Use the idea of https://github.com/tomgoldstein/loss-landscape to visualize the loss function.
# learn.fine_tune(2)
learn.load('resnet34')

<fastai.learner.Learner at 0x7f09d50b89a0>

TODO:

  • [ ] Report progress back to js.
clientEvents

Events (
  SEND_DATA: socket/socketReceiveData
  INVALID_EVENT: socket/socketInvalidEvent
  SEND_IMAGE_INPUT: socket/socketReceiveImageInput
  NOIMAGE_HEATMAP: socket/socketNoImageHeatmap
  SEND_HEATMAP: socket/socketReceiveHeatmap
  SEND_ERROR: socket/socketError
  CLOSE_CLIENT: socket/socketServerClosed
  SEND_LANDSCAPE: socket/socketReceiveLossLandscape
)

Utils

Event handler

get_loss_landscape[source]

get_loss_landscape(websocket, payload=None)

Sends the loss landscape for the model.

learn.fastexplorer()

INFO:root:To visualize the model information, go to:
INFO:root:https://renato145.github.io/fastexplorer-js
INFO:     Started server process [1705]
INFO:uvicorn.error:Started server process [1705]
INFO:     Waiting for application startup.
INFO:uvicorn.error:Waiting for application startup.
INFO:     Application startup complete.
INFO:uvicorn.error:Application startup complete.
INFO:     Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)
INFO:uvicorn.error:Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)
INFO:     Shutting down
INFO:uvicorn.error:Shutting down
INFO:     Waiting for application shutdown.
INFO:uvicorn.error:Waiting for application shutdown.
INFO:     Application shutdown complete.
INFO:uvicorn.error:Application shutdown complete.
INFO:     Finished server process [1705]
INFO:uvicorn.error:Finished server process [1705]