... | @@ -15,8 +15,11 @@ |
... | @@ -15,8 +15,11 @@ |
|
- [Weight visualization](manual-miscellaneous#weight-plotter)
|
|
- [Weight visualization](manual-miscellaneous#weight-plotter)
|
|
|
|
|
|
## Know Bugs/ Limitations:
|
|
## Know Bugs/ Limitations:
|
|
- 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
|
|
- The 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
|
|
|
|
|
|
- There exists an incompatibility with python-pyqt5.qtmultimedia (see #203), this leads that sometimes it is not possible to move the Layer Notes on some desktops. It is a 3rd party bug, to work around, please remove the python-pyqt5.qtmultimedia installtion.
|
|
|
|
- On Mate desktops a maximized Barista window hides the menu bar of Mate (see #213), this is also a 3rd party bug.
|
|
|
|
- On some desktops the characters of the title names from Note Items are cut of when they exceeds a certain length (see #186). This also happens with blobs of names. Its also the 3rd party bug, the calculation of Item size and text size does not works correctly.
|
|
|
|
|
|
## Weight plotter
|
|
## Weight plotter
|
|
The weight plotter can visualize the filter trained in the neural network (currently limited to convolutional layer).
|
|
The weight plotter can visualize the filter trained in the neural network (currently limited to convolutional layer).
|
... | | ... | |