mrdbourke / pytorch-deep-learning Goto Github PK

Hi all,

With the pytorch version 1.11 (and 1.12), the trick that Daniel uses (hidden_units*7*7) doesn;'t work. It worked I believe because the output in 1.10 of Conv_layer_2 =[1,10,7,7]. Multiplying each unit 10*7*7 = 490 and delivers [1,490] and thus solving this by using hidden_units*7*7 works in 1.10.

In 1.11 and 1.12, the output of conv_layer_2 is however is [10, 7, 7], leading to 7*7 and a size of [10*49]. Hence, you cannot solve the input by doing hidden*7*7 (results in 490) but rather, simply 7*7.

thus the linear layer becomes:

nn.Linear(in_features=7*7, out_features=output_shape)

Using this the shapes match and it will work on a single image,

Yet when training you will need the hidden*7*7 setup as it wont work otherwise.

Originally posted by @aronvandepol in #68

https://www.learnpytorch.io/06_pytorch_transfer_learning/

Says langauge model instead of language model.

For example, after training the model, to verify the effect of the model, you need f1 score, confusion matrix, etc.

Not sure what's happening with Notebook 03... seems to be breaking the documentation building process

Might have to manually turn it into a new notebook.

As in copy all of the contents of different cells to new cells.

Not ideal... but I'll try this tomorrow.

See the action breakage here: https://github.com/mrdbourke/pytorch-deep-learning/runs/5621310937?check_suite_focus=true

Create a template to include things like:

• Video timestamp
• Resource watching the video (e.g. YouTube, ZTM etc)
• "What I've tried so far..."
• "Where the code is running..." (e.g. Colab)

This notebook/section should turn the functions used in 04 into scripts that can be used for the rest of the course.

Should also make sure the model that comes out of 05, which will be a continuation of the model in 04 can fit the data of pizza, steak, sushi reasonably well.