Skip to content

Epoch bugfix #193

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Epoch bugfix #193

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ec0974f
Fix the Kaggle Dogs vs Cats competition link
kristjanr Dec 19, 2017
ddaedf2
Fix a bug and use epoch variable in the for loop instead of the const…
kristjanr Dec 23, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions deeplearning1/nbs/dogs_cats_redux.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -428,7 +428,7 @@
"latest_weights_filename = None\n",
"for epoch in range(no_of_epochs):\n",
" print \"Running epoch: %d\" % epoch\n",
" vgg.fit(batches, val_batches, nb_epoch=1)\n",
" vgg.fit(batches, val_batches, nb_epoch=epoch)\n",
" latest_weights_filename = 'ft%d.h5' % epoch\n",
" vgg.model.save_weights(results_path+latest_weights_filename)\n",
"print \"Completed %s fit operations\" % no_of_epochs"
Expand Down Expand Up @@ -1049,13 +1049,13 @@
{
"ename": "NameError",
"evalue": "name 'isdog' is not defined",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-125-78995ae88977>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0;31m#So to play it safe, we use a sneaky trick to round down our edge predictions\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2\u001b[0m \u001b[0;31m#Swap all ones with .95 and all zeros with .05\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 3\u001b[0;31m \u001b[0misdog\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0misdog\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mclip\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmin\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m0.05\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmax\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m0.95\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[0;31mNameError\u001b[0m: name 'isdog' is not defined"
]
],
"output_type": "error"
}
],
"source": [
Expand Down Expand Up @@ -1249,7 +1249,7 @@
"navigate_menu": true,
"number_sections": true,
"sideBar": true,
"threshold": 6,
"threshold": 6.0,
"toc_cell": false,
"toc_section_display": "block",
"toc_window_display": false
Expand Down
2 changes: 1 addition & 1 deletion deeplearning1/nbs/lesson1.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"We're going to try to create a model to enter the [Dogs vs Cats](https://www.kaggle.com/c/dogs-vs-cats) competition at Kaggle. There are 25,000 labelled dog and cat photos available for training, and 12,500 in the test set that we have to try to label for this competition. According to the Kaggle web-site, when this competition was launched (end of 2013): *\"**State of the art**: The current literature suggests machine classifiers can score above 80% accuracy on this task\"*. So if we can beat 80%, then we will be at the cutting edge as of 2013!"
"We're going to try to create a model to enter the [Dogs vs Cats](https://www.kaggle.com/c/dogs-vs-cats-redux-kernels-edition) competition at Kaggle. There are 25,000 labelled dog and cat photos available for training, and 12,500 in the test set that we have to try to label for this competition. According to the Kaggle web-site, when this competition was launched (end of 2013): *\"**State of the art**: The current literature suggests machine classifiers can score above 80% accuracy on this task\"*. So if we can beat 80%, then we will be at the cutting edge as of 2013!"
]
},
{
Expand Down