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

Retrain Inception Model Error in Android

I am following Tensorflow for poet instruction for retrain model. I have successfully create retrained_graph.pb and retrained_labels.txt. While I use imagenet_comp_graph_label_strings.txt and tensorflow_inception_graph.pb then application run…
kinjal patel
  • 585
  • 2
  • 4
  • 12
0
votes
2 answers

Where can I find pre trained word embeddings (English) in word2vec format of 50 dimensions?

Preferably it should be a txt file than a binary file. All of the pre-trained word embeddings I found where of 300+ dimensions. Thank you
stk555
  • 3
  • 1
  • 3
0
votes
0 answers

Tensorflow image_retraining:retrain in docker is not found

I'm new with tensorflow but I seem not to understand some stuff. I installed TF with docker container ( docker run -d -it gcr.io/tensorflow/tensorflow:latest-devel) which creates my container with tensor flow inside. I'm now trying to use…
Lucas Fischer
  • 13
  • 4
0
votes
1 answer

How a subset of pretrained caffe model can be saved?

I am working on a pretrained caffe model (in python) which has 3 layers. I want to decompose this caffe model and create a new model the same as first layer of this model. For example: Original Caffe model data -> conv1_1 -> conv1_2 -> conv2_1 ->…
Ali
  • 3
  • 2
0
votes
0 answers

tensorflow inception for retraining / fine tuning with a pretrained model: inception_train

I tried to retrain (new images, new classes) on top of the pretrained inception model, I therefor followed the instructions of the inception…
vvvox
  • 1
0
votes
1 answer

Visualizing the features of a pretrained network in TensorFlow

For a medical application I am retraining the pretrained Inception-v3 network using TensorFlow. This network has a final layer: pool_3:0 (2048 features) Using TF's classify_image, I figured out which of these features are most important for each…
nom
  • 148
  • 1
  • 6
0
votes
1 answer

Caffe: resuming from a trained snapshot fails with an error

I trained my network with some configuration , and then saved a snapshot of it. Now I am trying to resume from the last snapshot and it fails with this error message : I0328 13:44:30.756110 24238 net.cpp:283] Network initialization done. I0328…
Hossein
  • 24,202
  • 35
  • 119
  • 224
-1
votes
0 answers

Why should I consider models like YOLO, SSD, Faster R-CNN ,when TensorFlow or OpenCV are available options for custom object detection without models

Is it possible to create a custom object detection system without utilising established models like YOLO, SSD, Faster R-CNN, and similar approaches? If so, what are the steps to implement it? If not, what are the reasons behind its…
kush patel
  • 1
-1
votes
0 answers

How to fine tune a masked Bert Model to a Political leaning Model

I'm new in this fine tuning world and using a pre-trained models in order to create a new model that makes different predictions. I've been researching Bert Models, and the majority of them are Masked Models, which means they predict a word based on…
Elmauro
  • 41
  • 5
-1
votes
0 answers

Best transformer/techniques for urdu sentence embeddings

I am performing urdu sentence embeddings please suggest a model which is pretrained and fine tuned for urdu language and available freely, i have already checked urduhack avaialbe on hugging face i have already checked urduhack avaialbe on hugging…
Syeda Farwa
  • 1
-1
votes
0 answers

for fine-tuning a pre-trained transformer model, should I remove the coefficients of the fc layers that is after each attention head?

In order to fine-tune a pre-trained transformer model, in addition to the coefficients of the head layer (head.weight, head.bias), should I remove the coefficients of the fc layers that is after each attention head? this is some element of my…
a.h. hamedani
  • 1
  • 1
-1
votes
0 answers

in order to fine-tune a pre-trained transformer model, should I remove the coefficients of the fc layers that is after each attention head?

for fine-tune a pre-trained transformer model, in addition to the coefficients of the head layer (head.weight, head.bias), should I remove the coefficients of the fc layers that is after each attention head? this is some element of my pre-trained…
a.h. hamedani
  • 1
  • 1
-1
votes
1 answer

Generate an image similar to image name

I have a requirement where I want to generate an image that is similar to my item name. For eg. if my item name is Butter Chicken then I want an image to be generated of butter chicken. My requirement is only food specific. I looked into DeepAI…
Prerna Kakria
  • 67
  • 6
-1
votes
1 answer

Is my Inception V3 model overfitted or is it fine to have those fluctuations?

In this post, I have added graphs of both accuracy and loss of basic inception v3 model and another inception v3 model with dropout layer. Can anyone tell me whether these models are overfitted or not by looking at the graphs. Basic Inception V3…
Sai Chand
  • 9
  • 1
  • 4
-1
votes
1 answer

need guidance on using pre-trained weights in segmentation_models API

I want to use a pre-trained Unet model using segmentation_models API for the Cityscapes dataset, but I need the pre-trained weights for the same. Where can I find the pre-trained weights for a Unet model trained on the Cityscapes dataset? Please…
Tushar Patil
  • 13
  • 5
1 2 3
…
33
34