Jeremy will cover NLP and ULMFit in much more detail in a future lesson. This was just a brief example.
Very similar yes. I haven’t read the details of the proof, but I’m pretty sure both of them use the same mathematical theorem behind the scenes.
Yes, I think it’s the same concept.
I understand how fully connected layers relate to linear models, but don’t convolution layers do something sort of different?
Some satellite images has 4 channels, how can we deal with 4 channels or 2 channels datasets using pretrained models?
Character level language models are interesting too http://karpathy.github.io/2015/05/21/rnn-effectiveness/
For 2 channels you could create a dummy 3rd channel that is the average of the 2 channels
Like if another channel is from a depth sensor, like in the head pose data from the Kinect?
are certain shapes, or classification problems, more suited to say relu. for example with fourier (sp) transforms takes a ton of terms to build a step change, but one term to build a sine wave. is there something analogous four relu and the size of architecture, or size of middle layers?
For 4 channels, you could try to do some kind of dimensionality reduction (linear combinations of channels?) to transform to 3 channels.
Does predict function return multiple labels for multi-label classification?
Is it possible to create a model that can predict a class and a regression number by just creating the correct databunch?
Well, you can train two separate learners for that purpose.
Thank you! As always, great class
btw, congrats to everyone on still being here live. We have lost a lot of live viewers
lesson 1 had >1000, lesson 2 still >500, today we were down to a max of 278 youtube watchers if I saw correctly! (edit: others saw 400 watchers in the beginning) I still think it’s worth it getting up early!
But it might be better to learn the class and the regression number simultaneously.
After having converted the dicom images to png files i created the following open_image substitute. The you can use the pretrained model for rgb images as in the course resnet34, resnet50 …
#Function to open 16bit grayscale (fx an xray as png) and convert it to an rgb-tensor without loss of precision
#then you can assing it to the datasets like so: dsTrain.image_opener = dsValid.image_opener = open_image_16bit2rgb
#or use the datablock logic (i have not tried that)
def open_image_16bit2rgb( fn ):
a = np.asarray(PIL.Image.open( fn ))
a = np.expand_dims(a,axis=2)
a = np.repeat(a, 3, axis=2)
return Image( pil2tensor(a, np.float32 ).div(65535) )
Question: In the notebook it says we need to use “ImageMultiDataset” and it sounds like something to do manually or pay attention to. But I cannot find any reference to that afterwards. Is that change done automatically when using the .label_from_csv()? After running the notebook and looking at predictions (learn.TTA()),it seems like the output goes through a softmax and not sigmoid. This should not be the case for a mulitlabel problem?!