daviddoji/Fastbook_Julia
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

remove Normalize as stats are grabbed automatically (#502)

Browse Source 
* remove Normalize

* clean
This commit is contained in:
Hamel Husain
2022-03-06 15:48:34 -08:00
committed by GitHub
parent a251aae293
commit 035016fb0c
2 changed files with 8 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
06_multicat.ipynb
View File

@@ -1654,8 +1654,7 @@
" get_items=get_image_files,\n",
" get_y=get_ctr,\n",
" splitter=FuncSplitter(lambda o: o.parent.name=='13'),\n",
" batch_tfms=[*aug_transforms(size=(240,320)), \n",
" Normalize.from_stats(*imagenet_stats)]\n",
" batch_tfms=aug_transforms(size=(240,320)), \n",
")"
]
},
@@ -2169,11 +2168,11 @@
"split_at_heading": true
},
"kernelspec": {
"display_name": "Python 3",
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
}
},
"nbformat": 4,
"nbformat_minor": 2
"nbformat_minor": 4
}

11
clean/06_multicat.ipynb
View File

@@ -326,7 +326,7 @@
"source": [
"def binary_cross_entropy(inputs, targets):\n",
" inputs = inputs.sigmoid()\n",
" return -torch.where(targets==1, inputs, 1-inputs).log().mean()"
" return -torch.where(targets==1, 1-inputs, inputs).log().mean()"
]
},
{
@@ -534,8 +534,7 @@
" get_items=get_image_files,\n",
" get_y=get_ctr,\n",
" splitter=FuncSplitter(lambda o: o.parent.name=='13'),\n",
" batch_tfms=[*aug_transforms(size=(240,320)), \n",
" Normalize.from_stats(*imagenet_stats)]\n",
" batch_tfms=aug_transforms(size=(240,320)), \n",
")"
]
},
@@ -682,7 +681,7 @@
"1. When is it okay to tune a hyperparameter on the validation set?\n",
"1. How is `y_range` implemented in fastai? (See if you can implement it yourself and test it without peeking!)\n",
"1. What is a regression problem? What loss function should you use for such a problem?\n",
"1. What do you need to do to make sure the fastai library applies the same data augmentation to your inputs images and your target point coordinates?"
"1. What do you need to do to make sure the fastai library applies the same data augmentation to your input images and your target point coordinates?"
]
},
{
@@ -713,11 +712,11 @@
"split_at_heading": true
},
"kernelspec": {
"display_name": "Python 3",
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
}
},
"nbformat": 4,
"nbformat_minor": 2
"nbformat_minor": 4
}