All Questions
Tagged with tf.keras transfer-learning
20
questions
4
votes
1
answer
2k
views
Remove top layer from pre-trained model, transfer learning, tensorflow (load_model)
I have pre-trained a model (my own saved model) with two classes, which I want to use for transfer learning to train a model with six classes.
I have loaded the pre-trained model into the new training ...
- 53
3
votes
1
answer
486
views
KerasLayer vs tf.keras.applications performances
I've trained some networks with ResNetV2 50 ( https://tfhub.dev/google/imagenet/resnet_v2_50/feature_vector/4 ) and it work very well for my datasets.
Then I tried tf.keras.applications.ResNet50 and ...
- 499
2
votes
1
answer
2k
views
How to add a few layers before the model in transfer learning with tensorflow
I am trying to use transfer learning in tensorflow. I know the high level paradigm
base_model=MobileNet(weights='imagenet',include_top=False) #imports the
mobilenet model and discards the last ...
- 5,082
1
vote
1
answer
116
views
InvalidArgumentError while fine tuning using VGG16 with input shape as (192,192,3)
I'm using the multimodal MR image dataset. I don't understand what causes this error during training:
InvalidArgumentError: logits and labels must have the same first dimension, got logits shape [64,...
- 21
0
votes
2
answers
352
views
How to increse and decreses the model accuracy and batch size respectively
İ am working on transfer learning for multiclass classification of image datasets that consists of 12 classes. As a result, İ am using VGG19. However, the accuracy of the model is as much lower than ...
- 29
0
votes
1
answer
453
views
Unable to convert to RGB from Grayscale for transfer learning with FER2013 dataset
I have the similar problem with post here : How to convert RGB images to grayscale, expand dimensions of that grayscale image to use in InceptionV3?
Essentially I am training to use transfer learning (...
- 125
0
votes
1
answer
192
views
Validation loss bounces randomly when training a Keras model regardless of the used optimiser
I am retraining InceptionV3 model on 200 images and I am using Adam optimiser:
opt = Adam(lr=0.0001, decay=0.0001 / 100)
I noticed the loss bounces specially the validation. I thought that is down ...
- 1,065
0
votes
0
answers
15
views
Transfer Learning Accuracy Drop after Rerun
I had use below code to perform Transfer Learning with Inception by testing different optimizer and other setting.
However, I face the training accuracy drop from 70% to 20% after I try to put the ...
- 1
0
votes
0
answers
38
views
Warnings on arm64 when using tf.keras.preprocessing.image_dataset_from_directory() with color_mode="rgb" on grayscale images for transfer learning
I want to perform transfer learning with a pre-trained model that expects 3-channel input images such as VGG-16, but my images are grayscale. I am using tf.keras.preprocessing....
- 13
0
votes
1
answer
60
views
Error Pop Out while Add Layers from Pre-Trained Model
I am trying to fine-tune a pre-trained time-series model with 12 dimension physiological signals as inputs, yet, my dataset is only one dimension. Therefore, I built the first conv1d layer and set the ...
- 11
0
votes
1
answer
119
views
transfer learning using tensforflow.keras shown 90% accuracy but single image prediction shows differently
I am trying transfer learning via tensorflow.keras but someting is not working out. The training is showing a nice curves (Training Loss and Validation loss nicely droping ,validation_accuracy ...
- 11
0
votes
1
answer
264
views
Keras "SavedModel file does not exist at..." for a model retrieved from an online URL
Keras "SavedModel file does not exist at..." error occurs for a model retrieved from an online URL and never manually saved at any local directory.
The code ran just fine for as long as I've ...
- 11
0
votes
1
answer
616
views
Resizing images in preprocessing for inception, how to use batches?
I'm trying to resize some images to use them with Inception. I want to do it as a separate preprocessing step to speed things up later. Running tf.image.resize on all of the images at once crashes, as ...
0
votes
1
answer
190
views
VGG16 transfer learning with Imagenette dataset accuracy is 0
I am trying to include SENet module in the middle of VGG16 network at multiple locations and then train the model with Imagenette dataset. However I am getting 0 accuracy. I am just a beginner user, ...
- 121
0
votes
1
answer
161
views
Customize trainable parameters of KERAS model
I just want to set all the parameters to not trainable expect the ones that are connected to dense_5 layer which are it's own parameters and the parameters of dense_6 layer that are connected to ...
0
votes
1
answer
82
views
Can this be considered overfitting?
I have 4 classes, each with 1350 images. The validation set has 20% of the total images (it is generated automatically). The training model uses MobilenetV2 network:
base_model = tf.keras.applications....
-1
votes
1
answer
884
views
Facing ValueError: Shapes (None, None) and (None, 256, 256, 12) are incompatible
İ am working on transfer learning for multiclass classification of image datasets that consists of 12 classes. As a result, İ am using VGG19. However, I am facing an error i.e. Facing ValueError: ...
- 29
-1
votes
1
answer
714
views
Image Data generating for data augmentation
I am working on image classification by transfer learning in the 12 several classes of the dataset. However, I am facing overfitting. As a result, I applied data augmentation (Maybe flying) for ...
- 29
-2
votes
1
answer
283
views
how to detect not in trained-for-category images when using resnet50
I have trained resnet50 on four categories of images. It works fantastic when I feed it an image in any one of the four categories -- I have essentially 100% accuracy on images in these categories.
...
- 21
-3
votes
1
answer
140
views
How to increase Emotion Detection Validation Accuracy on VGG16 model ? [Transfer Learning]
import pandas as pd
import numpy as np
import keras
import tensorflow
from keras.models import Model
from keras.layers import Dense
from keras import optimizers
from keras.preprocessing.image import ...
