Stack Overflow
Stack Overflow

Questions tagged [efficientnet]

questions about retraining efficientnet with Keras to create new object detection models

efficientnet is a lightweight convolutional neural network architecture achieving the state-of-the-art accuracy with an order of magnitude fewer parameters and FLOPS, on both ImageNet and five other commonly used transfer learning datasets.

109 questions
1
vote
1 answer

Why is training loss oscilating up and down?

I am using the TF2 research object detection API with the pre-trained EfficientDet D3 model from the TF2 model zoo. During training on my own dataset I notice that the total loss is jumping up and down - for example from 0.5 to 2.0 a few steps…
Matthias
  • 9,817
  • 14
  • 66
  • 125
1
vote
1 answer

What does layer.get_weights() of a Separable convolutional layer means?

I learned that we can use the function layer.get_weights() to get the weight and bias of a layer. This will return a list of length 2. Weights of the layer are stored at layer.get_weights()[0] and the bias is stored at layer.get_weights()[1] (If the…
Saurav Rai
  • 2,171
  • 1
  • 15
  • 29
1
vote
1 answer

Is there anyway to get efficientnet pre-trained weight in hdf5 format?

I have some problems with getting pre-trained weights in efficientnet. So I googled for efficientnet.hdf5 but cannot find it. So is there anyway to get pre-trained weight in hdf5 format. Thank u.
Myat Kaung
  • 29
  • 1
  • 1
  • 6
1
vote
1 answer

Extracting features from EfficientNet Tensorflow

I have a CNN model trained using EfficientNetB6. My task is to extract the features of this trained model by removing the last dense layer and then using those weights to train a boosting model. i did this using Pytorch earlier and was able to…
Akshat Shreemali
  • 193
  • 2
  • 12
1
vote
1 answer

Flattening Efficientnet model

I am trying to remove the top layer in the efficientnet-pytorch implementation. However, if I simply replace the final _fc layer with my own fully connected layer, as suggested by the author in this github comment, I am worried that there is still a…
sachinruk
  • 9,571
  • 12
  • 55
  • 86
1
vote
1 answer

weights = 'noisy-student' ValueError: The `weights` argument should be either `None`, `imagenet`, or the path to the weights file to be loaded

I am using Google Colab and I want to use the weights of EfficientNet Noisy Student. https://www.kaggle.com/c/bengaliai-cv19/discussion/132894 First, I installed the package via: !pip install git+https://github.com/qubvel/efficientnet Then I tried…
Tobitor
  • 1,388
  • 1
  • 23
  • 58
1
vote
1 answer

EfficientDet-Custom Dataset -StringToNumberOp could not correctly convert string

As a beginner, I am trying to train my custom datasets with TensorFlow, but getting the following error when start training: here is my command line: python main.py…
Max
  • 509
  • 1
  • 7
  • 21
1
vote
1 answer

How can I train a model ( like EfficientNet, Resnet ) from scratch in Keras?

Is there a way, where we can load the architecture of a network and then train it from scratch in Keras?
Aditya Jain
  • 57
  • 1
  • 1
  • 7
1
vote
1 answer

Efficientnet inputshape error with tf.data.Dataset

when feeding a tf.data.Dataset to train EfficientnetB0 model I get the following error: ValueError: in converted code: …
feedFloward
  • 11
  • 1
1
vote
2 answers

Tensorflow 2 /Google Colab / EfficientNet Training - AttributeError: 'Node' object has no attribute 'output_masks'

I am trying to train EfficientNetB1 on Google Colab and constantly running into different issues with correct import statements from Keras or Tensorflow.Keras, currently this is how my imports look like import tensorflow as tf from tensorflow.keras…
Zubair Ahmed
  • 91
  • 12
1
vote
1 answer

Following Pyhthon CNN architectures Libraries : EfficientNet & DenseNet 169 EfficientNet import Problems

I'm trying to use the following Deep Learning CNN architecutres : DenseNet169 & EfficientNet with transfer learning. I've installed the following libraries bu PyCharm and call the following import libraries : from keras.models import Model from…
CaRoule
  • 11
  • 1
1
vote
1 answer

Why does the Gramian Matrix work for VGG16 but not for EfficientNet or MobileNet?

A Neural Algorithm of Artistic Style uses the Gramian Matrix of the intermediate feature vectors of the VGG16 classification network trained on ImageNet. Back then, that was probably a good choice because VGG16 was one of the best-performing…
fxtentacle
  • 763
  • 10
  • 15
1
vote
0 answers

Deploy Keras model on Spark

I have a trained keras model. https://github.com/qubvel/efficientnet I have a large updating dataset I want to get predictions on. Meaning to run my spark job every 2 hours or so. What is the way to implement this? MlLib does not support…
koren maliniak
  • 143
  • 10
1
vote
3 answers

How to fix 'tuple' object has no attribute 'layer'?

I am using layer from efficientnet for some postprocessing on that layer but after extracting the layer and performing the operation on that it shows that : AttributeError: 'tuple' object has no attribute 'layer' . Running on python 3.6.2 with…
Shubham Innani
  • 21
  • 1
  • 6
0
votes
0 answers

Getting the channel-wise importance weights of a squeeze and excitation block on keras

so I am training an Efficientnet B0 model on Keras. The goal is to implement this model on an asic chip to do the inference on hardware. The Efficientnet model has a Squeeze & Excitation block that has learnable parameters that tell us about the…
Wassim Chaabani
  • 1
1 2
3
4 5 6 7 8