Comments (2)
This dataset is a very small one 28X28(ie 784 pixels) which is very less as compared to the pictures we use daily.
If you use the same dense network for a 256X256 image, you will see the performance of CNN is far better than a simple fully connected network.
Even in MNIST, with proper optimizer and loss, CNN works slightly better than fully connected.
(Use optimizer='adam', loss='sparse_categorical_crossentropy')
from introtodeeplearning.
Echoing @NiranthS's comments. For larger images the difference will be even larger but even for MNIST you should be seeing a fairly large difference already. Your results 8/20 for CNN and 19/20 for Dense indicate that you have an bug in your code for the CNN model or training. I suggest debugging the CNN to see where the error is.
from introtodeeplearning.
Related Issues (20)
- IndexError: too many indices for array: array is 0-dimensional, but 2 were indexed HOT 2
- Lab1, Part1: Assertion fails HOT 15
- Lab 1, Example song question
- lab1 part 2: Batch definition to create training examples issue HOT 1
- [lab3 part1] bias_wrapped_dense_NN.call error HOT 4
- Lab 2, Part 1, Section 1.4: Missing `from_logits=True` argument? HOT 2
- Lab 3 Part 2 resampling gives error HOT 2
- Lab3, Part1: ValueError: too many values to unpack (expected 2) HOT 3
- xtra_labs, autonomous_driving: Cannot open in Google Colab
- Lab3 part1 ensemble_NN.compile
- problem of mdl.lab3.plot_accuracy_vs_risk
- Lab 1 Defining a network layer - Assertion error HOT 3
- Lab 3 (Section 1.3) - Too Many Values to Unpack Error HOT 2
- Lab1 module 'mitdeeplearning' has no attribute 'lab1' HOT 1
- Lab1 Part1 issue with func(), HOT 1
- Lab3 Part2 Section3.4 AttributeError Problem
- Images not loading in lab python notebooks HOT 1
- Lab 3 dependency issue: capsa HOT 3
- From one day to the next Lab1 Music model load weight misinterprets shape. Serialization error?
- [Lab 1 Part 2] - Missing softmax argument in Dense layer
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 introtodeeplearning.