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

Pretrained Tensorflow Model invalid argument error

I'm doing my project using tensorflow with pre-trained mobilenet_v2 model which can be found on https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md I wanted to get hidden layer values so I…
C.H.Song
  • 39
  • 6
0
votes
1 answer

How to load pretrained googlenet model in pytorch

I'm trying to finetune a GoogleNet network over a specific dataset but I'm having trouble loading it. What I try now is: model = torchvision.models.googlenet(pretrained=True) However I get an error: AttributeError: module 'torchvision.models' has…
ice
  • 39
  • 6
0
votes
1 answer

Losing output node names in TensorFlow model after fine-tuning from pre-trained model

I follow the tutorial at https://tensorflow-object-detection-api-tutorial.readthedocs.io to fine-tune a pre-trained model to detect new objects in images. The pre-trained model is ssd_inception_v2_coco. I trained and evaluated the model successfully…
Dee
  • 7,455
  • 6
  • 36
  • 70
0
votes
0 answers

Tensorflow object detection retraining, confidence score really low

I am trying to retrain the tensorflow object detection model - faster r cnn ( pretrained on iNaturalist) data. However, after training for around 60k steps ( where the total loss stabilizes), if I run an evaluation the confidence scores of my…
user3741951
  • 189
  • 1
  • 11
0
votes
1 answer

Decoding prediction outputs generated by a pretrained model to human readable labels

I'm trying to use a pre-trained object detection model from the Tensorflow model zoo. Basically, I've chosen faster_rcnn_inception_resnet_v2_atrous_oidv4 trained on the Open Images dataset. Here is my code: import tensorflow as tf # restore the…
lenhhoxung
  • 2,530
  • 2
  • 30
  • 61
0
votes
2 answers

Does the accuracy of the deep learning program drop if I do not put in the default input shape into the pretrained model?

As the title says, I want to know whether input shape affects the accuracy of the deep learning model. Also, can pre-trained models (like Xception) be used on grayscale images? P.S. : I recently started learning deep learning so if possible please…
Tsukikaze
  • 13
  • 4
0
votes
1 answer

Python: pre-trained VGG-face model for face anti-spoofing problem

I'm trying to solve face anti-spoofing problem by using pre-trained model (e.g., VGG trained on ImageNet). Where do I need to retrieve the features ? after which layer ? More specific, is it enough to change the output of the last full connected…
Aj.h
  • 1
  • 1
0
votes
0 answers

Loading pretrained model for MobileNetv2 FasterRCNN in tensorflow

I have pretrained model for MobileNetV2. The variables of pretrained model are shown in the link. My model to be fine tuned needs the following variables. WARNING:root:Variable [MobilenetV2/expanded_conv_15/depthwise/biases] is not available in…
batuman
  • 7,066
  • 26
  • 107
  • 229
0
votes
0 answers

Pretrained model for Biomedical Image Segmentation

I would like to use pre-trained model (in encoder part) for Biomedical Image segmentation with Unet architecture. My question is which pre-trained model should I use? I tried VGG16 and VGG19 with the following different options but I could not get…
John
  • 3
  • 1
  • 4
0
votes
1 answer

Number of bounding boxes in Tensorflow Object detection module

I'm doing inference using one of the pre-trained models, tensorflow object detection. However, the train config of the model limits the number of detections to just 5 boxes. Any idea on how to change this parameter during inference? The model i'm…
user3741951
  • 189
  • 1
  • 11
0
votes
1 answer

How does back propagation in CNN works for pre-trained embedding in text classification

How do the loss function works in case of pretrained word2vec embeddings as the weights are not updated during training.Then how do the backward pass works and what does it update for prediction?
Rumesa
  • 103
  • 1
  • 10
0
votes
0 answers

How to deal with NaN and 0 for Loss and Validation during Training

I am using SSD512(imagenet pre-trained model) and Faster_R-CNN(pre-trained) while training, the loss and confidence displays nan and validation as 0. [Basketball-ChainerCV]…
TulakHord
  • 422
  • 7
  • 15
0
votes
1 answer

How to open pretrained models in python

Hi I'm trying to load some pretrained models from .sav files and so far nothing is working. The models were originally made in pytorch and when I open the raw file in vs-code I can see that all the appropiate information was stored correctly. I've…
CertainlyNotAdrian
  • 337
  • 2
  • 16
0
votes
2 answers

Why do I receive the Error: Tensor is disposed, when using tf.grad() to implement FGSM?

I'm trying to implement the Fast Gradient Sign Method (FGSM) on MobileNet with tensorflow.js, however I'm having problems on the latest version (1.0.1) when computing the gradient using tf.grad(). The code is working fine with tfjs version 0.13.0…
BMcFadyen
  • 363
  • 3
  • 7
0
votes
1 answer

Load Pre-trained model in Pytorch

I am currently working on GANS, I have downloaded the code and models from http://www.cs.columbia.edu/~vondrick/tinyvideo/, where I just need to run to get output. I have given paths and all correctly, and the code where i am receiving an error is…
Rajesh
  • 221
  • 4
  • 16
1 2 3
…
33 34