Comments (4)
- this code doesnt work either:
tsne_to_grid_plotter_manual(tsne_results[:, 0], tsne_results[:, 1],
selected_filenames)
---------------------------------------------------------------------------
IndexError Traceback (most recent call last)
Cell In[72], line 1
----> 1 tsne_to_grid_plotter_manual(tsne_results[:, 0], tsne_results[:, 1],
2 selected_filenames)
Cell In[71], line 11, in tsne_to_grid_plotter_manual(x, y, selected_filenames)
9 x_y_dict = {}
10 for i, image_path in enumerate(selected_filenames):
---> 11 a = np.ceil(x[i] * (S - s))
12 b = np.ceil(y[i] * (S - s))
13 a = int(a - np.mod(a, s))
IndexError: index 2176 is out of bounds for axis 0 with size 2176
from practical-deep-learning-book.
- and this:
for i in range(3):
random_image_index = random.randint(0, num_images)
distances, indices = neighbors.kneighbors(
[feature_list[random_image_index]])
# Don't take the first closest image as it will be the same image
similar_image_paths = [filenames[random_image_index]] + \
[filenames[indices[0][i]] for i in range(1, 4)]
plot_images(similar_image_paths, distances[0])
gives:
IndexError: index 5281 is out of bounds for axis 0 with size 2176
but i fix this point:
random_image_index = random.randint(0, 2176)
from practical-deep-learning-book.
perhaps, it because i have less features extracted:
num_images = len(filenames)
num_features_per_image = len(feature_list[0])
print("Number of images = ", num_images)
print("Number of features per image = ", num_features_per_image)
Number of images = 8677
Number of features per image = 2048
in Books example:
Number of images = 8677
Number of features per image = 100352
dont know why that happened ?
from practical-deep-learning-book.
fixed in #169
from practical-deep-learning-book.
Related Issues (20)
- Cannot load 2-colab-what-does-my-neural-network-think.ipynb HOT 2
- Predicted Class Name not plottted in Ch2-what-does-my-neural-network-think.ipynb HOT 1
- requirements.txt HOT 2
- Invalid Argument Error HOT 6
- missing chapter HOT 1
- CV ML AL Book
- Book
- chapter-4/1_feature_extraction.ipynb assumed running on colab
- chapter-4/1_feature_extraction.ipynb using default batch size 32 instead of defined batch_size 128 HOT 1
- chapter-4/2-similarity-search-level-2.ipynb Annoy section never loaded index after initializing, inaccurate performance measure
- chapter-4/3-reduce-feature-length-with-pca.ipynb Wrong data used in annoy section
- chapter-4/4-improving-accuracy-with-fine-tuning.ipynb does not contain the final finetuning section that is in book HOT 1
- chapter-4/1_feature_extraction.ipynb finetuned model was predicting 101 classes and not 2048 features HOT 2
- chapter-4/2-similarity-search-level-1.ipynb Broken float division HOT 4
- chapter-4/2-similarity-search-level-3.ipynb Accuracy calculation on 2048 dim is too slow HOT 1
- chapter-2/1-predict-class MobileNetV3Small
- chapter-5/1-develop-tool.ipynb
- chapter 9. Conversion of h5 model to pb.
- chapter 9. infer.py does not work, but i fixed it. HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from practical-deep-learning-book.