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
1 answer

What is the difference between tfrecord and bottleneck

I have been studying transfer learning with models like inception_v4 and inception_resnet_v2. Found some projects that uses bottleneck and some uses tfrecords to store the training images. When retraining the inception_v4 model with the same data…
Eshaka
  • 974
  • 1
  • 14
  • 38
0
votes
1 answer

How to load a model using .ckpt.data and .ckpt.index

In the code, I have been using it uses a .ckpt like incption_v4.ckpt to load a model. am trying to use the pretrained pnesnet model and it comes as two separate file .ckpt.data and .ckpt.index. can someone please show me how to load from these two…
Eshaka
  • 974
  • 1
  • 14
  • 38
0
votes
0 answers

Difference in Keras applications model lists

In the past I've looked for pretrained CNNs I can import from tensorflow.keras.applications from looking at the keras website list here. I recently just noticed several more models on the keras applications GitHub, but I can't import those that…
Austin
  • 6,921
  • 12
  • 73
  • 138
0
votes
1 answer

Retraining a CNN without a high-level API

Summary: I am trying to retrain a simple CNN for MNIST without using a high-level API. I already succeeded doing so by retraining the entire network, but my current goal is to retrain only the last one or two Fully Connected layers. Work so…
Thomas Hubregtsen
  • 449
  • 1
  • 5
  • 22
0
votes
1 answer

ValueError: You are trying to load a weight file containing 14 layers into a model with 3 layers

(I couldn't find the solution with the previosly asked questions.) I use VGG16 to test on my data. My class number is 2 and I used this page to freeze conv layers and train top layers. Here is the code: from keras.applications import VGG16 model =…
umitkilic
  • 327
  • 1
  • 4
  • 17
0
votes
1 answer

Why the code I used to load pre-trained word2vec from google news corpus (English) is not working to load the google news corpus (Indonesian)?

I am working in a cross-cultural language study involving English and Indonesian participants. In the English participants, I successfully load the pre-trained word2vec from google news corpus (file: GoogleNews-vectors-negative300.bin). I was…
Annasya Masitah
  • 1
  • 1
0
votes
1 answer

Load pre-trained models in Tensorflow for Java

I'm trying to load pre-trained models in Tensorflow using the Java API. I notice that over time the format of the saved model files has changed and now there are saved models with file formats .pb , .ckpt and model directories with…
Dhvanan Shah
  • 51
  • 1
  • 4
0
votes
1 answer

Which object detection pre-trained models are available and convertible with TensorRT?

I'm looking into converting a pre-trained object detection model with TensorRT to try it out on my NVIDIA Jetson TX2 but every model I find has layers that are not yet supported by TensorRT. So far I tried SSD with MobileNet and Faster R-CNN but…
BourbonCreams
  • 353
  • 4
  • 21
0
votes
1 answer

How to print the prediction probabilities in Tensor Flow's retraining example?

I am using Tensor Flow's retraining example on my own dataset. The final test evaluation outputs the final test accuracy and the names of the misclassified images: test_accuracy, predictions = eval_session.run( [evaluation_step, prediction], …
krisg
  • 271
  • 2
  • 11
0
votes
1 answer

Inception V3 retrained model incorrect predictions after using optimize_for_inference and graph_transform tools

I have model generated using the tensorflow for poets tutorial. I have both binary and 3-class models that are exhibiting the same behavior. The forzen graph performs as expected but soon as I transform that to be used with opencv dnn module, the…
Henok G.
  • 49
  • 5
0
votes
1 answer

How to prepare test data for textsum?

I have been able to successfully run the pre-trained model of TextSum (Tensorflow 1.2.1). The output consists of summaries of CNN & Dailymail articles (which are chuncked into bin format prior to testing). I have also been able to create the…
KRW4
  • 67
  • 2
  • 10
0
votes
1 answer

Continue training a deeplearning4j model after it has been saved and loaded

I am using a Convolutional Neural Network and I am saving it and loading it via the model serializer class. What I want to do is to be able to come back at a later time and continue training the model on new data provided to it. What I am doing is I…
Arthur Dunbar
  • 23
  • 5
0
votes
0 answers

Change optimizer for pre-trained inception v3

I was wondering how I can change the optimizer for inception v3 from SGD to Adam Optimizer. I would like to keep the weights in pre-trained, but not the default SGD Optimizer. If I add Adam optimizer, it will throw an error saying it cannot find…
Long Le Minh
  • 335
  • 1
  • 2
  • 12
0
votes
0 answers

using tensorflow retrained graph in OpenCV-3.4 in C++

I started using tensorflow recently & referred to the tensorflow transfer learning tutorial from https://codelabs.developers.google.com/codelabs/tensorflow-for-poets/#3 and retrained the InceptionV3 model with my own image data. In python I was able…
coder999
  • 15
  • 7
0
votes
1 answer

Changing dimnesions of pretrained word2vec vectors

I have two different word embedding pretrained models that I want to combine together so that a missing word from one model can be complimented by the other model (in case the other model has the word that is missing in the first model). But the…
Golam Kawsar
  • 760
  • 1
  • 8
  • 21
1 2 3
…
33 34