Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update main.py #1

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Update main.py #1

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,7 +34,7 @@ def softmax(input):
# Hyper parameters
N, h_size, o_size = vocab_size, vocab_size, vocab_size # Hidden size is set to vocab_size, assuming that level of abstractness is approximately proportional to vocab_size (but can be set to any other value).
seq_length = 25 # Longer sequence lengths allow for lengthier latent dependencies to be trained.
learning_rate = 1e-1
learning_rate = 0.1

# Model parameter initialization
Wz = np.random.rand(h_size, N) * 0.1 - 0.05
Expand Down Expand Up @@ -69,7 +69,7 @@ def lossFun(inputs, targets, hprev):

# Calculate hidden units
h_hat[t] = tanh(np.dot(Wh, x[t]) + np.dot(Uh, np.multiply(r[t], h[t-1])) + bh)
h[t] = np.multiply(z[t], h[t-1]) + np.multiply((1 - z[t]), h_hat[t])
h[t] = np.multiply((1-z[t]), h[t-1]) + np.multiply((z[t]), h_hat[t])

# Regular output unit
y[t] = np.dot(Wy, h[t]) + by
Expand Down