need to ...
0
votes
0answers
18 views

Discrepancy in the results of model.evaluate and model.predict in Keras

I'm performing multi-class classification with three class labels in Keras. During training, both the training and validation losses were decreasing and accuracies were increasing. After training, I ...
0
votes
0answers
13 views

KFold Cross Validation multiclass recognition in Keras

I‘m trying to do KFold Cross Validation with a multiclass recognition problem. The dataset is the Uc-merced dataset, it contains 21 classes, for each class we have 100 images. This is the code: # ...
0
votes
0answers
17 views

Iterating over Conv2D layers of a pre-trained model

I am using progressive learning for making a model for classification. I first used vgg16 weights and add a Dense layer at the end to train the model. prior = keras.applications.VGG16( ...
0
votes
0answers
11 views

How to reconstruct sequence of unspecified length from LSTM autoencoder?

from keras import backend as K .... other dependencies ..... input_ae = Input(shape=(None, 2)) # shape: time_steps, n_features LSTM1 = LSTM(units=128, return_sequences=True, activation = 'relu')(...

15 30 50 per page
1
2 3 4 5
1823