Part 1 (2017)


Welcome to forums.fast.ai ( 2 3 4 5 ) (89)
About the Part 1 (2017) category (4)
Cannot use Azure Free Trial (no GPU machines available) (14)
Nb_val_samples Error (2)
Reversing Alzheimer’s ( 2 ) (21)
Making your own server ( 17 18 19 20 21 22 23 24 25 26 27 28 ) (555)
Windows Installation | SSH Error (9)
Can’t connect to Jupyter Notebook (tried 3 different machines) ERR_CONNECTION_TIMED_OUT ( 2 ) (27)
Use of plot_confusion_matrix seems inaccurate (2)
Lesson 2 discussion ( 4 5 6 7 8 9 10 11 12 13 14 15 ) (293)
Kaggle Questions ( 2 3 4 ) (72)
Fast.ai Deep Learning Course Part1 Personal Learning Note Sharing (11)
Poor performance on Dogs vs Cats (11)
Data augmentation for NLP ( 2 ) (21)
Blog Posts, Projects and Articles ( 2 3 ) (53)
How to use bcolz.carray when data set is too large to load into memory? (6)
Email links to collaborative filtering and recommender systems (2)
Please explain why batch size matters (5)
Setup problems: AWS ( 36 37 38 39 40 41 42 43 44 45 46 47 ) (927)
What to do while waiting for models to train? (12)
Crestle [easier alternative to AWS] ( 2 3 4 5 6 7 8 ) (157)
Collapsable / expandable jupyter cells (12)
About bounding box localization ( 2 ) (33)
Picasso: A free open-source visualizer for Convolutional Neural Networks (2)
Lesson 3 - Most GPU memory used up before fitting the model (3)
Lesson 4/5 Movielens question - Dealing with new users/movies/rankings? (15)
Why is batch_size Doubled for val_batches (7)
Loss function for negative input in autoencoder (3)
When I am trying to fit a model I am getting error : Expected object of type torch.cuda.LongTensor but found type torch.cuda.IntTensor (3)
Jeremy Howard had emergency heart surgery ( 2 3 4 5 ) (95)