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
0
votes
0 answers

ValueError: could not broadcast input array from shape (128,128,3) into shape (128,128,3,3)

ValueError: could not broadcast input array from shape (128,128,3) into shape (128,128,3,3) net_final.fit problem
Dr M Venkatanarayana Dean CRI
  • 1
0
votes
1 answer

Making Class Activation Map (CAM) for EfficientNetB3 architecture

I would like to draw a class activation map for a model built upon EfficeintNet B3. But when I follow different tutorials and codes from different sources, it simply fails.... #load images img = tf.keras.preprocessing.image.load_img( base,…
Maximus
  • 75
  • 8
0
votes
1 answer

AttributeError: module 'keras.utils' has no attribute 'get_file' errot occured using efficientnet and karas

[Error occur with karas and using EfficientNetThis is the error i got ]2 I tried: - import tensorflow.python.keras.utils as generic_utils installed segmentation-models also
A_galaxy
  • 11
  • 1
0
votes
0 answers

EfficientNet B0 Model does not predict right class while testing

I trained an effectivenetB0 model using a training dataset of about 400 images of army personals, the general public, and army vehicles specifically tanks of each category. After training it on the training set I get an accuracy of about 98% and on…
Usama Aleem
  • 113
  • 7
0
votes
1 answer

Improve the result of EfficientNet

Halo there, I'm still struggling in python. Now I'm going to use the EfficientNet model to detect the ripeness of palm oil. I'm using 5852 training picture which is divided into 4 class (1463 per class) with 132 testing picture (33 per class). After…
Muhammad Rifqi
  • 43
  • 8
0
votes
1 answer

Incorrect Shape in Tensorflow Neural Network - Batch size in shape

I'm following this tutorial on implementing EfficientNet on Keras.: Tensorflow I am using my own dataset and so had to load it manually. For some reason the batch size is being included in the tensor shape and it is throwing an error. from…
MontyP
  • 61
  • 9
0
votes
1 answer

Stacked model gets worse results than base models

I have made a stacking model using 5 efficientNet models for a Kaggle competition. Given below is the architecture of the stacking model: Model:…
Arthur
  • 21
  • 2
0
votes
2 answers

False prediction from efficientnet transfer learning

I'm new to transfer learning in TensorFlow and I choose tfhub to simplify finding a dataset, but now I'm confused because my model gives me a wrong prediction when I try to use an image from the internet. I used the efficientnet_v2_imagenet1k_b0…
Muhammad As'ad Muyassir
  • 15
  • 3
0
votes
1 answer

How to use EfficientNet-Lite4 with tensorflow Lite

I try to use EfficientNet-Lite4 on google colab with tensorflow Lite but i have an error name 'efficienetnet_lite4_spec' is not defined What should I do? Or does it only work with EfficientNet-Lite0?
zeewa42
  • 25
  • 4
0
votes
0 answers

A trained efficientnet-v2-b3 with train-acc 0.99 and val-acc 0.99 is very good at predicting the test dataset but poor at the train & val dataset

I used the pretrained EfficientNet-v2-b3 model from 'https://github.com/rwightman/pytorch-image-models' and the pytorch framework to train the cigarette box. The train is as follows: There are 1100 classes each of which is one cigarette…
licomeback
  • 1
  • 1
0
votes
1 answer

how to prevent overfitting/underfitting while using EfficientNet

i'm new in python so for my college final project, i use EfficientNet for the ripeness palm oil into 4 classification. i've total 5852 train data (1463 each) , and 132 test data (33 each). i used code from the internet. but the result is far from…
Muhammad Rifqi
  • 43
  • 8
0
votes
1 answer

Failed to run EfficientNet model to trained 4 class

I'm going to train my model with 4 classes with images. Here's my pre-trained code look like conv_base = EfficientNetB0(weights="imagenet", include_top=False, input_shape=(224, 224, 3)) I trained my…
Muhammad Rifqi
  • 43
  • 8
0
votes
1 answer

can i use PyTorch Data Loader to load raw data images which are saved in CSV files?

I have raw data images saved in separate CSV files(each image in a file). I want to train a CNN on them using PyTorch. how should I load data to be appropriate for using as CNN's input? (also, it is 1 channel and the image net's input is RGB as the…
forouzanf
  • 15
  • 3
0
votes
1 answer

How to fine tune a trained model and saved model with tensorflow?

I have a big dataset and I want to train efficientnetb0 by this dataset but google colab gets a run timeout so I want to train the fully connected layers of the model and save it then load it again after some hours and fine-tune the base…
Faezeh Mosayyebi
  • 61
  • 1
  • 3
0
votes
0 answers

Attribute error while training an efficientnet model

I'm trying to train a prediction model using EfficientnetB4 and coming across this error: AttributeError Traceback (most recent call last) in () ----> 1 X_train, X_val, X_test,…
Stephen Myers
  • 1
1 2 3 4 5
6
7 8