chapter 4:

- removing deprecated files - the gcloud sessions are not using the same runtime (so we need to re-download data) so writing outputs to gdrive to make sure things are running and outputs are accessible for subsequent notebooks in colab - renaming 4/1 notebook - since it had underscores instead of hyphens, the colab link in the notebook was not working - xception added to imports for notebook 1, since it is part of the model_maker - PracticalDL#163 - fixed - PracticalDL#164 - fixed - PracticalDL#169 - fixed - metric='angular' added for annoy as default arg will be removed in subsequent releases - removing a duplicate PCA + Annoy section - PracticalDL#170 - fixed - time is a negligible factor here, and we do not need it in the plots (since we are using optimised accuracy calculation using numpy from issue 170) - hence, modifying the plots - removing matplotlib.style.use('seaborn') since it is deprecated - the final fine-tuning notebook uses Caltech256 features (as per the book), which do not exist, since fine-tuning was done on Caltech101 - hence, renaming those files to caltech101. Can we retain caltech101 to test? - PracticalDL#167 - fixed, if the above is okay - formatted the code chapter 5: - write_grads and batch_size params have been removed from callback, or will be removed in subsequent releases - PracticalDL#174 - not able to replicate this issue - added a pointer to the notebook that suggests that for tensorboard to work without a 403 Forbidden error on Colab, cookies need to be allowed (I faced this issue) - notebook 3 in chapter 5 is the exact same as notebook 2 in chapter 2 - replaced the file directly - the autokeras notebook in Colab is named autokeras-error.ipynb - where can we change this to autokeras.ipynb? - fixing accuracy score calculation in the autokeras notebook - formatted the code chapter 6: - including the download_sample_image function - formatted the code
manavrmoorthy · Aug 28, 2023 · 90d5a6f · 90d5a6f
1 parent e1c1a62
commit 90d5a6f
Show file tree

Hide file tree

Showing 20 changed files with 37,534 additions and 6,231 deletions.
diff --git a/code/chapter-3/2-analyzing-the-results.ipynb b/code/chapter-3/2-analyzing-the-results.ipynb
diff --git a/code/chapter-4/1-feature-extraction-deprecated.ipynb b/code/chapter-4/1-feature-extraction-deprecated.ipynb
diff --git a/code/chapter-4/1-feature-extraction.ipynb b/code/chapter-4/1-feature-extraction.ipynb
diff --git a/code/chapter-4/1_feature_extraction.ipynb b/code/chapter-4/1_feature_extraction.ipynb
diff --git a/code/chapter-4/2-similarity-search-level-1.ipynb b/code/chapter-4/2-similarity-search-level-1.ipynb
diff --git a/code/chapter-4/2-similarity-search-level-2.ipynb b/code/chapter-4/2-similarity-search-level-2.ipynb
diff --git a/code/chapter-4/2-similarity-search-level-3.ipynb b/code/chapter-4/2-similarity-search-level-3.ipynb
diff --git a/code/chapter-4/3-reduce-feature-length-with-pca.ipynb b/code/chapter-4/3-reduce-feature-length-with-pca.ipynb
diff --git a/code/chapter-4/4-improving-accuracy-with-fine-tuning.ipynb b/code/chapter-4/4-improving-accuracy-with-fine-tuning.ipynb
diff --git a/code/chapter-4/README.md b/code/chapter-4/README.md
@@ -7,6 +7,8 @@ Like Google Reverse Image Search, we explore how one can use embeddings — a co
 Run the following command prior to running the scripts in this directory:
 
 `$ pip install annoy -U`
+`$ pip install nmslib -U`
+`$ pip install falconn -U`
 
 ## Code
 
@@ -23,4 +25,4 @@ In this portion of the chapter, we will find the least accurate (worst) performi
 
 ## Data
 
-We will be using the Caltech101 dataset. Please download the [Caltech101](http://www.vision.caltech.edu/Image_Datasets/Caltech101/101_ObjectCategories.tar.gz) dataset and place it in a `caltech101` directory.
+We will be using the [Caltech101](http://www.vision.caltech.edu/Image_Datasets/Caltech101/101_ObjectCategories.tar.gz) dataset. The commands for downloading the dataset can be found in the notebooks.
diff --git a/code/chapter-5/1-develop-tool.ipynb b/code/chapter-5/1-develop-tool.ipynb
diff --git a/code/chapter-5/1_develop_tool.ipynb b/code/chapter-5/1_develop_tool.ipynb
diff --git a/code/chapter-5/3-colab-what-does-my-neural-network-think.ipynb b/code/chapter-5/3-colab-what-does-my-neural-network-think.ipynb
diff --git a/code/chapter-5/3-colab-what-does-my-neural-network-think.ipynb.ipynb b/code/chapter-5/3-colab-what-does-my-neural-network-think.ipynb.ipynb