finish migrograd main functions.

Dockerfile

@@ -0,0 +1,28 @@
+# Base Image
+FROM nvidia/cuda:11.3.1-cudnn8-runtime-ubuntu20.04
+
+# System Dependencies and Cleanup
+RUN apt-get update -y && \
+    DEBIAN_FRONTEND=noninteractive TZ=Etc/UTC apt-get install -y tzdata && \
+    apt-get install -y software-properties-common ffmpeg libsm6 libxext6 libhdf5-serial-dev netcdf-bin libnetcdf-dev && \
+    add-apt-repository ppa:ubuntugis/ubuntugis-unstable && \
+    apt-get update && \
+    apt-get install -y curl build-essential gdal-bin libgdal-dev libpq-dev python3-gdal python3-pip apt-transport-https ca-certificates gnupg && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
+# Copy only the necessary files
+COPY requirements.txt /micrograd/requirements.txt
+
+# Install Python Packages
+RUN pip install --no-cache-dir -r /micrograd/requirements.txt
+
+# Set Working Directory and Prepare App
+WORKDIR /micrograd
+COPY micrograd /micrograd/micrograd
+COPY test /micrograd/test
+COPY app.py /micrograd/app.py
+
+RUN mkdir -p /root/.cache/torch/hub/checkpoints/
+
+CMD ["python3", "app.py"]

Makefile

@@ -0,0 +1,16 @@
+NAME=micrograd
+DOCKER=podman
+PORT=8008
+
+.PHONY=build run stop
+
+all: stop rm build run
+
+stop:
+	${DOCKER} stop ${NAME}
+rm:
+	${DOCKER} rm ${NAME}
+run:
+	${DOCKER} run -p ${PORT}:${PORT} -d --name ${NAME} -t ${NAME}
+build:
+	${DOCKER} build . --tag ${NAME}

app.py

@@ -0,0 +1,30 @@
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+from micrograd.train import model  # Replace with your ML model library
+from typing import List
+
+# Create FastAPI app
+app = FastAPI()
+
+# Load your ML model (replace this with your model loading logic)
+# model = engine.load_model("path/to/your/model")
+
+# Define a request model
+class Item(BaseModel):
+    data: List[float]  # Change 'list' to match the input format of your model
+
+# Endpoint for ML inference
+@app.post("/predict")
+async def predict(item: Item):
+    try:
+        # Perform prediction (modify this part according to your model's API)
+        nn = model()
+        prediction = nn(item.data)
+        return {"prediction": prediction.data}
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+# Run the API with Uvicorn
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=8008)

default.nix

@@ -0,0 +1,18 @@
+{ pkgs ? import <nixpkgs> {} }:
+
+pkgs.mkShell {
+  buildInputs = [
+    pkgs.python310
+    pkgs.python310Packages.numpy
+    pkgs.python310Packages.pytest
+    pkgs.python310Packages.uvicorn
+    pkgs.python310Packages.fastapi
+  ];
+
+  # Set PYTHONPATH to include your Python dependencies.
+  # This is useful if you are using Python modules that are not installed in the
+  # standard location.
+  # shellHook = ''
+  #   export PYTHONPATH=${pkgs.python3.sitePackages}:$PYTHONPATH
+  # '';
+}

micrograd/engine.py

@@ -1,4 +1,7 @@
 class Value:
+    """
+    add a comment
+    """
 
     def __init__(self, data, _children=(), _op='', label=''):
         self.data = data
@@ -30,6 +33,7 @@ class Value:
         return f"Value(data={self.data})"
 
     def __add__(self, other):
+        other = other if isinstance(other, Value) else Value(other)
         out = Value(data=self.data + other.data,
                     _children=(self, other), _op='+')
 
@@ -38,13 +42,37 @@ class Value:
             other.grad += 1.0 * out.grad
         out._backward = _backward
         return out
+    def __radd__(self, other):
+        return self + other
 
-    def __sub__(self, other):
-        out = Value(data=self.data - other.data,
-                    _children=(self, other), _op='-')
+    def __pow__(self, other):
+        assert isinstance(other, (int, float)), "int or float for now"
+        other = Value(other)
+        n = other.data
+        out = Value(data=self.data ** n,
+                    _children=(self, other), _op=f'**{n}')
+
+        def _backward():
+            self.grad += n * (self.data ** (n-1)) * out.grad
+        out._backward = _backward
         return out
 
+    def exp(self):
+        from math import exp
+        x = self.data
+        out = Value(data=exp(x),
+                    _children=(self,), _op='exp')
+
+        def _backward():
+            self.grad += out.data * out.grad
+        out._backward = _backward
+        return out
+
+    def __sub__(self, other):
+        return self + (-1 * other)
+
     def __mul__(self, other):
+        other = other if isinstance(other, Value) else Value(other)
         out = Value(data=self.data * other.data,
                     _children=(self, other), _op='*')
 
@@ -54,6 +82,12 @@ class Value:
         out._backward = _backward
         return out
 
+    def __rmul__(self, other):
+        return self * other
+
+    def __truediv__(self, other):
+        return self * other ** -1
+
     def tanh(self):
         from math import exp
         t = (exp(2 * self.data) - 1) / (exp(2 * self.data) + 1)

micrograd/nn.py

@@ -0,0 +1,55 @@
+import random
+from .engine import Value
+from typing import List, Union
+
+class Neuron:
+    def __init__(self, n_in: int):
+        self.w = [Value(random.uniform(-1, 1)) for _ in range(n_in)]
+        self.b = Value(random.uniform(-1, 1))
+
+    def __call__(self, x) -> Value:
+        # w * x + b
+        from functools import reduce
+        from operator import add
+        
+        if len(x) != len(self.w):
+            raise ValueError(f"mismatch dimension: x: {len(x)}, w: {len(self.w)}")
+        act = reduce(add, [w_i * x_i for w_i, x_i in zip(self.w, x)]) + self.b
+        return act.tanh()
+    def parameters(self):
+        return self.w + [self.b]
+
+class Layer:
+    def __init__(self, n_in: int, n_out: int):
+        self.neurons = [Neuron(n_in) for _ in range(n_out)]
+
+    def __call__(self, x) -> Union[List[Value], Value]:
+        out = [n(x) for n in self.neurons]
+        return out[0] if len(out) == 1 else out
+
+    def parameters(self):
+        out = []
+        for neuron in self.neurons:
+            for p in neuron.parameters():
+                out.append(p)
+        return out
+
+
+class MLP:
+    def __init__(self, n_in: int, n_outs: List[int]):
+        sizes = [n_in] + n_outs
+        self.layers = []
+        for i in range(len(n_outs)):
+            self.layers.append(Layer(sizes[i], sizes[i+1]))
+
+    def __call__(self, x):
+        for layer in self.layers:
+            x = layer(x)
+        return x
+
+    def parameters(self):
+        out = []
+        for layer in self.layers:
+            for l in layer.parameters():
+                out.append(l)
+        return out

micrograd/train.py

@@ -0,0 +1,36 @@
+from micrograd.nn import MLP
+
+def model():
+    n = MLP(3, [4, 4, 1])
+    xs = [
+        [2.0,  3.0, -1.0],
+        [3.0, -1.0,  0.5],
+        [0.5,  1.0,  1.0],
+        [1.0,  1.0,  1.0],
+    ]
+    y_true = [1.0, -1.0, -1.0, 1.0]
+    epochs = 20
+    lr = 0.08
+    for epoch in range(epochs):
+
+
+        # forward
+        y_pred = [n(x) for x in xs]
+        loss = sum([(y_p - y_t)**2 for y_p, y_t in zip(y_pred, y_true)])
+
+        # backward
+        for p in n.parameters():
+            p.grad = 0.0
+        loss.backward()
+
+        # update
+        for p in n.parameters():
+            p.data += -lr * p.grad
+
+        print(f"{epoch=:02d} | loss: {loss.data:4f}")
+    print(f"{[y.data for y in y_pred]}")
+    print(f"{[y for y in y_true]}")
+    return n
+
+if __name__ == "__main__":
+    model()

requirements.txt

@@ -1,3 +1,5 @@
 pytest
 notebook
 graphviz
+fastapi
+uvicorn

test/test_backprop.py

@@ -2,16 +2,6 @@ import pytest
 from micrograd.engine import Value
 
 
-def test_backward_tanh():
-    # inputs
-    x = Value(0.8814)
-    y = x.tanh()
-    y.grad = 1.0
-    y._backward()
-
-    assert pytest.approx(x.grad, 0.1) == 0.5
-
-
 def test_large_backprop():
     # inputs
     x1 = Value(2.0, label='x1')
@@ -107,3 +97,80 @@ def test_accumulation():
     b = a + a
     b.backward()
     assert a.grad == 2.0
+
+
+def test_backward_tanh():
+    # inputs
+    x = Value(0.8814)
+    y = x.tanh()
+    y.backward()
+
+    assert pytest.approx(x.grad, 0.1) == 0.5
+
+
+def test_backward_exp():
+    # inputs
+    x = Value(1.0)
+    y = x.exp()
+    y.backward()
+
+    assert pytest.approx(x.grad, 0.1) == 2.7
+
+
+def test_backward_pow():
+    # inputs
+    x = Value(1.0)
+    y = x ** 2
+    y.backward()
+
+    assert x.grad == 2.0
+
+
+def test_backward_div():
+    a = Value(4.0)
+    b = Value(2.0)
+    c = a / b
+    c.backward()
+    assert a.grad == 0.5
+
+
+def test_auto_diff_replace_tan_with_exp():
+    # inputs
+    x1 = Value(2.0, label='x1')
+    x2 = Value(0.0, label='x2')
+
+    # weights
+    w1 = Value(-3.0, label='w1')
+    w2 = Value(1.0, label='w2')
+
+    # bias
+    b = Value(6.8813735870195432, label='b')
+
+    h1 = x1 * w1
+    h1.label = 'h1'
+    h2 = x2 * w2
+    h2.label = 'h2'
+
+    h = h1 + h2
+    h.label = 'h'
+
+    n = h + b
+    n.label = 'n'
+    e = (2*n).exp()
+    y = (e - 1) / (e + 1)
+    y.label = 'y'
+
+    y.backward()
+    assert pytest.approx(n.grad, 0.001) == 0.5
+
+    assert pytest.approx(b.grad, 0.001) == 0.5
+    assert pytest.approx(h.grad, 0.001) == 0.5
+
+    assert pytest.approx(h1.grad, 0.001) == 0.5
+    assert pytest.approx(h2.grad, 0.001) == 0.5
+
+    assert pytest.approx(x1.grad, 0.001) == -1.5
+    assert pytest.approx(w1.grad, 0.001) == 1.0
+
+    assert pytest.approx(x2.grad, 0.001) == 0.5
+    assert pytest.approx(w2.grad, 0.001) == 0.0

test/test_nn.py

@@ -0,0 +1,66 @@
+from micrograd.nn import Neuron, Layer, MLP
+from micrograd.engine import Value
+import pytest
+
+def test_init_neuron():
+    inputs = 2
+    x = [1.0, 0.0]
+    n = Neuron(inputs)
+    assert len(n.w) == inputs
+    y = n(x)
+    assert isinstance(y, Value)
+
+def test_mismatch_number():
+    with pytest.raises(ValueError):
+        x = [1.0, 0.0]
+        n = Neuron(7)
+        n(x)
+
+def test_large_n_in():
+    n_in = 100
+    x = [1.0] * n_in
+    n = Neuron(n_in)
+    y = n(x)
+    assert isinstance(y, Value)
+
+def test_well_known_weights():
+    x = [1.0, 0.0]
+    w = [Value(0.0), Value(0.0)]
+    b = Value(0.0)
+
+    n = Neuron(2)
+    n.w = w
+    n.b = b
+    y = n(x)
+
+    assert y.data == sum([x[0] * w[0], x[1] * w[1], b]).tanh().data
+
+
+
+def test_mlp():
+    x = [2.0, 3.0, -1.0]
+    n = MLP(3, [4, 4, 4])
+    y = n(x)
+    assert len(y) == 4
+
+def test_mlp_single_out():
+    x = [2.0, 3.0, -1.0]
+    n = MLP(3, [4, 4, 1])
+    y = n(x)
+    assert isinstance(y, Value)
+
+def test_sample_mlp():
+    n = MLP(3, [4, 4, 1])
+    xs = [
+        [2.0,  3.0, -1.0],
+        [3.0, -1.0,  0.5],
+        [0.5,  1.0,  1.0],
+        [1.0,  1.0,  1.0],
+    ]
+    y_true = [1.0, -1.0, -1.0, 1.0]
+    y_pred = [n(x) for x in xs]
+    mse = sum([(y_p - y_t)**2 for y_p, y_t in zip(y_pred, y_true)])
+
+def test_mlp_parameters():
+    n = MLP(3, [4, 4, 1])
+    assert len(n.parameters()) == 41

test/test_value.py

@@ -1,3 +1,4 @@
+import pytest
 from micrograd.engine import Value
 
 
@@ -11,21 +12,21 @@ def test_value_repr():
     assert "Value(data=2.0)" == repr(v)
 
 
-def test_value_add():
+def test_value_add_opt():
     v1 = Value(2.0)
     v2 = Value(4.0)
     assert (v1 + v2).data == 6.0
     assert "Value(data=6.0)" == repr(v1 + v2)
 
 
-def test_value_sub():
+def test_value_sub_opt():
     v1 = Value(2.0)
     v2 = Value(4.0)
     assert (v1 - v2).data == -2.0
     assert "Value(data=-2.0)" == repr(v1 - v2)
 
 
-def test_value_mul():
+def test_value_mul_opt():
     v1 = Value(2.0)
     v2 = Value(4.0)
     v3 = Value(-1.0)
@@ -33,6 +34,36 @@ def test_value_mul():
     assert (v1 * v3).data == -2.0
 
 
+def test_value_rmul_opt():
+    a = Value(2.0)
+    b = 2 * a
+    assert b.data == 4.0
+
+
+def test_value_pow_opt():
+    a = Value(2.0)
+    b = a ** 2
+    assert b.data == 4.0
+
+
+def test_value_exp_opt():
+    a = Value(1.0)
+    b = a.exp()
+    assert pytest.approx(b.data, 0.1) == 2.7
+
+
+def test_value_int_opt():
+    a = Value(2.0)
+    b = a - 1
+    assert b.data == 1.0
+
+
+def test_value_div_opt():
+    a = Value(2.0)
+    b = a / 2
+    assert b.data == 1.0
+
+
 def test_value_mul_add():
     v1 = Value(2.0)
     v2 = Value(4.0)