• OS: Ubuntu 20.04
• PyQt version: pyqt5==5.10.1

It would be nice to mention the dependency on libxml2-dev libxslt1-dev in the docs when building from source on Ubuntu.

I've moved from Caffe/Digits to TensorFlow in my own work, and I want to update this to show how to do the same tasks with TensorFlow.

Given the hard work by @BirkhoffLee translating the original, I don't want to break what we already have. I'm debating whether to integrate it into the current document, or start a new one. I think it's nice to see how transferable the approach is across ML fr

Hi, thanks for the great code!

I wonder do you have plans to support resuming from checkpoints for classification? As we all know, in terms of training ImageNet, the training process is really long and it can be interrupted somehow, but I haven't notice any code related to "resume" in scripts/classification/train_imagenet.py.

Maybe @hetong007 ? Thanks in advance.

Thank you for the great effort, you are putting into this project :) There is, however, a feature I miss; rotated bounding boxes. Especially when objects are thin and diagonal, an ordinary bounding box fits poorly. Examples of such cases are shown here: rotated bounding boxes

A way annotation could be

• Explain in notebook/FAQ what non-maxima suppression is what values to set (threshold on IoU)
• Explain and provide code how to pick a good score threshold (reuse Patrick's plot which was implemented for the drone demo)

I tried building the docs, but was met with a graphviz error. Typically this means I can spend a few hours pecking away at the dependencies until I get stable build... or someone that has it working can export their environment, and publish an environment.yml that we can use with the build instructions.
I was going off of the d2l book since that's a dep here, but their [environment.yml](https://g

Dear TF Hub Team,

USE paper Section 5 has a interesting paragraph on evaluation where authors use Arc Cosine (Cos Inverse) whose range is 0 to Pi in radians instead of plain cosine distance with range 0 to 2.

". For the pairwise semantic similarity task, we directly assess
the similarity of the sentence embedding produced by our two encoders. As show

Hi,

I try to understand Deepdetect right now, starting with the Plattforms Docker container.
It looks great on pictures, but I have a hard time right now using it :)

My Problem: The docs seems to step over important points, like using JupyterLab. All examples shows the finished Custom masks, but how do I get them?

Is there something missing in the docs?

Example: https://www.deepdetec

(I will compile a list and hopefully open a PR if needed)

Describe the bug
This behavior is present in a plethora of catalyst's callbacks and losses. It's consistent, but it's definitely confusing for many new users.

To Reproduce
Steps to reproduce the behavior:
Use these functions/classes:
Callbacks

• [MeterMetricsCallback](https://github.com/catalyst-team/catalyst/blob/mas

We have a lot of repetitive instances in our data and it a simple Copy/Cut - Paste (Ctrl+C/X and Ctrl+V) function for bounding boxes would help speed up labelling by a lot!

Edit: Also multi-selection of multiple boxes/geometries would be great for a faster workflow

with video_demo.py about 20% speed compared to your 1.0 repo. but thanks much for sharing!

Thanks so much for your implementation. But I have several questions:

1. In the below picture, it seems that the class with less numbers is sampled repeatedly, while the class with more numbers is sub-sampled. So I wonder what's the difference between your method and traditional method?

![image](https://user-images.githubusercontent.com/13477956/53692261-7dcec580-3dc7-11e9-9363-968f3519bc81.p