Accuracy issue about age-gender-estimation HOT 16 OPEN

Hi @taewookim,

1. I simply chose 32x32 for efficiency in development and testing. It is not appropriate for deployment for its poor accuracy as you pointed out.
2. I think the image size should be larger if accuracy matters. The image size 64x64 is used in the sample code in README.md as python3 create_db.py --output data/imdb_db.mat --db imdb --img_size 64. In the original paper [1], the VGGNet is used; the input image size is 224x224.

[1] R. Rothe, R. Timofte, and L. V. Gool, "DEX: Deep EXpectation of apparent age from a single image," ICCV, 2015.

from age-gender-estimation.

ah oops.. completely forgot about that. Thank you @yu4u

from age-gender-estimation.

By the way, how do you figure out the upper limit on how far this architecture can be taken? I'm sure this is more of a hardware limitation as well as how much time I'm willing to wait on, but are there any guidelines?

from age-gender-estimation.

Did you mean how to determine the size of the network?
I like WideResNet with moderate depth (16-22); it provides good trade-offs between accuracy and computational cost.

from age-gender-estimation.

@yu4u

I tried changing img_size to 224 and the model is performing really bad. For each of the 3 dense layers (i.e. classifying 3 things), loss was anywhere between 9 and 20 .. and accuracy didnt go anywhere even above 0.25. I didn't even bother finishing 30 epochs (i stopped at 28)

I am re-training with img_size at 64, but do you have any idea where I might have gone wrong and what are some things that I can tweak?

EDIT: Lowering to 32 img_size helped to lower loss ... currently on epoch 7:

Epoch 7/30 - loss: 3.7325
dense_3_loss: 1.4535 - dense_1_loss: 0.2372 - dense_2_loss: 1.5244
dense_3_acc: 0.3509 - dense_1_acc: 0.9 - dense_2_acc: 0.4345

from age-gender-estimation.

Currently, my implementation is not suitable for larger sizes of images (e.g. 224) for several reasons: 1) it saves and loads all raw images; it requires large amount of memory, 2) the stride of the network is only 4 (before pool (8, 8)) because small image size is assumed.

If you use the image size 224, it seems good idea to use officially supported pre-trained models:
https://keras.io/ja/applications/

from age-gender-estimation.

so what's the largest possible that would you'd recommend w/your implementation? im on Google compute w/12gb VRAM K80 GPU w/ 30gb RAM

from age-gender-estimation.

I think 64x64 is good enough because there seem to be many low resolution images in the dataset.

from age-gender-estimation.

Hi, I tried this project with your pretrained model with default depth and width but it is giving the wrong prediction. for example it is predicting age 43 F of a 80-year female lady. It is predicting wrong on each and every image.

from age-gender-estimation.

Please confirm that your backend and channel order are consistent with the pretrained model.

from age-gender-estimation.

I am using your pretrained model and my hardware specs are different from your one. Is that an issue?

from age-gender-estimation.

What is your backend?

from age-gender-estimation.

Hi, I'd like to ask you where I can see the calculation of this model? because its accuracy is bad from 0.2 to 0.4

from age-gender-estimation.

See:

https://github.com/yu4u/age-gender-estimation/blob/master/demo.py#L101-L105

from age-gender-estimation.

Thank you for your reply. But I mean train and test(validation) accuracy.
When I set the learning rate = 0.001 by all epochs, It would be trained for train dataset. but val_loss increased so there was an over-fitting(did not decrease val_loss)

from age-gender-estimation.

The validation accuracy is automatically calculated by Keras using validation_data=(X_test, [y_test_g, y_test_a]).
Overfitting would be alleviated by data augmentation.

from age-gender-estimation.