hardianlawi / mtl-homoscedastic-uncertainty

Multi Task Learning Implementation with Homoscedastic Uncertainty in Tensorflow

Hi there 👋

• 👨🏻‍💻 I’m currently working full-time in a startup building a platform for productive discourse with purpose.
• 👯 I’m looking to collaborate on any "high impact" projects such as open-source ML tools, kaggle, etc.
• 📚 I'm interested in applied ML, ML ops/system, trading and investing.

mtl-homoscedastic-uncertainty's Issues

Example training file

Could you provide some example files for the training of the network? It seems like it's expecting a CSV file that will provide the full paths to the training images, correct? I would appreciate if you could send me also any other additional but needed file. Thank you for your time.

Shape of weight variables

Is the shape of the variable = []?
It is [1,] in the author's implementation and it works fine on another example with shape= [1,] but it does not work with shape=[]

Possible bug in binary classification logits in MTL estimator

In L118 it you update the the logit dictionary with logits[target_name] = logits[target_name]/uncertainties[target_name]

You later do this again when computing the task specific loss for binary classification
specific_loss = tf.nn.sigmoid_cross_entropy_with_logits( labels=labels[target_name], logits=logits[target_name]/uncertainties[target_name], )

binary cross entropy loss function

Hi, @hardianlawi !
I have referenced you code in my click-through rate prediction project.
However, one of my task could not converge and I have a question about the inconsistency regarding the binary cross entropy loss function and your implementation.

The loss function has added by the log of each task's theta, but you didn't include it in your implementation here:

MTL-Homoscedastic-Uncertainty/scripts/estimators.py

Line 149 in d3aa7e0

specific_loss = tf.nn.sigmoid_cross_entropy_with_logits(