-
**Describe the bug**
I am running the Criteo example, documented[ here](https://cloud.google.com/blog/products/gcp/using-google-cloud-machine-learning-to-predict-clicks-at-scale). I can run the prepr…
-
In a case where you have a long way, and are on one end of it (but iD knows that way is straight 'enough' to allow 'straighten' as a choice), it's possible to straighten a way from one end, and have i…
-
I start train_and_eval:
```bash
onmt-main train_and_eval --config/sample.yml --model_type Transformer
```
and set `save_checkpoints_steps: 5000` in config/sample.yml.
But the training process s…
-
In optimize.py, the shift_factors code has a bug that gives some odd (but not entirely bad) results.
To compute the masses used to determine the shifts, the code sums over each neuron (`masses = np…
-
I have trained the SSD7 for my own custom data (same format as udacity dataset including number of same number of class) where prediction results are horrible. The training data size is 8K and validat…
-
HI, I spent some time looking over the guided_a3c example, documentation and reading the code for the BTgymRandomDataDomain class, and my question is: if I want to use pandas.resample() function and d…
-
to foster community involvement - some richer sample code beyond MNIST should be tackled.
Generative Adversarial Networks is a hot topic amongst ML - and some sample code using swift should help enco…
-
I mean what's the matter if I set a big lambda_A , thanks XD .
-
This is not exactly an issue, more a missing feature: In the flowers model, the loss function only takes into account data loss and no regularization (such as L2 regularization) is possible except dro…
-
preliminary list of things that should or might go into 0.7
see issues for milestone 0.7 for some of the details
Note: We are planning for a short 0.7 release cycle, so prioritizing and trimming will…