Category "deep-learning"

Keras Data Generator, show generated input and output

I implemented an own simple datagenerator based on https://stanford.edu/~shervine/blog/keras-how-to-generate-data-on-the-fly My datagenerator uses as input and

When to stop training a object detection model ( YOLOV5 )

Hi I have three metrics on validation, obj_loss, vls_loss and box_loss, which one I should look at when deciding the timing to stop the model training?

"model.fit()" sometimes takes Y_train (i.e, label/category) and sometimes not why?

in some cases we do not send any Y_train(Category/classes) and the code still works For Example:- history = model.fit( train, epochs=epochs, batch_size=Batch, v

Using only certain layers from pretrained network for transfer learning

I am building a model for human face segmentation into skin and non-skin area. As a model, I am using the model/method shown here as a starting point and adding

How to implement IoU-like metric to monitor boundary intersection?

How to implement boundary metric in keras? I mean something like IoU but monitoring boundary over union during training? I found how to define iou metric, how d

In RNN, I am unable to understand how time steps are mapped to the Output shape

In Simple RNN Layer, number of units corresponds to the output shape specification. If unrolled, each time steps can be represented as a separate layer. But I a

Deep neural network gives a constant value as output

I have implemented a neural network from scratch. I have taken random values as both input and output. When I use a single layer( with sigmoid activation) the n

Faster RCNN - Number of epochs impact inference time

I have trained two Faster RCNN models with the exact same parameters with the exception of: Model 1: 150 epochs Model 2: 5 epochs Once the models have been trai

What are the numbering here for my model.summary()? I cannot understand clearly what the .summary() implies here

I know about the embedding layer, bidirectional LSTM and dense layers as well. However, I don't understand clearly that what are the numbering actually doing he

CUDA cuDNN: cudnnGetConvolutionForwardWorkspaceSize fails with bad parameter

I am currently trying to implement a very basic 2D convolution using CUDA cuDNN between an "image" of size 3x3 and a kernel of size 2x2, resulting in a 2x2 outp

Why do I get a Conv2D error trying to run Conv1D layer?

I am trying to write a simple 1 dimensional convolution with a regression (1 dimensional float) output. model = Sequential() model.add(Conv1D(filters=1, kernel_

How to fix the error where the target batch size does not match when I use CrossEntropyLoss function?

I am working on a trainning task with CNN. When I created the loss function with CrossEntropyLoss and trained the dataset, the error reminded me that the batch

Deep Learning Image Detection - Help needed deciphering machine learning loss and accuracy graph and finding solutions to fix model

I have an imbalanced dataset from Google OpenImages of 6 classes Train (starfish=439; Dolphin = 890; Turtle = 1362; Fish = 6216; Jellyfish = 733; Shellfish = 11

How do you implement SVoice?

I'm trying to use Facebook's SVoice to split out different speakers in my audio file using python. I found a library that implemented it here: https://github.co

Loss function for changing a classification network to a regression one

I am trying to change a neural network that classifies pointclouds into 40 different classes, to a regression networks that predicts a specific property of them

movie similarity using Word2Vec and deep Convolutional Autoencoders

i am new to python and i am trying to create a model that can measure how similar movies are based on the movies description,the steps i followed so far are: 1.

apply ResNet on CIFAR10 after resizing (pyTorch)

Given a pre-trained ResNet152, in trying to calculate predictions bench-marks using some common datasets (using PyTorch), and the first RGB dataset that came to

DNN model with maxout activation in tensorflow

How can I make this DNN model in tensorflow? 31 neurons in the first, 10 in the second, 5 in the third hidden layer, and 2 neurons in the output layer. The acti

ValueError: Input 0 of layer lstm_14 is incompatible with the layer: expected ndim=3, found ndim=4. Full shape received: [None, 12, 12, 64]

I am using CNN-LSTM network for image classification. My image size is (224, 224, 3) and batch size is 90. I m getting this error when i passing input to LSTM l

Fit unequal data into Linear Regression Model

How do I fit two unproportional arrays to a regression model? Is it possible to resize/reshape one without loosing the data? I used the code from here but my tr