Code for Machine Learning with TensorFlow: 2nd Edition Published by Manning Publications
Home Page: http://github.com/chrismattmann/MLwithTensorFlow2ed
License: Apache License 2.0
![dependabot[bot] avatar](https://avatars.githubusercontent.com/in/29110?v=4 "dependabot[bot]")
In listing 3.5, I think the weights are not reinitialized before each run. If I add a line to print out model weights, we can see that the model weights are non-zero after the first time through the loop.
sess = tf.Session()
init = tf.global_variables_initializer()
sess.run(init)
for reg_lambda in np.linspace(0, 1, 100):
w_val = sess.run(w); print(w_val) # <----------- ADDED THIS -------------
for epoch in range(training_epochs):
sess.run(train_op, feed_dict={X:x_train, Y:y_train})
final_cost = sess.run(cost, feed_dict={X:x_test, Y:y_test})
print('reg lambda', reg_lambda)
print('final cost', final_cost)
sess.close()
This prints out:
[0. 0. 0. 0. 0. 0. 0. 0. 0.]
reg lambda 0.0
final cost 0.081058994
[ 2.5665667e-03 9.3173017e-05 1.7256942e-03 -1.4493844e-05
1.2718090e-03 -5.8588204e-05 1.0161836e-03 -7.8277393e-05
8.5132103e-04]
reg lambda 0.010101010101010102
final cost 0.0801239
[ 5.0976453e-03 1.8751422e-04 3.4367563e-03 -2.7644883e-05
2.5339315e-03 -1.1590221e-04 2.0250683e-03 -1.5540000e-04
1.6967654e-03]
reg lambda 0.020202020202020204
final cost 0.07920629
[ 7.5936671e-03 2.8300245e-04 5.1333504e-03 -3.9473085e-05
3.7864731e-03 -1.7195975e-04 3.0267318e-03 -2.3138340e-04
2.5363949e-03]
reg lambda 0.030303030303030304
final cost 0.0783058
[ 1.0055063e-02 3.7961689e-04 6.8156384e-03 -4.9998103e-05
5.0295377e-03 -2.2677830e-04 4.0212511e-03 -3.0624296e-04
3.3702708e-03]
...SNIP...
I think the correct behavior is to reinitialize the weights for each value of lambda. I also captured the cost for each lambda.
lambdas = []; costs = [] # <-------- ADD THIS --------
for reg_lambda in np.linspace(0, 1, 100):
sess.run(init) # <-------- ADD THIS --------
for epoch in range(training_epochs):
sess.run(train_op, feed_dict={X:x_train, Y:y_train})
final_cost = sess.run(cost, feed_dict={X:x_test, Y:y_test})
print('reg lambda', reg_lambda)
print('final cost', final_cost)
lambdas.append(reg_lambda); costs.append(final_cost) # <-------- ADD THIS --------
sess.close()
Now if plot lambdas vs cost, it's a horizontal line.
It seems that changing reg_lambda is having no effect, but that's not easy to see when the weights are reused.
The first line in the listing sums the error values, but since some errors are positive and some are negative, they have the effect of cancelling out and lowering the error measurement.
>>> avg_error = functools.reduce(lambda a,b: a+b, (trY2-Y_train))
10683.684611765864
I believe it should be:
>>> avg_error = functools.reduce(lambda a,b: a+b, np.abs(trY2-Y_train))
178465.4145040395
Or even more succinctly, reuse the error vector computed in an earlier step:
>>> avg_error = np.sum(error)
178465.41450403954
I am having a hard time trying to plot this:
Hello,
I have reached chapter 4 and tried to replicate its notebook, but it doesn't seem to work properly, as it's not learning the proper values. The loss output is 0 from the beginning, so there is probably an issue there in how it's calculated.
I am investigating this issue, so I will come back to you if I find a fix
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 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.
An Open Source Machine Learning Framework for Everyone
Django
The Web framework for perfectionists with deadlines.
Laravel
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
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.