The Stack Overflow podcast is back! Listen to an interview with our new CEO.

Questions tagged [transfer-learning]

The tag has no usage guidance.

Filter by
Sorted by
Tagged with
0
votes
1answer
12 views

Transfer learning VGG16 does not work as expected. (Detect tacos as hamburgers)

I am new in this field of machine learning, to test I wanted to do a simple project. Create a cnn capable of recognizing hamburger images. As I do not have the ability to collect more than 10,000 ...
0
votes
0answers
13 views

ResNet50 Model is not learning with transfer learning in keras

I am trying to perform transfer learning on ResNet50 model pretrained on Imagenet weights for PASCAL VOC 2012 dataset. As it is a multi label dataset, I am using ...
0
votes
1answer
18 views

Can I save only some VGG19's layers into a .H5 file?

I am training a deep-learning style transfer model with the pretrained-VGG19 CNN. My aim is to use it in my Android app for personal purposes with Google Firebase Machine Learning Kit (which would ...
1
vote
0answers
17 views

Transfer Learning and Recommender Systems

I have a task in which I am pretending to have an "unobserved" system, let's call it the target system, that I am using an LSTM from a similar system that has observations to perform the regression. I ...
0
votes
1answer
30 views

Smallest Possible Dataset for Text Classification using BERT

What are your experiences for appropriate dataset sizes for usual text classification tasks using a finetuned BERT such as sentiment analysis? ~100 examples ~1000 examples ... ~10000000 examples ...
0
votes
1answer
8 views

layers of transfer learning

The disadvantage of using transfer learning is that it cannot be layered to reduce the number of parameters. In that statement what are the layers of transfer learning and the number of parameters?
2
votes
1answer
62 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?
1
vote
1answer
18 views

Hybrid classification neural network

I have product data and I need to classify products to categories (for example Lenovo laptop to Laptops category, etc.), each product has properties such as: description list with image URLs (...
0
votes
0answers
23 views

How to do transfer learning with limited data

I'm working on point cloud classification problem. I'm building a NN to classify point cloud. I found a really nice architecture that I want to use, called point net that receive a set of ordered ...
2
votes
1answer
104 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?
1
vote
1answer
20 views

Using data agumentation for a frozen pre-trained model

I was following the following article with regards to doing transfer learning: https://blog.keras.io/building-powerful-image-classification-models-using-very-little-data.html In the section, Using ...
0
votes
0answers
17 views

Fine-Tuning VGG16 : how to get features maps of training examples before fully-connected layers

I am working on a classification problem in a project. The specificity of my problem is that I have to use two different type of data to manage it. My classes are Car, Pedestrian, Truck and Cyclist. ...
1
vote
1answer
65 views

Are mainstream pre-trained models useful as discriminators?

In the context of GANs I see many papers designing new discriminator networks. I'm curious about the usefulness of designing discriminators as modified versions of mainstream models like Inception, ...
0
votes
0answers
26 views

using dataset to classifying and labelling another unlabeded dataset

I collect a collection of posts from Facebook and I use a published sentiment datset to labeling my collected dataset. is this a right technique and what its name is this transfer-learning ?
0
votes
1answer
104 views

Transfer learning VGGish (AudioSet). Impact of zero padding to fit the input size

I am trying to train a network on top of the VGGish architecture (https://github.com/tensorflow/models/tree/master/research/audioset/vggish), using (transfer learning) finetuning. I initially started ...
0
votes
0answers
30 views

Why gpt-2 could apply to other tasks without fine-tune?

Language Models are Unsupervised Multitask Learners https://github.com/openai/gpt-2
0
votes
0answers
18 views

Problem regarding designing the generator function

I am implementing the paper Perceptual GAN for small object detection. The design is described by the picture given below. I have used Transfer Learning concept and used a pretrained model inside the ...
0
votes
0answers
10 views

Pretrained model entirely losing its properties

I am a newbie in the field of deep learning, so advance apologies if any mistake is there. I was trying to use pretrained models like BERT and GPT2 for generating language in our native language (say, ...
0
votes
0answers
11 views

How to get model predictions on all classes after applying Transfer Learning?

I have been following transfer learning with TFHub to implement transfer learning in my model for text classification. However, I do not understand how to get probabilities for all the classes (1000 ...
2
votes
0answers
10 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
2answers
25 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
0answers
227 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 ...
0
votes
0answers
29 views

Text classifiaction for large datasets using Transfer learning

I am trying to do text classification on a very large set of documents using the pretrained GPT model. The problem is GPT takes max sequence length $\le$ 1024. I can't truncate the data as I need to ...
0
votes
0answers
388 views

Transfer learning on yolo using keras

I am working on a project that uses object detection. I have logo images that need to be detected in a video. I am doing this in keras. I followed this blog to convert the yolo weights to a keras ...
1
vote
0answers
46 views

TensorFlow: how to restore pre-trained meta model and pass it's weights and biases to the optimizer?

I trained a model on a specific dataset and saved it as a meta, I want to restore the model and use its weights and biases on another dataset the code isn't mine but I'm trying to restore the ...
0
votes
0answers
26 views

Transfer learning, saving final FC layer only

I've written some code for transfer learning classifier using pytorch/ResNet. I replaced the final FC layer with an FC layer with the correct number of output classes. I froze all layers except for ...
5
votes
2answers
128 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 ...
2
votes
0answers
109 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 ...
2
votes
1answer
37 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 ...
1
vote
1answer
32 views

Selection of base model for transfer learning

Is there a golden rule which gives intuition on which base model needs to be used for a give image classification problem. Most of the articles gives the below details which says how to train the ...
0
votes
0answers
11 views

semi supervised learning using transfer learning and shared memory

I am reading a paper here and I am not sure I am understanding something. They claim to have 83% unsupervised on CIFAR 10, but they used something that is semi supervised. At the very least, they used ...
6
votes
0answers
186 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 ...
3
votes
1answer
75 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 ...
1
vote
1answer
922 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 ...
0
votes
0answers
43 views

Finetuning pretrained inception_v3 in pytorch

I'm following this tutorial but I'm having some trouble with inception. Every architecture works successfully, but when I run the tutorial code for inception, I get the following error: ...
1
vote
0answers
62 views

Transfer Learning with CNN layer trainable True - Accuracy not improving

I am working on a image classification problem with 4 classes. And I am using Transfer Learning (Resnet50) to train the model. Below are the observation. Pre-trained weights are from ...
1
vote
0answers
558 views

Keras load pre-trained weights. Shape mismatch

I have some trouble loading pre-trained weights with Keras. Let's say I have a keras model model and that my weights are stored at ...
2
votes
0answers
126 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 ...
0
votes
1answer
27 views

How to measure the performance of a domain adaptation /Transfer learning technique? [closed]

Given that the performance you achieve depends on how far the target from the source domain is, how can you judge the performance of an algorithm?
1
vote
0answers
119 views

Output range of BERT model shrinks after fine-tuning on domain specific dataset

My model's sigmoid output range has shrunk after transfer learning with small a dataset. My pretrained model has an output range of 0 to 1. After fine-tuning with a smaller domain specific dataset, ...
0
votes
0answers
19 views

How to merge 2 Neural Network weight model with different classification?

I'm new in this stream and got a stuck at a question, is it possible to merge 2 NN weight model (compiled and trained with the same architecture InceptionV3) with different classes of classifications (...
2
votes
3answers
357 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 ...
2
votes
2answers
129 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 ...
0
votes
2answers
821 views

Over fitting in Transfer Learning with small dataset

I am using Transfer Learning to perform image classification. Base model used : Resnet50 using ImageNet dataset ...
0
votes
1answer
28 views

How to input different sized images into transfer learning network

I have been looking online for a solution but have a difficult time finding a clear enough solution. I want to know how to use transfer learning (VGG16 for example) on images that have different sizes ...
0
votes
0answers
15 views

Domain Adaption with different tasks and domains

I know there exist plenty of deep learning algorithms for domain adaption (ADDA, DIRT-T, etc..), as long as the task keeps the same, e.g. I want to transfer knowledge from SVHN dataset to MNIST ...
0
votes
0answers
33 views

Can transfer learning be applied to predict sales

Let matrix A be a user item matrix.Upon performing UV decomposition , I get a user factor matrix and factor entity matrix. The company I am interning at doesn't keep track of the user factor matrix.I ...
2
votes
1answer
346 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 ...
2
votes
1answer
328 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 ...