Questions tagged [transfer-learning]

The tag has no usage guidance.

Filter by
Sorted by
Tagged with
9
votes
1answer
422 views

How to arrange the dataset/images for CNN+LSTM

I am working on an image classification problem using Transfer Learning with Resnet50 as base model (in Keras) (For example Class A and Class B). There is a time factor involved in this ...
6
votes
3answers
4k 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 ...
6
votes
2answers
1k 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 ...
6
votes
2answers
8k views

Default value of learning rate in adam optimizer - Keras

I am working on a image classification problem using Transfer Learning. Parameters used given below: Adam optimizer with learning rate - 0.0001 ...
6
votes
2answers
8k 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 ...
6
votes
2answers
9k 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. ...
5
votes
2answers
344 views

Feeding 3 consecutive video frames to a CNN to track a tennis ball

I want to use CNN transfer learning to track a tennis ball from TV broadcasts of tennis matches. I used VGG annotating tool annotation tool link (use version 1 of the tool for compatibility with ...
5
votes
2answers
136 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 ...
5
votes
2answers
863 views

meaning of fine-tuning in nlp task

There are two types of transfer learning model. One is feature extraction, where the weights of the pre-trained model are not changed while training on the actual task and other is the weights of the ...
5
votes
1answer
275 views

How to use MNIST dataset to make predictions on similar images (colorblindness charts)?

I am trying to use the MNIST dataset to train a convolutional neural network to classify digits written in colorblindness charts. As some people have suggested, I have tried playing with the ...
4
votes
2answers
213 views

Why are results without Transfer Learning better than with Transfer Learning?

I developed a neural network for license plate recognition and used the EfficientNet architecture (https://keras.io/api/applications/efficientnet/#efficientnetb0-function) with and without pretrained ...
4
votes
1answer
149 views

Make the CNN to say “I don't know”

I am currently working on an image classification problem. To ease the implementation I used transfer learning in Keras with ...
4
votes
2answers
2k views

How to add a CNN layer on top of BERT?

I am just playing with bert (Bidirectional Encoder Representation from Transformer) Research Paper Suppose I want to add any other model or layers like Convolutional Neural Network layers (CNN), Non ...
4
votes
1answer
268 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 ...
3
votes
3answers
2k views

Neural Network Model using Transfer Learning not learning

I am a beginner in Deep Learning and working on Road Crack detection using transfer learning. I am working on binary classification with two classes , crack and no crack. My distribution of two ...
3
votes
1answer
1k 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 ...
3
votes
1answer
537 views

incremental learning vs transfer learning

Can anyone explain me how incremental learning differs from transfer learning with example? Also does Transfer learning limited to neural networks?
3
votes
1answer
729 views

How to properly resize input images for transfer learning

I have to resize some images of different size to 224x224 before they can be passed as input for VGG19, and then apply ...
3
votes
0answers
28 views

What's the definition of retrainingļ¼Ÿ

In transfer learning, we always use new data to retrain the pre-trained model. But, what is the specific and official definition of retraining? Or what papers mentioned this definition, in transfer ...
3
votes
1answer
97 views

Transfer Learning Question: Extending the Functionality of a Multipose-Estimation Machine Learning Model?

I have experimented with a number of different machine learning models used for pose estimation. Most of them output a heatmap and offsets for the detected person(s) in the image. I really like the ...
3
votes
1answer
51 views

How to choose layer from which to unfreeze image classification model

I'm wondering what steps do you take to decide on the part of the model to unfreeze. Do you do multiple experiments? Since the use of GPU is expensive, you must have some guidelines. Note: I know ...
3
votes
0answers
53 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 ...
3
votes
1answer
781 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: ...
2
votes
2answers
351 views

How to add a new category to a existing trained deep learning model?

i have trained my deep learning model initially with 5 classes now i want to add another class without training the whole model over again for those 5 classes. How can I do that?
2
votes
2answers
357 views

Why do I need pre-trained weights in transfer learning?

I am using a Mask-RCNN. I first chose the resnet50 backbone then downloaded COCO pre-trained weights. Why do I need pre-trained weights for transfer learning? The transfer learning approach is to ...
2
votes
2answers
41 views

Does partial transfer learning require a lot of computer power?

I want to be sure my understanding of the problem is correct. I want to do image classification and current state of the art in my field is achieved by transfer learning with VGG16. Since image on ...
2
votes
1answer
706 views

Why is performance worse when my time-series data is not shuffled prior to a train/test split vs. when it is shuffled prior to the split?

We are running RandomForest model on a time-series data. The model is run in real time and is refit every time a new row is added. Since it is a timeseries data, we set shuffle to false while ...
2
votes
1answer
57 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 ...
2
votes
1answer
410 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. ...
2
votes
1answer
765 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 ...
2
votes
1answer
129 views

Existing pre-trained NLP models to detect if a text input is a question

I would like to quickly filter text data into question and non-questions. Using the presence of question mark in the text is too crude. Are there any existing models I can use to aid me with my task?
2
votes
4answers
28 views

Image Classification using Single Class Dataset using Transfer Learning [closed]

I only have around 1000 images of vehicle. I need to train a model that can identify if the image is vehicle or not-vehicle. I do not have a dataset for not-vehicle, as it could be anything besides ...
2
votes
1answer
51 views

Transfer learning for a regression problem

if my understanding is correct, in case of image classification and NLP, if I have a pre-trained model, to train on new data, I can reshape the data according to the pre-trained model. So there is no ...
2
votes
1answer
101 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 ...
2
votes
1answer
44 views

Any useful tips on transfer learning for a text classification task

I am doing a supervised binary text classification task. I want to classify the texts from site A, site B, and site C. The in-domain performance looks OK for texts of each site. (92%-94% accuracy). ...
2
votes
1answer
306 views

Error when trying Transfer Learning

I'm trying to train a model which is an extension of Google's Inception-V3 for the purpose of recognizing and classifying whether there is any pneumonia using x-ray images. I've used Tensorflow-Hub ...
2
votes
0answers
32 views

Real-life applications/examples of transfer learning approaches

I recently read a nice, informative paper titled 'A Survey on Transfer Learning'. It mentions 3 settings of transfer learning - inductive, transductive, and unsupervised. At the same time, it states ...
2
votes
1answer
125 views

Why is convnet transfer learning taking so long?

I am using transfer learning to train a binary image classification model using keras' pretrained VGG16 model. The code can be found below : ...
2
votes
2answers
470 views

Model not learning when using transfer learning

I am working on a personal project on image classification (two classes) and am trying to see how the MobileNet v2 structure would perform. While training the training accuracy is already quite high ...
2
votes
0answers
14 views

Confusion regarding prediction results of SVM and ANN on feature vectors

I am making a custom image classifier using Transfer Learning on Inception V3. I have 3 classes of images with ~6K images each. The input dimension of the network is 500X500 and the output of the ...
2
votes
1answer
564 views

How does BERT deal with catastrophic forgetting?

In the ULMFit paper authors propose a strategy of gradual unfreezing in order to deal with catastrophic forgetting. That is, when the model starts be fine-tuned according to a downstream task, there ...
2
votes
0answers
217 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 ...
1
vote
2answers
387 views

Is Flatten() layer in keras necessary?

In CNN transfer learning, after applying convolution and pooling,is Flatten() layer necessary? I have seen an example where after removing top layer of a vgg16 ,first applied layer was ...
1
vote
2answers
83 views

How many layers should I replace in transfer learning CNN

I am designing a convolutional neural network that I believe requires transfer learning to function in practice. The network will be a character level CNN for text classification, more specifically, ...
1
vote
2answers
145 views

Imbalanced Dataset (Transformers): How to Decide on Class Weights?

I'm using SimpleTranformers to train and evaluate a model. Since the dataset I am using is severely imbalanced, it is recommended that I assign weights to each ...
1
vote
1answer
26 views

Daily new data for my neural network, and I want transfer(?) learning

I made my neural network, it is pre-trained for 180 days of data. ...
1
vote
2answers
35 views

Why does Transfer Learning works better on smaller datasets than on larger ones?

This question is not about the utility of Tranfer Learning compared with regular supervised learning. 1. Context I'm studying Health-Monitoring techniques, and I practice on the C-MAPSS dataset. The ...
1
vote
1answer
86 views

Understanding Transfer Learning of Word Embeddings

I can't quite visualize how transfer learning of pre-trained word embeddings is useful in an NLP task( say named entity recognition ) . I'm studying Andrew NG's Sequence Models course and he seems to ...
1
vote
2answers
293 views

PyTorch: How to use pytorch pretrained for single channel image

If I have to create a model in pytorch for images having only single channel. How can I transform my model to adopt to this new architecture without having the need to compromise the pre-trained ...
1
vote
1answer
132 views

Comparison with transfer learning and CNN from scratch on a small dataset

I am doing image classification with CNN, and I have a training set of 3200 imges and a training set of 400 images. I have used two different approches for doing this classification : Transfer ...