Stack Overflow
Stack Overflow

Questions tagged [transfer-learning]

749 questions
0
votes
0 answers

Transfer Learning in Keras

It is possible to download weights for any CNN from the keras repository directly during execution of the program using : model = VGG16(weights='imagenet', include_top=True, input_shape = (224, 224, 3)) but is it possible to download the weights…
Jeet Sensarma
  • 23
  • 4
0
votes
0 answers

Transfer learning in TF Object Detection API: How to train only the last few layers with weights?

I borrowed everything from TF/Model_Zoo (the config files and the model files as is), and started the training by using my images and annotations without changing the config file other than the paths. In the original config files, there is no…
Selin Tosun
  • 1
  • 2
0
votes
0 answers

Neural Network stuck at training

Hello everyone I started training a network ana it got stuck, it did not finish the first epoch. Here is the code I used: top_model_weights_path = '/data/fc_model.h5' img_width, img_height = 150, 150 -train_data_dir =…
Oussama
  • 603
  • 6
  • 10
  • 18
0
votes
0 answers

Training accuracy reaches 1.0 after the first training epoch

I am working on a transfer learning model (based off of Vgg19) with the following architecture. _________________________________________________________________ Layer (type) Output Shape Param…
Milad M
  • 1,538
  • 2
  • 13
  • 13
0
votes
1 answer

Error specifying convolutional base from pre-trained XCeption-architecture with keras in R under Windows

Is there something really obvious that I am doing when trying to use the convolutional base from the XCeption architecture pre-trained on ImageNet? Here is my code that produces the error at the end of the question: require(keras) conv_base1 <-…
Björn
  • 644
  • 10
  • 23
0
votes
1 answer

Where can I download pretrained weights for tensorflow.contrib.slim.nets?

I see various places on the web and even in code from a homework assignment that just seems to know where pretrained checkpoints for various tf-slim models can be downloaded. Example:…
Joey Carson
  • 2,973
  • 7
  • 36
  • 60
-1
votes
1 answer

Load weights to new model, how much have been correctly loaded?

I want to load the weights from model A to model B. Model B last few layers are a bit different, thus the weights for those layers should not be loaded. I'm using load_weights with parameters such that layer that are different are…
n0tis
  • 750
  • 1
  • 6
  • 27
-1
votes
1 answer

python transfer art cartoon with custom dataset

How can I cartoonize images with the model trained with a custom dataset? There are projects on the internet that cartoonize pictures with library methods without a dataset, but I couldn't find a project source for the purpose I wanted. Could you…
Sery Can 21
  • 13
  • 1
-1
votes
1 answer

What's The Best Pre-Trained Model (Transsfer Learning) Based On Problem Or Images?

How choose the best pre-trained model (transfer learning) for a particular image processing problem based on the type of problem; medical, biological and etc and even based on images; objects that not different in colors but in shapes or even are…
Soroush Mirzaei
  • 331
  • 2
  • 12
-1
votes
1 answer

Why is transfer learning using VGG16 bad for image coloursatinon

im working on training a model to colorise black and white images. so far, ive found 2 methods; transfer learning using vgg16 autoencoder from scratch ive did both and noticed transfer learning using vgg16, although it trains faster, it produce…
Vortekus
  • 69
  • 1
  • 9
-1
votes
1 answer

use weight transfer learning trained in customer data after training in another customer data

I hope you are well I have a question can I train transfer learning like pre-trained model 'vgg16' trained on ImageNet in my customer data and save weight to train another customer data? How I can do this, please Thanks for ur time
Asma Hekal
  • 19
  • 3
-1
votes
1 answer

Keras Applications (Transfer Learning)

I am a student and currently studying deep learning by myself. Here I would like to ask for clarification regarding the transfer learning. For example MobileNetv2 (https://keras.io/api/applications/mobilenet/#mobilenetv2-function), if the weights…
JunJie Lim
  • 13
  • 4
-1
votes
1 answer

How can I fine-tune EfficientNetB3 model and retain some of its exisiting labels?

I've tested EfficientNetB3 model (trained on ImageNet) on my large image set and it recognizes some classes of images that I have with varying accuracy, the others are not recognized at all. For example, it does a great job for school buses:…
Wodzu
  • 6,932
  • 10
  • 65
  • 105
-1
votes
1 answer

Training and testing with embeddings in transfer learning

I am doing transfer learning with google audioset embeddings. According to the documentation, the embedding layer does not include a final non-linear activation, so the embedding value is pre-activation I want to train and test a new model on top…
Sabid Habib
  • 419
  • 1
  • 4
  • 16
-1
votes
1 answer

Can I use pretrained YOLO for a regression task?

I'm planning to do it using YOLO for a CNN supervised regression task. Given an image, predict the number of times it will be viewed. I'm inclined on using YOLO as it is an object detector. Highly viewed photos mostly contain objects(face, animals,…
Rayleigh
  • 20
  • 5
1 2 3
…
49 50