Category "keras"

Using 3d sparse input with partial shape in Keras/Tensorflow gives error

I am trying to create a dense neural network where my input is a sparse 3d matrix. When converted to a dense matrix the shape is (2, None, n) (where n is a numb

Conv2D output shape in CNN too small

The input shape in the first Conv2D layer is supposed to be (100, 100, 1) however the output is (None, 98, 98, 200). I understand what 200 and None determine bu

ImportError('Could not import PIL.Image. ' working with keras-ternsorflow

I'm following some lectures from lynda.com about deep learning using Keras-TensorFlow in a PyCharmCE enviroment and they didn't have this problem. I get this er

having a very large loss when I am training a regression loss

I want to predict the center of the pupil from an image. so I used a CNN with 3 Dence layer. so the input is an image and the output is a coordinate (X,Y). my m

fit_generator() to save model with least validation loss

How do I use keras function fit_generator() to train and simultaneously save the model weights with lowest validation loss?

ValueError: The two structures don't have the same sequence length

Recently I tried to convert mask rcnn in this repository from tensorflow 1 to tensorflow 2. After re-writing the codes and when I run sample "shape" and execute

Keras loss is NaN when training for semantic segmentation

I am using the headsegmentation dataset. A single mask looks like this All mask images are a single channel. This is my code: image_size = 512 batch = 4 labels

Running keras model on ubuntu VM (UTM) on Mac with M1 chip

I have a Mac with an M1 Pro chip. I was able to install keras/tensorflow with tensorflow-metal PluggableDevice. My image classification model runs smoothly on m

ImportError: No module named 'keras'

So basically, I am fairly new to programming and using python. I am trying to build an ANN model for which I have to use Tensor flow, Theano and Keras library.

Reverse Image search (for image duplicates) on local computer

I have a bunch of poor quality photos that I extracted from a pdf. Somebody I know has the good quality photo's somewhere on her computer(Mac), but it's my unde

tensorflow:Can save best model only with val_acc available, skipping

I have an issue with tf.callbacks.ModelChekpoint. As you can see in my log file, the warning comes always before the last iteration where the val_acc is calcula

Tensorflow's seq2seq: tensorflow.python.framework.errors_impl.InvalidArgumentError

I am following quite closely the Seq2seq for translation tutorial here https://www.tensorflow.org/addons/tutorials/networks_seq2seq_nmt#define_the_optimizer_and

Getting error in Spyder Anaconda from Keras Libraries CNN: WARNING:root:Limited tf.compat.v2.summary API due to missing TensorBoard installation

I am trying to implement the Keras libraries for Convolutional Neural Networks on my Spyder IDE using Anaconda as such: from keras.models import Sequential

nearly 0% GPU-Util but high GPU Memory

A newbie for machine learning here. I'm now training a fairly easy model from tutorial using the dataset fashion_mnist on Win10. However, the training process t

frequency of words in text not present in another text with tf.Tokenizer

I have a text A and a text B. I wish to find the percentage of words in text B (counting all occurrences) not present in the vocabulary (i.e., the list of all u

making GRU/LSTM states trainable in Tensorflow/Keras and add some random noise

I train the following model based on GRU, note that I am passing the argument stateful=True to the GRU builder. class LearningToSurpriseModel(tf.keras.Model):

Tensorflow LSTM/GRU reset states once per epoch and not for each new batch

I train the following model based on GRU, note that I am passing the argument stateful=True to the GRU builder. class LearningToSurpriseModel(tf.keras.Model):

How to properly initialize TensorFlow GRU-layer with noisy states?

I wish to experiement with noisy GRU states instead of resetting them to zero for each batch. I try below an implementation. My initial code was resetting initi

TypeError: Inputs to a layer should be tensors. Got: <tensorflow.python.keras.engine.functional.Functional object at 0x000001ADE3B6BEE0>

I'm trying to Implement Inception_resnet_v2 inside Faster-RCNN instead of using ResNet50. but when I try to run the code I got this TypeError: TypeError: Inputs

How to overcome "TypeError: Exception encountered when calling layer "tf.keras.backend.rnn" (type TFOpLambda)"?

I'm trying to re-implement the text summarization tutorial here. The tutorial employs the Attention Layer proposed for Keras on GitHub (which does not come with