I'm new to tensorflow and the inception model. I found the following tutorial online (https://www.tensorflow.org/versions/master/how_tos/image_retraining/) and wanted to test this on my own project.
I'm trying to let the model recognize ethnicity based on people in a picture. I have made a training set of approx 850 images per category.
For some reason I'm unable to get more than a 65% accuracy level. I tried increasing the training steps and amount of images as well.
Maybe the inception model is not the correct model to use for this?
Could someone point me in a good direction of what I can do to improve the results?
Regards,
P.
Do you get 65% accuracy on the train or on the test set?
If it is on the train set, you are probably doing something wrong with your code.
If it is on the test set, you are indeed using the wrong model. The Inception model is a very very big model, and having only 850 images per category won't give you a good general model. It will simply "remember" those 850 images. (think of remembering the answer to each question on a test, instead of learning for a test)
Maybe you can try building a simpler, smaller model first and see how well that model learns!
Related
I have a question in deeplab v3 accuracy right now the best accuracy(mIOU) achieved by the model xception65_coco_voc_trainval 87.80. I was wondering that can we further increase it if i train the model for less number of class lets say for person only using the same dataset or it will not make any difference.
The problem is along the edges model has problem identifying it correctly. The orignal image had all green background and after applying the mask some greenish remains. So 2 questions in short
1. If i train for single class then will accuracy improve ?
2. If not then is there any other method i can apply to achive better results
Note:
Background doesn't have to be green in all cases.
i saw the remove.bg website and they have done good job, does any one knows what approach have they taken to achieve good results
Thanks
I am re-training the SSD MobileNet with 900 images from the Berkeley Deep Drive dataset, and eval towards 100 images from that dataset.
The problem is that after about 24 hours of training, the totalloss seems unable to go below 2.0:
And the corresponding mAP score is quite unstable:
In fact, I have actually tried to train for about 48 hours, and the TotoalLoss just cannot go below 2.0, something ranging from 2.5~3.0. And during that time, mAP is even lower..
So here is my question, given my situation (I really don't need any "high-precision" model, as you can see, I pick 900 images for training and would like to simply do a PoC model training/predication and that's it), when should I stop the training and obtain a reasonably performed model?
indeed for detection you need to finetune the network, since you are using SSD, there are already some sources out there:
https://gluon-cv.mxnet.io/build/examples_detection/finetune_detection.html (This one specifically for an SSD Model, uses mxnet but you can use the same with TF)
You can watch a very nice finetuning intro here
This repo has a nice fine tuning option enabled as long as you write your dataloader, check it out here
In general your error can be attributed to many factors, the learning rate you are using, the characteristics of the images themselves (are they normalized?) If the ssd network you are using was trained with normalized data and you don't normalize to retrain then you'll get stuck while learning. Also what learning rate are they using?
From the model zoo I can see that for SSD there are models trained on COCO
And models trained on Open Images:
If for example you are using ssd_inception_v2_coco, there is a truncated_normal_initializer in the input layers, so take that into consideration, also make sure the input sizes are the same that the ones you provide to the model.
You can get very good detections even with little data if you also include many augmentations and take into account the rest of the things I mentioned, more details on your code would help to see where the problem lies.
I need a tensorflow model which recognizes a dog's breed. I downloaded the Stanford Dogs Dataset - 20,580 images in 120 categories (=breeds). I followed the procedure described in TensorFlow For Poets to retrain mobilenet_1.0_224. I used --how_many_training_steps=4000 and defaults for everything else. I got this tensorboard graph:
Training and validation accuracy
The validation accuracy is only about 80%.
What can I do to improve it?
In the research paper MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications, the test accuracy using the 'MobileNet_1.0_224' architecture on the Stanford Dogs dataset is 83.3%, which seems in line with your results.
When you visually examine the Stanford Dogs Dataset you will find a lot of the breeds look similar, which makes it hard to reach a higher accuracy, even with the state of the art image classifiers in accuracy. You might improve your results by either splitting similar looking breeds into larger subcategories.
Alternatively, you might tweak the training settings of the retrain.py script in the Tensorflow for Poets tutorial, but the gains will be likely be marginal.
I just try to dive into TensorFlows Object Detection. I have a very small training set of circa 40 images yet. Each image can have up to 3 classes. But now the question came into my mind: Does every training image need every class? Is that important for efficient training? Or is it okay if an image may only have one of the object classes?
I get a very high total loss with ~8.0 and thought this might be the reason for this but I couldn't find an answer.
In general machine learning systems can cope with some amount of noise.
An image missing labels or having the wrong labels is fine as long as overall you have sufficient data for the model to figure it out.
40 examples for image classification sounds very small. It might work if you start with a pre-trained image network and there are few classes that are very easy to distinguish.
Ignore absolute the loss value, it doesn't mean anything. Look at the curve to see that the loss is decreasing and stop the training when the curve flattens out. Compare the loss value to a test dataset to check if the values are sufficiently similar (you are not overfitting). You might be able to compare to another training of the exact same system (to check if the training is stable for example).
I have followed this Tensorflow tutorial on transfer learning with the Inception model using my own dataset of 640x360 images. My question comes in 2 parts
1) My data set conatains 640x360 images. Is the first operation that happens a downsampling to 299x299? I ask because I have a higher res version of the same dataset and I am wondering if training with the higher resolution images will result in different performance (hopefully better)
2) When running the network (using tf.sess.run()) is my input image down-sampled to 299x299?
Note: I have seen the 299x299 resolution stat listed many places online like this one and I am confused at exactly which images its referring to; the initial training dataset images (for Inception I think it was imagenet), the transfer learning dataset (my personal one), the input image when running the CNN, or a combination of the 3.
Thanks in advance :)
The inception model will resize your image to 299x299. This can be confirmed by visualizing the tensorflow graph. If you have enough samples to do the transfer learning, the accuracy will be good enough with resizing to 299x299. But if you really want to try out the training with actual resolution, the initial input layers of the graph size needs to be changed