First of all, I'm new to the Deep Learning platform, please correct me if I did any mistake.
I'm trying to implement the age detection by using DEX method. As of now my understand is that, they tried to train a CNN weight model using VGG-16 architechture. I'm using IMDB_WIKI dataset as they suggest in their paper.
I'm using TensorFlow, Keras to train my weight model in Python3 language.
My Steps to train the model(I just starts with the IMDB set):
Load the IMDB mat file and get training data and validation data set(10% of total dataset)
Create a VGG-16 model with ImageNet weight(I belive its a large dataset)
As ImageNet have 1000 classes, remove the last layer of model and put my single age class output layer instead.
Also add a dropout layer on the top of output layer(frankly don't know how it is working)
My experiment start from here :)
Freeze the layers alreay pretrain into VGG-16 architechture, except my new added layers, now there are some non-trainable objects available. In that case my training age accuracy is just 19% which is too poor, i hope detecting real age it should be 50-56%.
By seeing that I guess that may be due to, I didn't train all the layers. I remove the freezeness of the layers and tried to train but it's showing me a out of memory exception, After that I have just freeze 8 layers of my total architecture, after training 40 epochs I found that age accuracy is 11% which is less that before :(
Can any one please help me to understand this paper properly, please ?
Thank you.
"Also add a dropout layer on the top of output layer(frankly don't know how it is working)" - That is just plainly wrong. A dropout layer sets multiplies the output with 0, making the activation and the gradient 0. If you use this as your final layer with k percent, then your result will be rubbish in k percent of cases, e.g. dropping your accuracy. Just remove it and it should be better.
It is already implemented in deepface package for python
#!pip install deepface
from deepface import DeepFace
obj = DeepFace.analyze("img1.jpg", actions = ["age", "gender"])
print(obj)
The model is trained based on the instructions of DEX paper. It builds a VGG model in the background and loads pre-trained weights. Besides, it runs on TensorFlow framework and Keras APIs.
Related
I followed a blog on how to implement a vgg16-model from scratch and want to do the same with the pretrained model from Keras. I looked up some other blogs but can't find a fitting solution I think. My task is to classify integrated circuit images into defect or non defects.
I have seen on a paper that they used pretrained imagenet model of vgg16 for fabric defect detection, where they freezed the first seven layers and fine tuned the last nine for their own problem.
(Source: https://journals.sagepub.com/doi/full/10.1177/1558925019897396)
I have already seen examples on how to freeze all layers except the fully connected layers, but how can I try the example with freezing first x layers and fine tune the others for my problem?
The VGG16 is fairly easy to implement from scratch but for models like resnet or xception it is getting a little trickier.
It is not necessary to implement a model from scratch to freeze a few layers. You can do this on pre-trained models as well. In keras, you'd use trainable = False.
For example, let's say you want to use the pre-trained Xception model from keras and want to freeze the first x layers:
#In your includes
from keras.applications import Xception
#Since you're using the model for a different task, you'd want to remove the top
base_model = Xception(weights='imagenet', include_top=False)
#Freeze layers 0 to x
for layer in base_model.layers[0:x]:
layer.trainable = False
#To see all the layers in detail and to check trainable parameters
base_model.summary()
Ideally you'd want to add another layer on top of this model with the output as your classes. For more details, you can check this keras guide: https://keras.io/guides/transfer_learning/
A lot of times the pre-trained weights can be very useful in other classification tasks but in case you want to train a model from scratch on your dataset, you can load the model without the imagenet weights. Or better, load the weights but don't freeze any layers. This will retrain every layer taking imagenet weights as an initialization.
I hope I've answered your question.
I want extract 1000 image features using pretrained Xception model.
but xception models last layer(avg_pool) give 2048 features.
Can i reduce final output feature number without additional training?
I want image features before the softmax not predcition result.
base_model = xception.Xception(include_top=True, weights='imagenet')
base_model.summary()
self.model = Model(inputs = base_model.input, outputs=base_model.get_layer('avg_pool').output)
This model was trained to produce embeddings in 2048-dimensional space to the classifier after it. There is no sense in trying to reduce the dimensionality of the embedding space, unless you are combining very complex and inflexible models. If you are just doing simple transfer learning with no memory constraints, just snap your new classifier (extra layers) on top of it, and retrain after freezing (or not) all layers in the original Xception. That should work regardless of Xception output_shape. See the keras docs.
That said, if you REALLY need to reduce dimensionality to 1000-d, you will need a method that preserves (or at least tries to preserve) the original topology of the embedding space, otherwise your model will not benefit at all from transfer learning. Take a look at PCA, SVD, or T-SNE.
I'm trying to do a binary classification with a Deep Neural Network (esp. VGG16) in Keras. Unfortunately I have a very imbalanced data-set (15.000/1.800 images) but just can't find a way to circumvent that..
Results that I'm seeing
(on training and validation data)
Recall = 1
Precision = 0.1208 (which is exactly the ratio between class 0 and class 1 samples)
AUC = 0.88 (after ~30 epochs with SGD, which seems to be 1 - Precision)
What I've done
Switching from loss/accuracy metrics to AUC with this little helper
Utilizing class_weight like described here which doesn't seem to help
Trying different optimizers (SGD, Adam, RMSProp)
Adding BatchNormalization layers to my (untrained) VGG16 and set use_bias to False on Convolutional Layers. See my whole network as a gist here.
Doing Augmentation to enlarge dataset with Keras inbuilt ImageDataGenerator.
What I think could help further (but did not try yet)
Doing more data augmentation for one class than the other. Unfortunately I'm using one ImageDataGenerator for my whole training data and I don't know how to augment one class more than the other.
Maybe a custom loss-function which penalises false decisions more? How would I implement that? Currently I'm just using binary_crossentropy.
Theoretically I could adjust the class-membership-threshold for prediction but that doesn't help with training and would not improve the result, right?
Maybe decrease batch-size like suggested here. But I don't really see why that should help. Currently I'm determining the batch-size programmatically to show all the training and validation data to the network in one epoch:
steps_per_epoch = int(len(train_gen.filenames) / args.batch_size)
validation_steps = int(len(val_gen.filenames) / args.batch_size)
What do you think should I tackle first or do you have a better idea? I'm also glad for every help with implementation details.
Thank you so much in advance!
Maybe try to prepare class-balanced batches ( includes doublings of class 1 ) like described in https://community.rstudio.com/t/ensure-balanced-mini-batches-while-training/7505 ( R Studio ). Also read Neural Network - Working with a imbalanced dataset and balancing an imbalanced dataset with keras image generator
Another possibility is to perform feature extraction in the pre-processing meaning letting run image processing algorithms over the images to highlight characteristic features
I'm working on a project that requires the recognition of just people in a video or a live stream from a camera. I'm currently using the tensorflow object recognition API with python, and i've tried different pre-trained models and frozen inference graphs. I want to recognize only people and maybe cars so i don't need my neural network to recognize all 90 classes that come with the frozen inference graphs, based on mobilenet or rcnn, as it seems this slows the process, and 89 of this 90 classes are not needed in my project. Do i have to train my own model or is there a way to modify the inference graphs and the existing models? This is probably a noob question for some of you, but mind that i've worked with tensorflow and machine learning for just one month.
Thanks in advance
Shrinking the last layer to output 1 or two classes is not likely to yield large speed ups. This is because most of the computation is in the intermediate layers. You could shrink the intermediate layers, but this would result in poorer accuracy.
Yes, you have to train own model. Let's see in short words some ways how to do.
OPTION 1. When you want to apply transfer knowledge as maximum as possible, you can froze the CNN layers. After, you change a quantity of detected classes with dimension of classifier (dense layers). The classifier is the latest part in CNN architecture. Now, you should retrain only classifier.
OPTION 2. Assuming, you want to apply transfer knowledge for first layers of CNN (for example, froze first 2-3 CNN layers) and retrain rest of CNN with classifier. After, you change a quantity of detected classes with dimension of classifier. Now, you should retrain rest of CNN layers and classifier.
OPTION 3. Assuming, you want to retrain whole CNN with classifier. After, you change a quantity of detected classes with dimension of classifier. Now, you should retrain whole CNN with classifier.
Generally, the Tensorflow Object Detection API is a good start for beginners! How to proceed with your problem you can see here more detail about whole process and extra explanation here.
I am trying to solve a time series prediction problem. I tried with ANN and LSTM, played around a lot with the various parameters, but all I could get was 8% better than the persistence prediction.
So I was wondering: since you can save models in keras; are there any pre-trained model (LSTM, RNN, or any other ANN) for time series prediction? If so, how to I get them? Are there in Keras?
I mean it would be super useful if there a website containing pre trained models, so that people wouldn't have to speent too much time training them..
Similarly, another question:
Is it possible to do the following?
1. Suppose I have a dataset now and I use it to train my model. Suppose that in a month, I will have access to another dataset (corresponding to same data or similar data, in the future possibly, but not exclusively). Will it be possible to continue training the model then? It is not the same thing as training it in batches. When you do it in batches you have all the data in one moment.
Is it possible? And how?
I'll answer your last questions first.
Will it be possible to continue training the model then? It is not the same thing as training it in batches. When you do it in batches you have all the data in one moment. Is it possible? And how?
Yes, it is possible. In general, it's called transfer learning. But keep in mind that if two datasets represent very different populations, the network will soon "forget" what it learned on the first run and will optimize to the second one. To do this, you simply start training from a loaded state instead of random initialization and save the model afterwards. It is also recommended to use a smaller learning rate on the second run in order to adapt it gradually to the new data.
are there any pre-trained model (LSTM, RNN, or any other ANN) for time
series prediction? If so, how to I get them? Are there in Keras?
I haven't found exactly a pre-trained model, but a quick search gave me several active GitHub projects that you can just run and get a result for yourself: Time Series Prediction with Machine Learning (LSTM, GRU implementation in tensorflow), LSTM Neural Network for Time Series Prediction (keras and tensorflow), Time series predictions with Keras (keras and theano), Neural-Network-with-Financial-Time-Series-Data (keras and tensorflow). See also this post.
Now you can use BERT or related variants and here you can find all the pre-trained models: https://huggingface.co/transformers/pretrained_models.html
And it is possible to pre-train and fine-tune RNN, and you can refer to this paper: TimeNet: Pre-trained deep recurrent neural network for time series classification.