Scratchpad

[ymoisan]

• log files in JSON (easier parsing and future interop ?)
• Trap standard error (AWS) and add full python traceback in output.txt
• Fonctions lambda dans GH ?? (t3.large revenu!)
• possible memory leak during images_to_samples.py (with file ...; wrap in a Python lambda ?)
• Log files renaming --> add the config file name in the log name

[mpelchat04]

Active Learning

Active learning aims to facilitate the annotation process by letting the model choose candidates for new annotations. After a phase of training, the model runs inference on a stack of unlabeled images. We then calculate entropy mesure on the predicted sample and use samples with low entropy (or uncertainty) as new candidate for annotations. The annotator is put to contribution in order to accept/reject the proposed annotations. The accepted annotations are then incorporated into the training dataset and we start a new iteration of training.
How the annotations will be accepted/rejected is still to be determined...

[mpelchat04]

Test the Intel Python distribution

Intel claims their Python distro is much faster for anything numeric. Since it can be installed with conda, can we give it a try ?

[mpelchat04]

Federated learning

"In a typical machine learning system, an optimization algorithm like Stochastic Gradient Descent (SGD) runs on a large dataset partitioned homogeneously across servers in the cloud. Such highly iterative algorithms require low-latency, high-throughput connections to the training data. But in the Federated Learning setting, the data is distributed across millions of devices in a highly uneven fashion. In addition, these devices have significantly higher-latency, lower-throughput connections and are only intermittently available for training." https://ai.googleblog.com/2017/04/federated-learning-collaborative.html

Could this be applied in a later stage, e.g. to optimize our model through time ?