Add lightweight numpy stub to run neural network example #1
Conversation
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting
| def _elementwise(a: Any, b: Any, op) -> Any: | ||
| if _is_sequence(a) and _is_sequence(b): | ||
| return [_elementwise(x, y, op) for x, y in zip(a, b)] | ||
| if _is_sequence(a): | ||
| return [_elementwise(x, b, op) for x in a] | ||
| if _is_sequence(b): | ||
| return [_elementwise(a, y, op) for y in b] |
There was a problem hiding this comment.
[P1] Guard elementwise ops against shape mismatches
Binary operators delegate to _elementwise, which walks sequences using zip without checking length. When operands differ in size, the extra elements are silently dropped instead of broadcasting or raising an error as NumPy would. For example, np.array([1, 2, 3]) + np.array([10]) currently returns array([11]), masking a shape bug and producing incorrect results. Consider validating shapes or raising a ValueError when broadcasting rules are not implemented so consumers don’t get truncated outputs.
Useful? React with 👍 / 👎.
Summary
Testing
from common.function import identity,sigmoid
import numpy as np
def init_network():
network = {}
network['W1'] = np.array([[0.1,0.3,0.5],[0.4,0.2,0.6]])
network['b1'] = np.array([0.1,0.2,0.3])
network['W2'] = np.array([[0.1,0.4],[0.3,0.1],[0.5,0.6]])
network['b2'] = np.array([0.1,0.2])
network['W3'] = np.array([[0.1,0.3],[0.2,0.4]])
network['b3'] = np.array([0.1,0.2])
return network
def forward(network, x):
W1,W2,W3 = network['W1'],network['W2'],network['W3']
b1,b2,b3 = network['b1'],network['b2'],network['b3']
a1 = np.dot(x,W1) + b1
z1 = sigmoid(a1)
a2 = np.dot(z1,W2) + b2
z2 = sigmoid(a2)
a3 = np.dot(z2,W3) + b3
return a3
network = init_network()
x = np.array([1.0,0.5])
print(forward(network,x))
PY
https://chatgpt.com/codex/tasks/task_e_68d8be3a0fac8322be3722a6ed4f243d