-
This is a question, not a bug. @AlexeyAB is there a way to incorporate the "Visually Coherent Image Mixup" augmentation strategy? Amazon recently published a paper that claims that this approach resul…
-
Hey @AlexeyAB , I am getting segmentation fault while trying to run yolov4-tiny model in Jetson Nano using darknet.py file. However, the same thing with the same code is working fine on my system. But…
-
Hi @pythonlessons
I have trained a custom tiny-yolov3-prn model using AlexCarey Darknet. While using Convert_to_pb script to convert darknet weights into tensorflow, Iam facing the below error:
…
-
## PAN
```
... -> PAN -> Dim(batch, y, x, #anchors * (xywh + conf + #classes)) ~#size
```
## Head
```
raw -> sigmoid -> raw, sig
raw, sig -> split -> Dim(batch, y, x, xywh + conf + #class…
-
Could you provide pretrained weights file you have used? When I tried to use the files in the provided link, the assertion fails and gives "AssertionError: failed to read all data". I believe the weig…
Bekci updated
4 years ago
-
On the RTX 2080Ti (CUDA 10.0, TensorRT 6.05, Cudnn 7.6.01):
for yoloV4 608x608, source image is 1080*1920:
darknet source code process each image about 40 milliseconds, however, tensorrt + yoloV…
-
im trained a weights file by darknet yolov4-tiny,
there are 3 classes in my custom dataset, so my .cfg file for darknet:
```
[net]
# Testing
#batch=1
#subdivisions=1
# Training
batch=32
su…
-
Does anyone has experience about this trt-engine loading with flask api,
the following code works well if I am not using flask api
```python
# .....
# ... codes from `trt_yolo.py`
# .....
i…
-
**Mosaic-data** augmentation (like [CutMix](https://arxiv.org/abs/1905.04899) augmentation): https://github.com/AlexeyAB/darknet/issues/3114#issuecomment-552158041
* Mosaic-data mAP increasing: htt…
-
Hello @jkjung-avt !
After 50 hours running , the installation script for Tensorflow 2.3.0 failed with the following message
ERROR: /home/mluser/src/tensorflow-2.3.0/tensorflow/python/keras/api/…