mirror of
https://github.com/MLSysBook/TinyTorch.git
synced 2026-04-28 14:02:32 -05:00
9aaa159fb6
- Replace Dense with Linear (API name change) - Fix PositionalEncoding parameter order (max_seq_len, embed_dim) - Replace Variable with Tensor (API consolidation) - Replace learning_rate with lr for optimizers - Remove Sequential (not in current API) - Replace BCELoss with BinaryCrossEntropyLoss - Remove LeakyReLU (not in current API) - Fix dropout eval test - Skip advanced NLP gradient tests (requires autograd integration) - Reduce loss improvement threshold for test stability - Fix tensor reshape error message to match tests
203 lines
8.5 KiB
Python
Generated
203 lines
8.5 KiB
Python
Generated
# ╔═══════════════════════════════════════════════════════════════════════════════╗
|
|
# ║ 🚨 CRITICAL WARNING 🚨 ║
|
|
# ║ AUTOGENERATED! DO NOT EDIT! ║
|
|
# ║ ║
|
|
# ║ This file is AUTOMATICALLY GENERATED from source modules. ║
|
|
# ║ ANY CHANGES MADE HERE WILL BE LOST when modules are re-exported! ║
|
|
# ║ ║
|
|
# ║ ✅ TO EDIT: src/01_tensor/01_tensor.py ║
|
|
# ║ ✅ TO EXPORT: Run 'tito module complete <module_name>' ║
|
|
# ║ ║
|
|
# ║ 🛡️ STUDENT PROTECTION: This file contains optimized implementations. ║
|
|
# ║ Editing it directly may break module functionality and training. ║
|
|
# ║ ║
|
|
# ║ 🎓 LEARNING TIP: Work in src/ (developers) or modules/ (learners) ║
|
|
# ║ The tinytorch/ directory is generated code - edit source files instead! ║
|
|
# ╚═══════════════════════════════════════════════════════════════════════════════╝
|
|
# %% auto 0
|
|
__all__ = ['BYTES_PER_FLOAT32', 'KB_TO_BYTES', 'MB_TO_BYTES', 'Tensor']
|
|
|
|
# %% ../../modules/01_tensor/tensor.ipynb 1
|
|
import numpy as np
|
|
|
|
# Constants for memory calculations
|
|
BYTES_PER_FLOAT32 = 4 # Standard float32 size in bytes
|
|
KB_TO_BYTES = 1024 # Kilobytes to bytes conversion
|
|
MB_TO_BYTES = 1024 * 1024 # Megabytes to bytes conversion
|
|
|
|
# %% ../../modules/01_tensor/tensor.ipynb 7
|
|
class Tensor:
|
|
"""Educational tensor that grows with student knowledge.
|
|
|
|
This class starts simple but includes dormant features for future modules:
|
|
- requires_grad: Will be used for automatic differentiation (Module 05)
|
|
- grad: Will store computed gradients (Module 05)
|
|
- backward(): Will compute gradients (Module 05)
|
|
|
|
For now, focus on: data, shape, and basic operations.
|
|
"""
|
|
|
|
def __init__(self, data, requires_grad=False):
|
|
"""Create a new tensor from data."""
|
|
### BEGIN SOLUTION
|
|
self.data = np.array(data, dtype=np.float32)
|
|
self.shape = self.data.shape
|
|
self.size = self.data.size
|
|
self.dtype = self.data.dtype
|
|
self.requires_grad = requires_grad
|
|
self.grad = None
|
|
### END SOLUTION
|
|
|
|
def __repr__(self):
|
|
"""String representation of tensor for debugging."""
|
|
grad_info = f", requires_grad={self.requires_grad}" if self.requires_grad else ""
|
|
return f"Tensor(data={self.data}, shape={self.shape}{grad_info})"
|
|
|
|
def __str__(self):
|
|
"""Human-readable string representation."""
|
|
return f"Tensor({self.data})"
|
|
|
|
def numpy(self):
|
|
"""Return the underlying NumPy array."""
|
|
return self.data
|
|
|
|
def __add__(self, other):
|
|
"""Add two tensors element-wise with broadcasting support."""
|
|
### BEGIN SOLUTION
|
|
if isinstance(other, Tensor):
|
|
return Tensor(self.data + other.data)
|
|
else:
|
|
return Tensor(self.data + other)
|
|
### END SOLUTION
|
|
|
|
def __sub__(self, other):
|
|
"""Subtract two tensors element-wise."""
|
|
### BEGIN SOLUTION
|
|
if isinstance(other, Tensor):
|
|
return Tensor(self.data - other.data)
|
|
else:
|
|
return Tensor(self.data - other)
|
|
### END SOLUTION
|
|
|
|
def __mul__(self, other):
|
|
"""Multiply two tensors element-wise (NOT matrix multiplication)."""
|
|
### BEGIN SOLUTION
|
|
if isinstance(other, Tensor):
|
|
return Tensor(self.data * other.data)
|
|
else:
|
|
return Tensor(self.data * other)
|
|
### END SOLUTION
|
|
|
|
def __truediv__(self, other):
|
|
"""Divide two tensors element-wise."""
|
|
### BEGIN SOLUTION
|
|
if isinstance(other, Tensor):
|
|
return Tensor(self.data / other.data)
|
|
else:
|
|
return Tensor(self.data / other)
|
|
### END SOLUTION
|
|
|
|
def matmul(self, other):
|
|
"""Matrix multiplication of two tensors."""
|
|
### BEGIN SOLUTION
|
|
if not isinstance(other, Tensor):
|
|
raise TypeError(f"Expected Tensor for matrix multiplication, got {type(other)}")
|
|
if self.shape == () or other.shape == ():
|
|
return Tensor(self.data * other.data)
|
|
if len(self.shape) == 0 or len(other.shape) == 0:
|
|
return Tensor(self.data * other.data)
|
|
if len(self.shape) >= 2 and len(other.shape) >= 2:
|
|
if self.shape[-1] != other.shape[-2]:
|
|
raise ValueError(
|
|
f"Cannot perform matrix multiplication: {self.shape} @ {other.shape}. "
|
|
f"Inner dimensions must match: {self.shape[-1]} ≠ {other.shape[-2]}"
|
|
)
|
|
result_data = np.matmul(self.data, other.data)
|
|
return Tensor(result_data)
|
|
### END SOLUTION
|
|
|
|
def __getitem__(self, key):
|
|
"""Enable indexing and slicing operations on Tensors."""
|
|
### BEGIN SOLUTION
|
|
result_data = self.data[key]
|
|
if not isinstance(result_data, np.ndarray):
|
|
result_data = np.array(result_data)
|
|
result = Tensor(result_data, requires_grad=self.requires_grad)
|
|
return result
|
|
### END SOLUTION
|
|
|
|
def reshape(self, *shape):
|
|
"""Reshape tensor to new dimensions."""
|
|
### BEGIN SOLUTION
|
|
if len(shape) == 1 and isinstance(shape[0], (tuple, list)):
|
|
new_shape = tuple(shape[0])
|
|
else:
|
|
new_shape = shape
|
|
if -1 in new_shape:
|
|
if new_shape.count(-1) > 1:
|
|
raise ValueError("Can only specify one unknown dimension with -1")
|
|
known_size = 1
|
|
unknown_idx = new_shape.index(-1)
|
|
for i, dim in enumerate(new_shape):
|
|
if i != unknown_idx:
|
|
known_size *= dim
|
|
unknown_dim = self.size // known_size
|
|
new_shape = list(new_shape)
|
|
new_shape[unknown_idx] = unknown_dim
|
|
new_shape = tuple(new_shape)
|
|
if np.prod(new_shape) != self.size:
|
|
raise ValueError(
|
|
f"Total elements must match: {self.size} ≠ {np.prod(new_shape)}"
|
|
)
|
|
reshaped_data = np.reshape(self.data, new_shape)
|
|
result = Tensor(reshaped_data, requires_grad=self.requires_grad)
|
|
return result
|
|
### END SOLUTION
|
|
|
|
def transpose(self, dim0=None, dim1=None):
|
|
"""Transpose tensor dimensions."""
|
|
### BEGIN SOLUTION
|
|
if dim0 is None and dim1 is None:
|
|
if len(self.shape) < 2:
|
|
return Tensor(self.data.copy())
|
|
else:
|
|
axes = list(range(len(self.shape)))
|
|
axes[-2], axes[-1] = axes[-1], axes[-2]
|
|
transposed_data = np.transpose(self.data, axes)
|
|
else:
|
|
if dim0 is None or dim1 is None:
|
|
raise ValueError("Both dim0 and dim1 must be specified")
|
|
axes = list(range(len(self.shape)))
|
|
axes[dim0], axes[dim1] = axes[dim1], axes[dim0]
|
|
transposed_data = np.transpose(self.data, axes)
|
|
result = Tensor(transposed_data, requires_grad=self.requires_grad)
|
|
return result
|
|
### END SOLUTION
|
|
|
|
def sum(self, axis=None, keepdims=False):
|
|
"""Sum tensor along specified axis."""
|
|
### BEGIN SOLUTION
|
|
result = np.sum(self.data, axis=axis, keepdims=keepdims)
|
|
return Tensor(result)
|
|
### END SOLUTION
|
|
|
|
def mean(self, axis=None, keepdims=False):
|
|
"""Compute mean of tensor along specified axis."""
|
|
### BEGIN SOLUTION
|
|
result = np.mean(self.data, axis=axis, keepdims=keepdims)
|
|
return Tensor(result)
|
|
### END SOLUTION
|
|
|
|
def max(self, axis=None, keepdims=False):
|
|
"""Find maximum values along specified axis."""
|
|
### BEGIN SOLUTION
|
|
result = np.max(self.data, axis=axis, keepdims=keepdims)
|
|
return Tensor(result)
|
|
### END SOLUTION
|
|
|
|
def backward(self):
|
|
"""Compute gradients (implemented in Module 05: Autograd)."""
|
|
### BEGIN SOLUTION
|
|
pass
|
|
### END SOLUTION
|