aitk's People
aitk's Issues
Adding install for TrainFollow
Install must be added for TrainFollow notebook in order to run on Google Colab.
%pip install aitk --quiet
For more comments see Google Colab TrainFollow Notebook.
Issues with XOR notebook
Install must be added for XOR notebook in order to run on Google Colab.
%pip install aitk --quiet
Change line 2 to :
import aitk.networks
#aitk.networks.__version__
Additionally the block of code in line 16 has some issues which I was not able to fix:
for epoch, weights in net.get_weights_from_history():
net.set_weights(weights)
net.predict_pca(inputs, scale=.5, colors=["r", "b", "b", "r"], sizes=300)
input("Epoch %s" % epoch)
For more comments see Google Colab XOR Notebook.
world.watch() fails to render (sometimes)
In a notebook cell, I ran
world.watch()
When I ran this on my macbook, the cell outputted this text:
Image(value=b'\xff\xd8\xff\xe0\x00\x10JFIF\x00\x01\x01\x00\x00\x01\x00\x01\x00\x00\xff\xdb\x00C\x00\x08\x06\x0โฆ
When I run this in CoLab, the image of the world renders, and updates, correctly. However, when I press "Mirror output in tab" to show that cell in a side window (so that it keeps showing as I scroll through the notebook), the cell in that side window also outputs the above text.
I expected the image to render in all three contexts.
Problem in rendering network
I tried the following:
x = range(1, 3)
And got this error:
ERROR:
I expected to see blah blah blah. This is the text
Adding install for CollectReinforcementData
Install must be added for CollectReinforcementData notebook in order to run on Google Colab.
%pip install aitk --quiet
For more comments see Google Colab CollectReinforcementData Notebook.
New notebook to simulate a simple neuron
Adding installs for Structure_of_Convolutional_Neural_Networks notebook
Two installs must be added for Structure_of_Convolutional_Neural_Networks notebook in order to run on Google Colab.
%pip install aitk --quiet
AND
%pip install tf --quiet
For more comments see Google Colab Structure_of_Convolutional_Neural_Networks Notebook.
Adding install for Coverage
Install must be added for Coverage notebook in order to run on Google Colab.
%pip install aitk --quiet
For more comments see Google Colab Coverage Notebook.
Issues with Subsumption notebook
The install must be added:
%pip install aitk --quiet
In addition to the problem with the install, the LightEnclosed world is once again not able to load, so the rest of the notebook breaks. This occurs in line 9.
world = aitk.robots.load_world("LightEnclosed")
For more comments see: Google Colab Subsumption notebook.
Issues with Robot_Memory
There seems to be an import based error with this code on line 34:
network = create_network(robot)
This code not running breaks the entire rest of the notebook essentially.
Google Colab Robot_Memory
Adding install for ZigZagWall
Install must be added for ZigZagWall notebook in order to run on Google Colab.
%pip install aitk --quiet
For more comments see Google Colab ZigZagWall Notebook.
Code issues with AITKKeras notebook
Added:
%pip install aitk --quiet
Changed code block three from:
(x_train, y_train), (x_test, y_test) = await mnist.load_data_async()
To:
(x_train, y_train), (x_test, y_test) = mnist.load_data()
For additional comments see Google Colab AITKKeras
Adding install for CartWorld Notebook
Install must be added for CartWorld notebook in order to run on Google Colab.
%pip install aitk --quiet
For more comments see Google Colab CartWorld Notebook.
Create a data manipulation notebook!
In this notebook, we will provide an accessible example to biased datasets in neural networks. This smaller example will provide a conduit to explaining larger issues with bias in the training of neural networks.
Create a small example of how transformers and LLMs work
Possible datasets:
- Only using two words: 0 and 1
- Using TinyStories: https://arxiv.org/abs/2305.07759
a. Dataset: https://huggingface.co/datasets/roneneldan/TinyStories
Possible models:
- Not sure
Issue with world in SeekLight notebook
The world "LightEnclosed" is not recognized in line 4 of the SeekLight notebook.
world = aitk.robots.load_world("LightEnclosed")
Fore more comments see: Google Colab SeekLight notebook
Issues with ClassifyDigitsWithPCA notebook
Once again having an issues with the input dataset as in the ClassifyingDigits notebook.
In line 3:
Code:
inputs = get_digit_inputs()
Throws this error:
FileNotFoundError Traceback (most recent call last)
<ipython-input-3-73e7cc90aa80> in <cell line: 1>()
----> 1 inputs = get_digit_inputs()
2 inputs.shape
<ipython-input-2-cdd8a157308e> in get_digit_inputs()
1 def get_digit_inputs():
2 """Each digit is represented by a 6x6 grid of 1's and 0's separated by blank lines."""
----> 3 fp = open("digits.data", "r")
4 data = []
5 while True:
FileNotFoundError: [Errno 2] No such file or directory: 'digits.data'
This then breaks the code further down when trying to access the input dataset. Further, an install statement must be added before neural networks are used.
For more comments regarding this notebook see: Google Colab ClassifyDigitsWithPCA notebook
Adding install for CollectData
Install must be added for CollectData notebook in order to run on Google Colab.
%pip install aitk --quiet
For more comments see Google Colab CollectData Notebook.
Adding install for MazeSearch
Install must be added for MazeSearch notebook in order to run on Google Colab.
%pip install aitk --quiet
For more comments see Google Colab MazeSearch Notebook.
Problem with file in BalanceData notebook
Even after adding an install for aitk, the notebook's file 'follow_data.csv' does not appear to be accessible, making this code in line 2 unable to run.
df = pd.read_csv('follow_data.csv', sep=',')
For more comments, see Google Colab BalanceData.
Issues with ClassifyingDigits notebook
Having an error in line 3:
Code:
inputs = get_digit_inputs()
Error:
---------------------------------------------------------------------------
FileNotFoundError Traceback (most recent call last)
[<ipython-input-4-73e7cc90aa80>](https://localhost:8080/#) in <cell line: 1>()
----> 1 inputs = get_digit_inputs()
2 inputs.shape
[<ipython-input-1-cdd8a157308e>](https://localhost:8080/#) in get_digit_inputs()
1 def get_digit_inputs():
2 """Each digit is represented by a 6x6 grid of 1's and 0's separated by blank lines."""
----> 3 fp = open("digits.data", "r")
4 data = []
5 while True:
FileNotFoundError: [Errno 2] No such file or directory: 'digits.data'
After adding import statement, some of the code begins to work. However, since the inputs has not been given a dataset, the network is not able to be trained, and this breaks the rest of the notebook.
For more comments on this notebook see: Google Colab ClassifyingDigits.
Adding install for CompassAndBeacon
Install must be added for CompassAndBeacon notebook in order to run on Google Colab.
%pip install aitk --quiet
For more comments see [Google Colab CompassAndBeacon Notebook](https://colab.research.google.com/drive/1rVHpN1V6zU6XSCOEZMu6NTDwR31_wqOw?usp=drive_link.
Adding install for StringGA
Install must be added for StringGA notebook in order to run on Google Colab.
%pip install aitk --quiet
For more comments see Google Colab StringGA Notebook.
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ 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. ๐๐๐
-
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 โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.