-
Thanks for the contribution first!
I have a question here. I'm doing some research of tiny-yolo so I need to reproduce the result, which is the mAP, of tiny-yolo. In the [README.md](https://github.c…
-
Relevant information from `pip freeze`:
```
coremltools==3.0b3
tensorflow==1.12.0
tfcoreml==0.4.0b1
```
Script used:
```python
import tfcoreml as tf_converter
tf_graph_path = '/wayfair/…
-
-
Hi,
I wanted to ask if it's possible to somehow compress images and annotations in one file. Something like numpy array? Because when dataset is small it's not big deal, but when dataset is big (in m…
-
I started using your yolov3 framework to detect cracks on metal drilling parts. I would appreciate some hints on how to fine tune the the yolov3 network and its hyperparameters to be able detecting lo…
-
Hello,
Is it possible to create a superclass and a subclass using LSTM version of yolov3-spp? For example superclass ("person") and subclasses ("jumping" or "standing")
Thanks in advance!
-
**Describe the bug**
Running Example:-Train-Single-Class in google colab hangs and is not improving mAP
**To Reproduce**
Steps to reproduce the behavior:
1. Open Google Colab Notebook...
2. Run…
-
@glenn-jocher
in yolov3.cfg, the width and height are 416, the anchor: 10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326
in yolov3-spp.cfg, the width and height are 608, th…
-
I have wrapped libdarknet.so in python using an adapted derivative of the reference ctypes wrapper provided in this repo. This is then used as a library by a (python) ROS node. This node is probably n…
-
@AlexeyAB : Max Pool is for reducing the feature map size but if we choose stride=1, it retains the same size. I am talking about the final maxpool layer of yolov3-tiny. Is there any purpose for this …