Category "neural-network"

Gradio - Pytorch MNIST Digit Recognizer

I watched the following video on YouTube https://www.youtube.com/watch?v=jx9iyQZhSwI where it was shown that it is possible to use Gradio and the learned model

PyTorch bool value of tensor with more than one value is ambiguous

I am trying to train a neural network with PyTorch, but I get the error in the title. I followed this tutorial, and I just applied some small changes to meet my

How to handel Imbalance data while using LSTM

I am doing a project on an online signature verification system using RNNs LSTM. In the project, I am facing a problem while using the signatures as LSTM trai

Can I perform non-text sequence classification in fastai?

I am trying to figure out if I can use fastai for my problem. I am trying to classify sequences of floats. Each sequence is a vector of 24 floats. In principle,

Splitting an ONNX DNN Model

I'm trying to split DNN Models in order to execute part of the network on the edge and the rest on the cloud. Because it has to be cross-platform and work with

Activation function on the hidden layers for Regression models in neural networks

I am trying to predict a single output value,y, using two input features. I read that regression models usually don't use any activation function, and even when

Train multi-output regression model in pytorch

I'd like to have a model with 3 regression outputs, such as the dummy example below: import torch class MultiOutputRegression(torch.nn.Module): def __init

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

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

Tensorflow error: ValueError: Shapes (128, 100) and (128, 100, 139) are incompatible

I try to use Functional API for my model, but i don't understand why i have error: ValueError: Shapes (128, 100) and (128, 100, 139) are incompatible My code:

How can one use the RemoveIsolatedNodes transform in Pytorch Geometric?

I am trying to run a graph classification problem in pytorch-geometric and I see that some of my graphs contain isolated nodes (which can cause problems). For e

The method np_utils.to_categorical give me an error

np_utils.to_categorical Keras method give me an error when i gived it a a vector of [962] element which contain 3 classes [1,1,1,...,2,2,2,...3,3,3]. The used

Moving averaging of Loss during Training in Keras

I am using Keras with TensorFlow to implement a deep neural network. When I plot the loss and number of iterations, there is a significant jump in loss after ea

Missing val_acc after fitting sequential model

I am missing information about the 'val_acc' attribute when I fit a compiled sequential model. I have a sequential model that is compiled with 'accuracy' metr

ValueError: Input 0 of layer hiddenL1 is incompatible with the layer: its rank is undefined, but the layer requires a define rank

I am trying to create a sequential keras model with custom weights. The weights come from a row in a numpy array. When running the code I get the error: Value

Early stopping in Bert Trainer instances

I am fine tuning a BERT model for a multiclass classification task. My problem is that I don't know how to add "early stopping" to those Trainer instances. Any

How to define a specific keras layer weight as non-trainable?

Let's suppose we have a neural nets with three layers : Inputs > Hidden > Outputs and consider that the weigths between the Hidden and Outputs layers are

One box object detection

I am using a faster rcnn model to predict one object in an image. There can only be one object in each image. Is it possible to force Faster Rcnn to train and p

Google Colab GPU RAM depletes quickly on test data but not so on training data

I am training my neural network built with PyTorch under Google Colab Pro+ (Tesla P100-PCIE GPU) but encounters the following strange phenomenon: The amount of

How to save the model weights after running train_detector in mmdetection?

cfg.optimizer.lr = 0.02 / 8 cfg.lr_config.warmup = None cfg.log_config.interval = 600 # Change the evaluation metric since we use customized dataset. cfg.evalua