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
0
votes
0 answers

EfficientNet increasing training and validation loss, decreasing accuracy after 100 epochs

I've been running the EfficientNet code from Google on my own image datasets and have run into the following problem. For each variant of the architecture (b0 to b7) the training and validation loss decrease up until +/- 100 epochs. After which both…
Adnan Fiaz
  • 31
  • 5
-1
votes
1 answer

How can I fine-tune EfficientNetB3 model and retain some of its exisiting labels?

I've tested EfficientNetB3 model (trained on ImageNet) on my large image set and it recognizes some classes of images that I have with varying accuracy, the others are not recognized at all. For example, it does a great job for school buses:…
Wodzu
  • 6,932
  • 10
  • 65
  • 105
-1
votes
1 answer

how can i fix pytorch predict problem with deep learning

Given groups=1, weight of size [48, 3, 3, 3], expected input [5, 128, 129, 4] to have 3 channels, but got 128 channels instead. This is my code: **model_ft.eval() for image in test_loader: image = image.cuda() output =…
-2
votes
2 answers

AttributeERROR : module'tensorflow.keras.applicationsas no attribute efficientnet_v2

When i try to run the efficientNetv2 model I got this erreur Error-message AttributeError: module'tensorflow.keras.applications ' has no attribute 'efficientnet_v2' Tensorflow version : tensorflow-gpu:2.6
Cy Rine
  • 1
  • 4
1 2 3 4 5 6 7
8