Lesson 2 In-Class Discussion ✅

Part 1 (2019)
95

@rachel Ppl in previous thread were asking why ConvLearner name was changed to create_cnn.

7 Likes
96

I do not know if it is true in Fastai, but in Keras, if you have dropout layer, your training loss can be higher than validation loss, since dropout is not applied during validation.

1 Like
100

Looking at the Teddy, Grizzly, Black Bear classification problem, what can I do If I have pictures with another animal, e.g. a Zebra, but no Zebra training data? Is there an option to say “other” in general in classification?

3 Likes
101

Rachel I can confirm this one had a lot of likes.

3 Likes
102

That pixel-to-numbers graphic is from this article: https://medium.com/@ageitgey/machine-learning-is-fun-part-3-deep-learning-and-convolutional-neural-networks-f40359318721

It’s part of a series that looks really good. The author has more great looking deep learning articles here: https://medium.com/@ageitgey

19 Likes
103

Hey I have upgraded using commands in https://forums.fast.ai/t/faq-resources-and-official-course-updates/27934 that and it is showing
‘Name: fastai
Version: 1.0.18’

But still getting not found error for download_images . I am on salamander.ai

1 Like
104

can anyone help with this error “NameError: name ‘download_images’ is not defined”

3 Likes
105

is it always fine to just randomly split validation set and training set?

106

I am getting error even after successful upgrade

107

check your fastai.version

108

from my experience is no. Since dropout is not applied during validation, at least on Keras.

1 Like
109

Not in my experience on tabular data

2 Likes
110

@Rachel There are a few likes regarding the mysterious 3s in the end points on the range of values passed in to the learning rate finder:

4 Likes
111

import fastai
print(fastai.version)
1.0.15

1 Like
112

Do we have to reinstall everytime it changes version? I assume git pull just gets the code not the update of fastai

113

Might be different on tabular data, but for CNNs nine times out of ten validation error still goes below training error by the end

1 Like
114

Name: fastai Version: 1.0.18 Summary: fastai makes deep learning with PyTorch faster, more accurate, and easier

115

can learn.recorder.plot_losses() be explained in a bit more detail? why train_loss is plotted for each iteration whereas val_loss is plotted after each epoch?

116

Thanks! I wonder if there is anyone who looks at this rigorously…

1 Like
117

Git pull is just for the nbs/doc/materials. The libraries should be updated with pip or conda.

1 Like