|
|
|
## Know Bugs/ Limitations:
|
|
|
|
- not all informations(available layers,etc. ) get reloaded by changing the caffe path, some informations are always loaded from the path in the bashrc-file
|
|
|
|
- Layer types "MemoryData" and "Input" can't be used to run caffe inside of Barista. However, it can be used to build and export a net. see #200 and #219
|
|
|
|
- Incompatibility with python-pyqt5.qtmultimedia, see #203
|
|
|
|
|
|
|
|
## Weight plotter
|
|
|
|
The weight plotter can visualize the filter trained in the neural network (currently limited to convolutional layer).
|
|
|
|
![image](/uploads/ea6a7099e4e1c3f2ee052233215fc810/image.png)
|
|
|
|
By use of the three comboboxes the desired session, snapshot and layer can be chosen respectively.
|
|
|
|
By holding and dragging the left mouse button, the visualization can be panned in a desired direction.
|
|
|
|
Using the mouse wheel alters the scale of the picture.
|
|
|
|
A visualization can be saved by clicking the **save** button and entering a desired name and format-suffix.
|
|
|
|
|
|
|
|
[previous page](manual-training) |
|
|
|
\ No newline at end of file |