Stack Exchange Network

Stack Exchange network consists of 174 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

Questions tagged [transfer-learning]

The tag has no usage guidance.

0
votes
1answer
9 views

Preprocessing for finetuned CNN model from pretrained models

Is it necessary to preprocess the images the same way as they were during the training of pretrained models in our finetuned model to use it for a different classification task ? Say, I have a ...
2
votes
0answers
32 views

How to help neuronal network with an other model

I am working on an image classification problem, the input data normally is images to classify, but I thought latitude and longitude would play something on these satellite images. I sorted by ...
0
votes
1answer
33 views

Why and how BERT can learn different attentions for each head?

https://towardsdatascience.com/deconstructing-bert-distilling-6-patterns-from-100-million-parameters-b49113672f77 I read the blog above. It visualizes that different color/head has different ...
1
vote
0answers
16 views

Pre training for multi label classification

I have to pre train a model in order to do transfer learning or fine tuning in multi label classification. I'm pretraining with cifar10 dataset and I wonder if I have to use for the pre training '...
-1
votes
0answers
18 views

Is it better to cluster an image based on a feature vector or logits?

My end goal is to use supervised machine learning to find visually similar images, trained on a data set that I curated. I followed the guide here: https://www.tensorflow.org/hub/tutorials/...
0
votes
2answers
31 views

Does fine-tuning of transferred layers perform better than frozen transferred layers?

I recently learned concepts of transfer learning. Is it necessarily true that fine-tuning of transferred layers perform better than frozen transferred layer? why?
0
votes
1answer
30 views

Image features (produced by VGG19) do not properly train an ANN in Keras

I've used a VGG16 network to extract features from an image dataset, creating a features dataset using the following code: ...
-1
votes
0answers
17 views

What type of data augmentation should I do on a facial expression dataset?

I want to do data augmentation on a facial expression dataset, but I don't know what types should I use, I don't want to lose information. I want to use transfer learning on a small dataset.
1
vote
1answer
61 views

Which is the fastest image pretrained model?

I had been working with pre-trained models and was just curious to know the fastest forward propagating model of all the computer vision pre-trained models. I have been trying to achieve faster ...
0
votes
0answers
28 views

How to load the pretrain weight of layers of a DNN when adding a layer between its layers in keras?

I have a pretrain DNN network with size [a1,a2,a3,a4], I would like to do transfer learning. I want to add the layer between layer 3 and 4 so I have [a1,a2,a3,a34,a4] which showing my 5 layers. My ...
1
vote
0answers
25 views

How to implement facial attendance system using less number of images of particulars

I have a project to implement facial Attendance where I have 5-6 images of particular and when individual comes, model should map the current image with person's earlier available images so if ...
0
votes
0answers
20 views

Is it possible to perform transfer learning using kernel ridge regression or any non-iterative approach of machine leaning techniques?

kernel ridge regression can be used for regression or classification task. How can we perform transfer learning for kernel ridge regression?
1
vote
1answer
39 views

Resource and useful tips on Transfer Learning in NLP

I have a few label data for training and testing a DNN. Main purpose of my work is to train a model which can do a binary classification of text. And for this purpose, I have around 3000 label data ...
1
vote
1answer
17 views

Simple question about prediction classes of item in question vs not item in question

Let's say I wanted to use transfer learning to train a model to detect object A vs everything else. In this case, do I provide 2 types of input, images of object A and images of everything else, and ...
0
votes
1answer
91 views

Keras cNN Transfer Model: Reduce Final Model Size?

I'm working with multiple cNNs to be ran on mobile devices. If I create these cNNs from scratch (black n white, 256x256), I'm able to produce a binary classification model of about 10mb, which is a ...
1
vote
1answer
25 views

What tasks you train with one set of features and predict with another?

The most common scenario in supervised learning is to have data points with a set of features and train a model to make classification predictions afterward. Usually, for predictions to make sense ...
0
votes
0answers
11 views

How to build a sentence qulaity estimatior?

I am working on a problem where I need to predict sentence quality(say if a sentence is well written then 10,moderately written then 5 and if too many mistakes or poor formation 1/2 on a scale of 1-10)...
0
votes
0answers
176 views

Train model on new class without retraining on old classes

I created a face recognition system in which we train model on person's face , what i want is to to train them on new person's face without retaining on old man face , is it possible. Please suggest ...
0
votes
0answers
30 views

correcting conditional and marginal distribution in transfer learning

I understand that in case of transfer learning, we can have the target and the source data having different domain distributions. In such cases, authors in many papers suggest bringing the marginal ...
0
votes
0answers
377 views

Intermediate layer output from pretrained TensorFlow model

I want to use the ResNet architecture to extract features from an image. That is, I plan to pass the image through ResNet, and take the feature maps from the final convolutional layer (the one just ...
2
votes
1answer
192 views

Transfer learning by concatenating the last classification layer

Before going into an obvious XY problem, I will explain you what I'm trying to do. I'm training a simple MobileNet pre-trained with Imagenet for multiclass classification. What I do is freeze all the ...
0
votes
0answers
296 views

Error when checking : expected flatten_1_input to have shape (7, 7, 512) but got array with shape (150, 150, 3)

I have used keras to train the top layer of VGG16 on a new dataset. Then i used the saved model to make a prediction on a test image, but I encountered this error : ...
5
votes
2answers
118 views

Can neural networks be adapted without recreating them completely?

If I have, for example, a classification network which can tell if there is a dog or a cat in a picture, is it possible to adapt the network so it can also learn to detect a mouse? Without making a ...
2
votes
1answer
173 views

Fine-tuning NLP models

In computer vision, if we don't have a large training set, a common method is to start with a pre-trained model for some related task (e.g., ImageNet) and fine-tune that model to solve our problem. ...
3
votes
1answer
157 views

Keras bug NasNetlarge no top

I am trying to use NasNetlarge in Keras without the top but I cant get rid of the top: ...
1
vote
0answers
15 views

Domain adaption vs. heirarchical model - when to use which?

I know a little bit about domain adaption and also about random effects models, but I'm a little unsure if they're at all compatible. Domain adaptive models (based on ANNs) usually try to find some ...
1
vote
0answers
15 views

How to change the pooling to adaptpooling before FC layer in the Inception-ResnetV2 model in keras

Now I am using the keras model: Inception-ResnetV2 to do image classification using transfer learning. The main code about this model is as following: ...
2
votes
0answers
118 views

GTX 1080t ti rans out of memory

I have 60000 images divided into two classes. I have tried to build transfer learning with pretrained ResNet50 but my new GTX 1080 ti returns -1 after couples of epochs. My guess is that it runs out ...
3
votes
2answers
838 views

Is there any proven disadvantage of transfer learning for CNNs?

Suppose I know that I want to use a ResNet-101 architecture for my specific problem. There are ReseNet-101 models trained on ImageNet. Is there any disadvantage of using those pre-trained models and ...
2
votes
1answer
1k views

What are the consequences of not freezing layers in transfer learning?

I am trying to fine tune some code from a Kaggle kernel. The model uses pretrained VGG16 weights (via 'imagenet') for transfer learning. However, I notice there is no layer freezing of layers as is ...
1
vote
2answers
17 views

a simple way to test wether a tree-based classifier would transfer well to a target population?

I trained a tree-ensemble classifier (XGBOOST) on population A, validated it and I'm satisfied with its accuracy (AUC 0.78). Now I'm trying to transfer it to a slightly different population B, and ...
1
vote
0answers
456 views

Transfer learning: Poor performance with last layer replaced

I am using a transfer learning approach. For this I followed the tensorflow for poets tutorial. I use a pre-trained InceptionV3 architecture trained on the Imagenet dataset. The last layer and the ...
0
votes
0answers
38 views

Knowledge Distillation

I'm trying to use Knowledge Distillation by Hinton on a Keyword Spotting Algorithm. I deicided to implement the KWS with a Convolutional Neural Network, trained on google SpeechCommand Dataset. I ...
5
votes
2answers
2k views

Why is input preprocessing in VGG16 in Keras not 1/255.0

I am just trying to use pre-trained vgg16 to make prediction in Keras like this. ...
1
vote
0answers
60 views

Where to find pre-trained models for transfer learning [closed]

I am new to the machine learning field, but I wanted to try and implement a simple texture classification algorithm with Keras (to give a clear idea about what I mean as 'texture', [this][1] is the ...
2
votes
1answer
541 views

Transfer learning (on pre-trained inception net model) for multi label classification is giving similar probability for all labels

Number of labels: 1000, Dataset size: 200000 images Final probability for 1000 labels is in the range of 0.3 to 0.34. I was expecting large variation in probabilities. Can someone tell me what I am ...
5
votes
2answers
567 views

What is the purpose of untrainable weights in Keras

In this page it is mentioned that when trainable=false, the weight won't be updated and is used for optimization, too. But I still do not understand how it can be ...