-
Things like `classes=da.unique(y)` may be inefficient. This will have to be called on each block of data, which is expensive especially if the `y` isn't persisted.
Things like `sample_weight` are t…
-
# Details
## Description:
This document will be for planning our group’s presentation on College Board’s AP CSA Unit 5. It will be done in markdown format on this google document first so th…
-
In the original paper, bias correction layer consists of only two parameters "alpha" and "beta", which are only applied to the logits corresponding to the last trained group of classes. Here it seems …
-
**Introduction or background of this discussion**:
Guide for running the example of robot/lifelong_learning_bench/semantic-segmentation
**Contents of this discussion**:
These days I was …
-
How to reproduce the results of the coco dataset
When I first trained 70 classes,the“e2e_faster_rcnn_R_50_C4_1x.yaml”：
`MODEL:
META_ARCHITECTURE: "GeneralizedRCNN"
WEIGHT: "catalog://ImageNetP…
-
## Discussion
### What aspect of the language would you like to see improved?
I would like to see some form of incremental compilation implemented in Crystal so compilation does not slow down si…
-
**System information**
- OS Platform and Distribution (e.g., Linux Ubuntu 20.04): Ubuntu 20.04
- DeepRec version or commit id: 23252970
- Python version: python3.6.9
- Bazel version (if compiling…
HH-66 updated
4 months ago
-
The manner in which features captured in the latent spaces of our mutli-scale, multi-modal VAEs are lifted into other systems is a primary design concern. Before proposing a completely integrated appr…
-
@AlexeyAB If i train my yolov3 on k classes and get the weights generated. Now, if I want to add one more class to it .How to do it
Approach 1 :- Do I need to make k+1 classes in my cfg and then t…
-
- **Model-Free vs Model-Based RL**
>1)**Model-based** algorithmis an algorithm that uses _the transition function_ (and _the reward function_) in order to estimate the optimal policy.
> The age…