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

Some minor typos in chapter 11

Browse Source
This commit is contained in:
alvarotap 2020-04-17 12:20:29 +02:00 committed by GitHub
parent b8184baaf0
commit 3ba44079f7
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
11_midlevel_data.ipynb
View File

@ -61,7 +61,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"The factory method `TextDataLoaders.from_folder` is very convenient when your data is arranged the exact same way as the IMDb dataset, but in practice, that often won't be the case. The data block API offers more flexibility. As we saw in the last chapter, we can ge the same result with:"
"The factory method `TextDataLoaders.from_folder` is very convenient when your data is arranged the exact same way as the IMDb dataset, but in practice, that often won't be the case. The data block API offers more flexibility. As we saw in the last chapter, we can get the same result with:"
]
},
{
@ -147,29 +147,6 @@
"toks[0]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"tensor([ 2, 8, 20, 27, 11, 88, 18, 53, 3286, 45])"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"num = Numericalize()\n",
"num.setup(toks)\n",
"nums = toks.map(num)\n",
"nums[0][:10]"
]
},
{
"cell_type": "markdown",
"metadata": {},
@ -1079,7 +1056,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"Here the resize transform is applied to each of the two images, but not the boolean flag. Even if we have a custom type, we can thus benefit form all the data augmentation transforms inside the library.\n",
"Here the resize transform is applied to each of the two images, but not the boolean flag. Even if we have a custom type, we can thus benefit from all the data augmentation transforms inside the library.\n",
"\n",
"We are now ready to build the `Transform` that we will use to get our data ready for a Siamese model. First, we will need a function to determine the class of all our images:"
]
@ -1098,7 +1075,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"Then here is our main transform. For each image, il will, with a probability of 0.5, draw an image from the same class and return a `SiameseImage` with a true label, or draw an image from another class and a return a `SiameseImage` with a false label. This is all done in the private `_draw` function. There is one difference between the training and validation set, which is why the transform needs to be initialized with the splits: on the training set, we will make that random pick each time we read an image, whereas on the validation set, we make this random pick once and for all at initialization. This way, we get more varied samples during training, but always the same validation set."
"Then here is our main transform. For each image, il will, with a probability of 0.5, draw an image from the same class and return a `SiameseImage` with a true label, or draw an image from another class and return a `SiameseImage` with a false label. This is all done in the private `_draw` function. There is one difference between the training and validation set, which is why the transform needs to be initialized with the splits: on the training set, we will make that random pick each time we read an image, whereas on the validation set, we make this random pick once and for all at initialization. This way, we get more varied samples during training, but always the same validation set."
]
},
{
@ -1220,7 +1197,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"And we have can now train a model using those `DataLoaders`. It needs a bit more customization than the usual model provided by `cnn_learner` since it has to take two images instead of one. We will see how to create such a model and train it in <<chapter_arch_dtails>>."
"And we can now train a model using those `DataLoaders`. It needs a bit more customization than the usual model provided by `cnn_learner` since it has to take two images instead of one. We will see how to create such a model and train it in <<chapter_arch_dtails>>."
]
},
{