Lesson 3 In-Class Discussion ✅

Part 1 (2019)
109

Can we use fastai for feature extraction?

1 Like
110

Looks like it’s here: https://github.com/fastai/fastai/blob/master/docs_src/data_block.ipynb

5 Likes
111

worked for me - im using the dev version

113

is it possible to do multi label classification with a model trained on single labels?

2 Likes
114

Can we use DataBlock API with text DataSet?

1 Like
115

If you mean getting the activations of a specific layer in a network yes, you can do this with hooks. You can see this thread or refer to the docs

2 Likes
116

Here the validation set is created by putting aside some part of the training set (20% randomly chosen). The test set doesn’t have labels (it’s a kaggle competition).

1 Like
117

Is there a way to make the buttons in jupyter notebook when you hit shift+Tab not giant?

2 Likes
118

how to add test set after model was trained using data without test images?

1 Like
119

Yes, very much so. You should get familiar with the process, but all steps come in a certain order to answer one specific problem. The block name comes from the fact you can use all the different strategies for labelling/putting aside a validation set/creating datasets/transforming plugged together like this.

6 Likes
120

Does this screw up the Shift+Tab-ability of these functions?

1 Like
121

are these data augmentation features documented, which does what?

1 Like
122

I’d look at the doc :wink:

2 Likes
123

I get name 'Config' is not defined when I try to run path = Config.data_path()/'planet'

Any idea why?

124

can i use custom define loss in fastai?

1 Like
125

Not up to date with the library?

126

I think of DataBlocks as kind of like how we layered our models. All the piece gets stacked up in order:

nn.Sequential(
    Flatten(),
    nn.ReLU(),
    nn.Dropout(0.5),
    nn.Linear(25088,256),
    nn.ReLU(),
    nn.BatchNorm1d(256),
    nn.Dropout(0.5),
    nn.Linear(256,4+len(cats)),
)
5 Likes
127

Is it possible to change the cost function in fastai?

128

Of course, you can plug it in learn.loss_func.

4 Likes
129

Up until now I’ve heard the terms DataSet, DataBunch, and DataBlocks. Is there a doc somewhere that explains the difference between them?

1 Like