Category "deep-learning"

Error in loading image_dataset_from_directory in tensorflow?

This is the code from https://keras.io/examples/vision/image_classification_from_scratch/ import tensorflow as tf from tensorflow import keras from tensorflo

Pytorch nn.CrossEntropyLoss() always returns 0

I am building a multi-class Vision Transformer Network. When passing my values through my loss function, it always returns zero. My output layer consisits of 37

How to improve the visibility of numbers on license plate for OCR

I am using easyocr methods to recognize the text on the license plate but the results are not good. I have developed deep learning model which detects license p

AttributeError: 'Model' object has no attribute '_distribution_strategy'

I'm trying to train a UNet, but for some reason I get the following error: Traceback (most recent call last): File "<ipython-input-54-b56497e81356>", l

Apply Tensorflow tf.keras.initializers.GlorotNormal(seed=1) to tf.Variable

How to apply the initializer to the tf.Variable function? Am I on the right track? def initialize_parameters(): initializer

Keras ValueError: Dimensions must be equal - How to pass label-dependent values to custom loss function

I have a keras model with 5 outputs. My labels include 5 values to compare these to, but also 25 additional values representing a correlation matrix for the 5 v

Evaluate model result for multitask learning with keras

I designed a CNN for a multitask classification in keras, where I have one input and two different class of classes in output. I compiled the model in this way

Evaluate model result for multitask learning with keras

I designed a CNN for a multitask classification in keras, where I have one input and two different class of classes in output. I compiled the model in this way

Training simple CNN-LSTM model

I have a task for my project paper and I do not get how to train the model. This model is supposed to take an image and segment it into different classes. The h

dice coefficient and dice loss very low in UNET segmentation

I'm doing binary segmentation using UNET. My dataset is composed of images and masks. I divided the images and masks into different folders ( train_images, trai

RTX 3070 compatibility with Pytorch

NVIDIA GeForce RTX 3070 with CUDA capability sm_86 is not compatible with the current PyTorch installation. The current PyTorch install supports CUDA capabilit

Use multiple images for batch inference cppflow C++

I'm trying to use cppflow library in windows 10 x64 machine in VS2019 C++. I want to inference my model for batch of images (vector <cv::Mat> ). I write a

Keras CNN, Incompatible shapes: [32,20,20,1] vs. [32,1]

I'm trying to reconstruct in Python the Gradient Transformation Network model in the paper titled : Single Image Super-Resolution Based on Deep Learning and Gra

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

Variational Autoencoder KL divergence loss explodes and the model returns nan

I'm training a Conv-VAE for MRI brain images (2D slices). the output of the model is sigmoid, and the loss function binary cross-entropy: x = input, x_hat = out

Onnxruntime NodeJS set intraOpNumThreads and interOpNumThreads by execution mode

I'm using Onnxruntime in NodeJS to execute onnx converted models in cpu backend to run inference. According to the docs, the optional parameters are the followi

Deep Reinforcement Learning - CartPole Problem

I tried to implement the most simple Deep Q Learning algorithm. I think, I've implemented it right and know that Deep Q Learning struggles with divergences but

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

Deep learning CNN: low accuracy

I am training a convolutional neural network for binary time series classification. The training accuracy on both models is very different. If on the first it g

LSTM model fails

enter image description here model = Sequential() model.add(LSTM(units=32, return_sequences=True, input_shape=(training.shape[1],1))) model.add(Dropout(0.2)) mo

Other Categories