Questions tagged [transfer-learning]

The tag has no usage guidance.

1
vote
0answers
20 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
23 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 ...
4
votes
2answers
58 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
21 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
32 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
23 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
10 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
60 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
66 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
94 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
24 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
22 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
145 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
45 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
18 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
63 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
15 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
129 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
86 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
1answer
215 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
22 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
11 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
24 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
190 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
210 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 ...
1
vote
0answers
6 views

Why not mixing original training in favor of Pseudo-rehearsal?

In multiple task transfer training, I just learnt that Pseudo-rehearsal can be used to solve the problem of 'catastrophic forgetting' problem, i.e. NN forgets the original generalization while ...
1
vote
0answers
17 views

Supervisory information through side output in convolutional neural network

I am trying to implement this paper https://ieeexplore.ieee.org/document/7828014 Here they have mentioned text local (edge) and global regions as supervisory information. Side output is generated ...
1
vote
1answer
27 views

Transfer learning - small database

I am trying to use transfer learning in medical (ultrasound pictures). The problem is - I have very limited picture database = 400 (360+40). I am using resnet50 (I don't think this is important but ...
1
vote
0answers
30 views

Training InceptionV3/Resnet on custom data with CoreML/CreateML

I'm new to the CoreML/CreateML scene. I know that there is an image classifier built by Apple that can be easily trained by drag/dropping data, with pretty good accuracy. What I am wondering is, is ...
0
votes
1answer
42 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 ...
3
votes
0answers
40 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
66 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
89 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 '...
0
votes
2answers
131 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
52 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: ...
3
votes
1answer
398 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 ...
1
vote
0answers
27 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 ...
2
votes
1answer
61 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
23 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
277 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
35 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
1answer
51 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
579 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 ...
3
votes
1answer
221 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 ...
5
votes
2answers
127 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
264 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
372 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
17 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
17 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: ...