Data type issue in "micrograd/micrograd /nn.py: class Neuron(Module)/__call__(self, x)"
- Dominant language
- Jupyter Notebook
- Stars
- 17.6k
- Forks
- 2.8k
- PR merge metrics
- No merged PRs in 30d
Description
source code in micrograd/micrograd /nn.py: class Neuron(Module)/__call__(self, x) is:
class Neuron(Module):
def __init__(self, nin, nonlin=True):
self.w = [Value(random.uniform(-1,1)) for _ in range(nin)]
self.b = Value(0)
self.nonlin = nonlin
def __call__(self, x):
act = sum((wi*xi for wi,xi in zip(self.w, x)), self.b)
return act.relu() if self.nonlin else act
when you ran it, it occurred:
Cell In[14], line 21, in Neuron.__call__(self, x)
19 def __call__(self, x):
20 act = sum(wi*xi for wi,xi in zip(self.w, x)), self.b
---> 21 return act.relu() if self.nonlin else act
AttributeError: 'tuple' object has no attribute 'relu'
so it should be changed as :
class Neuron(Module):
def __init__(self, nin, nonlin=True):
self.w = [Value(random.uniform(-1,1)) for _ in range(nin)]
self.b = Value(0)
self.nonlin = nonlin
def __call__(self, x):
act = sum(wi*xi for wi,xi in zip(self.w, x)) + self.b
return act.relu() if self.nonlin else act
Contributor guide
No contributing guide indexed for this repository
Research direction
Open micrograd/micrograd/nn.py and inspect Neuron.__call__(self, x), focusing on how act is computed before relu() is called. Correct the tuple-producing expression so the method returns a Value-compatible activation, then verify that the reported AttributeError no longer occurs when the neuron is run.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 1/5
- Estimated time
- Under an hour
- Activity status
- Stale
- Clarity
- Clearly specified
- Newbie friendliness
- 50/100