Category "tensorflow"

Custom keras loss function binary cross entropy giving improper results

Did anyoe have a convincing solution to make custom_binarycrossentropy work? I tried all possible methods (even making the whole training data size same as the

Keras loss value significant jump

I am working on a simple neural network in Keras with Tensorflow. There is a significant jump in loss value from the last mini-batch of epoch L-1 to the first m

Labmap.pbtxt file creation

I am trying to create my labelmap.pbtxt, but the file is not created. Here's the code Train_Annotations_Path = "C:/Users/JAAD_dataset/Workspace/annotations/Anno

Deeplearning with Python Tensorflow,Keras

I am writing masters thesis about deeplearning and have a problem probably about library. Below is the error: AttributeError: module 'tensorflow.compat.v2' has

Resize image in cppflow tensorflow c++

Using cppflow, I have a 224x224 jpeg that I am trying to resize to 128x128. auto input = cppflow::decode_jpeg(cppflow::read_file(std::string(filename))); auto r

Tensorflow: Could not load dynamic library 'libcusolver.so.11'; dlerror: libcusolver.so.11: cannot open shared object file: No such file

I've been trying to run tensorflow in my gpu for some long days but I've been not able to accomplish it. I know that there are several questions with similar qu

Does image classification transfer learning require negative examples?

Task is to determine which of 3 classes does an image belongs to, or none. I received a ready model. EfficientNet B4 with ImageNet weights had transfer learnin

Loading TensorFlow model to manipulate an audio stream with C++

I want to load a machine learning model created with TensorFlow into my C++ Audio Application made with JUCE6. In order to use TensorFlow inside C++, I am using

Cannot set tensor: Dimension mismatch. Got 3 but expected 4 for input 0

This is probably going to be a stupid question but I am new to deep learning and TensorFlow. Here I have converted my deep learning model to TF-lite, after that

PIL.UnidentifiedImageError: cannot identify image file <_io.BytesIO object

I am trying to train my model (Image classification) using Tensorflow. I keep getting an error when I try to run the following cell: hist = model.fit(

PIL.UnidentifiedImageError: cannot identify image file <_io.BytesIO object

I am trying to train my model (Image classification) using Tensorflow. I keep getting an error when I try to run the following cell: hist = model.fit(

Keras model.fit() runs faster on GPU when the CPU is loaded with a heavy multiprocessing script

I wasn't expecting this to happen. The relevant code pieces are: import os import tensorflow as tf os.environ['TF_XLA_FLAGS'] = '--tf_xla_enable_xla_devices' .

Failing to load model using multiprocessing on windows

This program works on Unix and I'm trying to transition it to windows. It uses multiprocessing and I understand it's an issue with being forced to use spawning

Failing to load model using multiprocessing on windows

This program works on Unix and I'm trying to transition it to windows. It uses multiprocessing and I understand it's an issue with being forced to use spawning

Converting a tf.dataset to a PyTorch Dataset?

I'm working on this project where all the data comes preprocessed and ready as a tensorflow datasets which looks like this: <MapDataset shapes: {input_ids: (

(Keras) ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type float)

I know this problem has been answered previously in the link below,but it does not apply to my situation.(Tensorflow - ValueError: Failed to convert a NumPy arr

Batchnormalize, Dropout and number of layers

I'm learning batchnormalisation and dropout. Saw this https://www.kaggle.com/ryanholbrook/dropout-and-batch-normalization. The model model = keras.Sequential([

AttributeError: 'Sequential' object has no attribute '_get_distribution_strategy'

I am following an online course through linkedin regrading the Building of models through Keras. This is my code. (This is claimed to work) import pandas as p

How to use tensorflow 2.0 with AWS Lambda?

I am new to AWS Lambda and running a tensorflow model in AWS Lambda. Now tensorflow 1.0.0 is the one that fits into the 50Mb limit but since tensorflow 2.0 is

TensorFlow: How do I generate a dataset from two arrays?

I've been trying to generate a custom dataset from two arrays. One with the shape (128,128,6) (satellite data with 6 channels), and the other with the shape (12