Stack Overflow
Stack Overflow

Questions tagged [pre-trained-model]

A machine learning model created by someone else. Questions about the practical use and implementation details (using a pretrained model as a starting point, or benchmark) are allowed; however, questions about the theory behind these models are off-topic.

A machine learning model created by someone else. Questions about the practical use and implementation details (using a pretrained model as a starting point, or benchmark) are allowed, questions about the theory behind these models are off-topic and should be asked on the Artificial Intelligence site.

505 questions
0
votes
0 answers

How to Proceed with Fine-Tuning and Testing InceptionV3 in Keras?

I was going through the documentation on Keras alongside previous questions and responses here on StackOverFlow. Currently, this is what I have so far: #Creating base pre-trained model (Default Input Size for ResNet50 is (299, 299)) base_model =…
CodingPoding
  • 33
  • 2
  • 9
0
votes
1 answer

tensorflow inception retrain

I was following this tutorial at https://www.tensorflow.org/versions/master/tutorials/image_retraining After I went through a few hurdles, I got retrain.py running. Then I realized the new model was only able to classify images for the new…
Han
  • 1
  • 2
0
votes
1 answer

Fine Tuning dimensionality error

I am trying to use Resnet50 for image classification problem. However it shows error and I could not fix it. RuntimeError: inconsistent tensor size, expected tensor [120 x 2048] and src [1000 x 2048] to have the same number of elements, but got…
soshi shimada
  • 425
  • 1
  • 7
  • 21
0
votes
0 answers

Insert and train an additional layer between trained lstm layers and output layers

Here is what I wanna do: I want to use some transfer learning techniques to deal with sequence problems: First use dataset_1 to train a lstm model, Second insert another lstm layer before the output layer, and then use dataset_2 to only…
Mountain_y
  • 1
  • 2
0
votes
1 answer

Keras InceptionV3 model.predict

Code: from keras.applications import InceptionV3 model = InceptionV3(weights="imagenet") shape = (None,image_size,image_size,num_channels) x = tf.placeholder(tf.float32, shape=shape) adv_x,grad_x = fgm(x, model, model.predict(x),…
Yash Sharma
  • 33
  • 5
0
votes
1 answer

ValueError: Error when checking target: expected dense_2 to have 4 dimensions, but got array with shape (64, 50) (Keras)

While training pretrained model using Keras in such a way: baseModel = keras.applications.resnet50.ResNet50(include_top=False, weights='imagenet') t = baseModel.output t = MaxPooling2D()(t) t = Dense(1000, activation='relu',…
Firsttry
  • 319
  • 1
  • 3
  • 6
0
votes
0 answers

load_weights failing : the order of weight values changed in keras

This is my network. I loaded weights and then fine tuned the network. the architecture remained same throughout. But when I loaded the weights after fine tuning( block5 and fc layers trainable), the order of weights in the weights values have…
Hooli
  • 711
  • 2
  • 13
  • 24
0
votes
1 answer

How to Retrain Inception's Final Layer for New Categories

I used the retraining example for inception on TF Retrain Inception but I get an error if I try to classify an image. I used the following code - is the code for classification wrong or is there a problem with my memory allocation? import tensorflow…
user3483676
  • 177
  • 1
  • 8
0
votes
1 answer

where is the graph file of open images pretrained model?

I need the graph file(.pb file) of pretrained openimages dataset. After downloading the model there are only 3 files labelmap.txt model.ckpt model.ckpt.meta Where can I find the .pb file?
MysticForce
  • 1,253
  • 1
  • 16
  • 27
0
votes
0 answers

TypeError: RunCppShapeInference() takes exactly 5 arguments (6 given)

I am getting this error TypeError: RunCppShapeInference() takes exactly 5 arguments (6 given) while running the pretrained vgg16 net. Can anyone tell me what is the problem. from keras.models import Sequential from keras.layers.core import Flatten,…
Asad Mahmood
  • 154
  • 1
  • 12
0
votes
1 answer

How to use a pretrained model with Tensorflow?

I know that the following is an already answered question, but even though i tried and tried all the proposed solutions, none of them solved my problem. I made this net for training over MNIST dataset. At the beginning it was deeper, but in order…
SilvioBarra
  • 223
  • 1
  • 2
  • 6
0
votes
1 answer

where to get the pre-trained models for "Show and Tell: A Neural Image Caption Generator"?

I have no resource to train the training datasets for Show and Tell: A Neural Image Caption Generator, so where to get the pre-trained models?
JustinGong
  • 399
  • 1
  • 4
  • 17
0
votes
2 answers

tensorflow retrain model file

im getting started with tensorflow und using retrain.py to teach it some new categories - this works well - however i have some questions: In the comments of retrain.py it says: "This produces a new model file that can be loaded and run by any…
HeikoG
  • 1,793
  • 1
  • 20
  • 29
0
votes
1 answer

Worse performance with transfer learning in convolutional neural network

I am doing emotion recognition with convolutional neural networks in MatConvNet. I have one main big dataset(A with 40.000 pics) and two harder, smaller datasets(B,C with 5.000 pics) with the same classes. When I run my network on the dataset A with…
Nicole
  • 31
  • 6
0
votes
0 answers

Keras image data ordering

When using a Theano backend in Keras, is it always necessary to use a 'channels_first' image data ordering? Or can we also use 'channels_last' as well and the Theano backend takes care of any conversions?
AbhinavChoudhury
  • 1,167
  • 1
  • 18
  • 38
1 2 3
…
33 34