I'm looking into training an object detection network using Tensorflow, and I had a look at the TF2 Model Zoo. I noticed that there are noticeably less models there than in the directory /models/research/models/, including the MobileDet with SSDLite developed for the jetson xavier.
To clarify, the readme says that there is a MobileDet GPU with SSDLite, and that the model and checkpoints trained on COCO are provided, yet I couldn't find them anywhere in the repo.
How is one supposed to use those models?
I already have a custom-trained MobileDetv3 for image classification, and I was hoping to see a way to turn the network into an object detection network, in accordance with the MobileDetv3 paper. If this is not straightforward, training one network from scratch could be ok too, I just need to know where to even start from.
If you plan to use the object detection API, you can't use your existing model. You have to choose from a list of models here for v2 and here for v1
The documentation is very well maintained and the steps to train or validate or run inference (test) on custom data is very well explained here by the TensorFlow team. The link is meant for TensorFlow version v2. However, if you wish to use v1, the process is fairly similar and there are numerous blogs/videos explaining how to go about it
Related
My goal is to test out Google's BERT algorithm in Google Colab.
I'd like to use a pre-trained custom model for Finnish (https://github.com/TurkuNLP/FinBERT). The model can not be found on TFHub library. I have not found a way to load model with Tensorflow Hub.
Is there a neat way to load and use a custom model with Tensorflow Hub?
Fundamentally: yes. Everyone can create the kind of models that TF Hub hosts, and I hope authors of interesting models do consider that.
For TF1 and the hub.Module format tailored to it, see
https://www.tensorflow.org/hub/tf1_hub_module#creating_a_new_module
For TF2 and its revised SavedModel format, see
https://www.tensorflow.org/hub/tf2_saved_model#creating_savedmodels_for_tf_hub
That said, a sophisticated model like BERT requires a bit of attention to export it with all bells and whistles, so it helps to have some tooling to build on. The BERT reference implementation for TF2 at https://github.com/tensorflow/models/tree/master/official/nlp/bert comes with an open-sourced export_tfhub.py script, and anyone can use that to export custom BERT instances created from that code base.
However, I understand from https://github.com/TurkuNLP/FinBERT/blob/master/nlpl_tutorial/training_bert.md#general-info that you are using Nvidia's fork of the original TF1 implementation of BERT. There are Hub modules created from the original research code, but the tooling to that end has not been open-sourced, and Nvidia doesn't seem to have added their own either.
If that's not changing, you'll probably have to resort to doing things the pedestrian way and get acquainted with their codebase and load their checkpoints into it.
Is there any equivalent/alternate library to fastai in tensorfow for easier training and debugging deep learning models including analysis on results of trained model in Tensorflow.
Fastai is built on top of pytorch looking for similar one in tensorflow.
The obvious choice would be to use tf.keras.
It is bundled with tensorflow and is becoming its official "high-level" API -- to the point where in TF 2 you would probably need to go out of your way not using it at all.
It is clearly the source of inspiration for fastai to easy the use of pytorch as Keras does for tensorflow, as mentionned by the authors time and again:
Unfortunately, Pytorch was a long way from being a good option for part one of the course, which is designed to be accessible to people with no machine learning background. It did not have anything like the clear simple API of Keras for training models. Every project required dozens of lines of code just to implement the basics of training a neural network. Unlike Keras, where the defaults are thoughtfully chosen to be as useful as possible, Pytorch required everything to be specified in detail. However, we also realised that Keras could be even better. We noticed that we kept on making the same mistakes in Keras, such as failing to shuffle our data when we needed to, or vice versa. Also, many recent best practices were not being incorporated into Keras, particularly in the rapidly developing field of natural language processing. We wondered if we could build something that could be even better than Keras for rapidly training world-class deep learning models.
I am trying to find a worked example of neural network pruning for the Faster-RCNN architecture.
My core stack is Tensorflow 1.12, its object_detection API (link) on Python3.5.2 in Ubuntu 16.04 LTS. I came across some Neural Network Pruning repos (e.g. link, implementing NVIDIA's pruning paper with Taylor expansion link - looking the most promising however (a) implemented in Pytorch and (b) on classification networks rather than detectors).
I am also aware of the existence of a pruning functionality within TensorFlow under this package (link), but could only run an example found in the comments of the following StackOverflow question (link) to train and prune (not thoroughly tested) a simple Neural Network for hand written digits classification using MNIST dataset.
I am looking for a worked example and not reporting any bugs or issues in code.
Can someone point to me a worked example of pruning Faster-RCNN -or other detectors- found on the TensorFlow's object detection API (link), preferably using TensorFlow's pruning package (link)?
Pruning is orthogonal to the meta-architecture used for object detection. When we talk about the TensorFlow Object Detection API, it heavily relies on builders that read the config and create corresponding nets, classes etc. I believe you want to prune the feature extractor as the most heavy part. If so, you need to first prune some feature extractor from slim (let's say, Inception-V2), give it a name, add its pruned version to models, adjust proto config and many more. Shortly speaking, you need to introduce a new type of feature extractor. But I am not aware of any existing examples on that.
I'm a user of Tensorflow Object Detection API. I use it a lot to train models like Faster-RCNN on my images. From what I understand, there is a backbone network (in my experiences, ResNet) used to extract features.
I would like to re-use the weight of this specific network, but when I save my model, it's a Faster RCNN model and, even after hours in the documentation and in the source files, I don't see how to isolate the weight of the backbone network.
Is something somebody else already has realized before ? Or is Tensorflow OD API not the right tool for what I need ?
Thank you for your help or advises !
I have a question related to this one:
TensorFlow in production for real time predictions in high traffic app - how to use?
I want to setup TensorFlow Serving to do inference as a service for our other application. I see how TensorFlow Serving helps me to do that. Additionally, it mentions a continuous training pipeline, which probably is related to the possibility that TensorFlow Serving can serve with multiple versions of a trained model. But what I am not sure is how to retrain your model as you get new data. The other post mentions the idea to run retraining with cron jobs. However, I am not sure if automatic retraining is a good idea. What architecture would you propose for a continuous retraining pipeline with a system continuously facing new, labelled data?
Edit: It is a supervised learning case. The question is would you automatically retrain your model after n new datapoints came in or would you retrain during the downtime of the customer automatically or just retrain manually?
You probably want to use some kind of semi-supervised training. There's fairly extensive research in that area.
A crude, but expedient way, which works well, is to use the current best models that you have to label the new, incoming data. Models are typically able to produce a score (hopefully a logprob). You can use that score to only train on the data that fits well.
That is an approach that we have used in speech recognition and is an excellent baseline.