-
I've try to training v3-tiny model with the visdrone2019 dataset.
It doesn't seem converging so far.
Could you kindly give me some advice. Thanks a lot.
**Data**: The objects in this dataset is…
-
In order to detect small targets,I add new *mbox_* layers after conv3_3;
The configuration is
```prior_box_param {
min_size: 15.0
max_size: 30.0
aspect_ratio: 2
flip: true
…
-
I have dataset witch is not in annotated format. it have directory like this -
training_images //(folder name)
1.jpg
1.txt (bounding box information)
2.jpg
2.txt
…
-
I was trying to train a modified yolo network with some pre-trained weights for the given network only. But it's doesn't train and directly saves the weights.
. Chrome has some stuff too though it's a bit larger than what we need: https://gi…
-
Make the learning rate decay slower as it might be currently getting too small.
-
Hi Avanti, When I modify part of the example code and then have an error to be reported here. I don't know why. Could you help me out?
```python
tfmodisco_results = modisco.tfmodisco_workflow.workf…
-
### What should we add?
Currently, functions like `smooth_gaussian` return DataArrays with no names. This causes problems if you want to combine DataArrays into a Dataset, as in the following example…