froog 0.3.0__py3-none-any.whl → 0.3.2__py3-none-any.whl

froog/nn.py

@@ -10,8 +10,8 @@ from froog.tensor import Tensor
 import numpy as np
 
 def Linear(*x):
-  # TODO: why dividing by sqrt?
-  ret = np.random.uniform(-1., 1., size=x)/np.sqrt(np.prod(x)) # random init weights
+  # random Glorot initialization
+  ret = np.random.uniform(-1., 1., size=x)/np.sqrt(np.prod(x))
   return ret.astype(np.float32)
 
 def swish(x):
@@ -55,6 +55,6 @@ class BatchNorm2D:
   def __call__(self, x):
     x = x.sub(self.running_mean.reshape(shape=[1, -1, 1, 1]))
     x = x.mul(self.weight.reshape(shape=[1, -1, 1, 1]))
-    x = x.div(self.running_var.add(Tensor([self.eps], gpu=x.gpu)).reshape(shape=[1, -1, 1, 1]).sqrt()) # TODO: shouldn't div go first?
+    x = x.div(self.running_var.add(Tensor([self.eps], gpu=x.gpu)).reshape(shape=[1, -1, 1, 1]).sqrt())
     x = x.add(self.bias.reshape(shape=[1, -1, 1, 1]))
     return x

froog/ops.py

@@ -340,7 +340,6 @@ class MaxPool2D(Function):
                             *ctx.kernel_size)
 register('max_pool2d', MaxPool2D)
 
-
 class AvgPool2D(Function):
   @staticmethod
   def forward(ctx, x, kernel_size=(2,2)):
@@ -351,7 +350,7 @@ class AvgPool2D(Function):
   @staticmethod
   def backward(ctx, grad_output):
     s, = ctx.saved_tensors
-    py, px = ctx.kernel_size                                  # TODO: where does kernel_size come from?
+    py, px = ctx.kernel_size                                  # kernel_size passed from forward context
     my, mx = (s[2]//py)*py, (s[3]//px)*px
     ret = np.zeros(s, dtype=grad_output.dtype)
     for Y in range(py):

froog/ops_gpu.py

@@ -5,6 +5,8 @@
 # |    ___||    __  ||  |_|  ||  |_|  ||   ||  |
 # |   |    |   |  | ||       ||       ||   |_| |
 # |___|    |___|  |_||_______||_______||_______|
+#
+# OpenCL kernels
 
 import numpy as np
 from .tensor import Function, register
@@ -71,7 +73,6 @@ def unary_op(ctx, code, x):
   prg.unop(ctx.cl_queue, [np.prod(ret.shape)], None, x, ret)
   return ret
 
-# ???
 @functools.lru_cache
 def cl_pooling_krnl_build(cl_ctx, iter_op, result_op, init_val=0):
   prg = """

froog/tensor.py

@@ -62,7 +62,7 @@ class Tensor:
       self.gpu = False
 
     self.data = data
-    self.grad = None # TODO: why self.grad.data instead of self.grad?
+    self.grad = None
 
     if gpu:
       self.gpu_()

froog/utils.py

@@ -67,7 +67,8 @@ def im2col(x, H, W):
   tx = x.reshape(bs, -1)[:, idx]
 
   # all the time is spent here
-  tx = tx.ravel() # TODO: whats the purpose of ravel ???
+  # np.ravel() flattens the array into a 1-dimensional shape
+  tx = tx.ravel()
   return tx.reshape(-1, cin*W*H)
 
 def col2im(tx, H, W, OY, OX):

{froog-0.3.0.dist-info → froog-0.3.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: froog
-Version: 0.3.0
+Version: 0.3.2
 Summary: a beautifully simplistic tensor library
 Author: Kevin Buhler
 License: MIT
@@ -27,7 +27,7 @@ Requires-Dist: urllib
   <br/>
 </div>
 
-```froog``` is an easy-to-read tensor library (<a href="https://www.pepy.tech/projects/froog">11k pip installs!</a>) meant for those looking to get into machine learning and who want to understand how the underlying machine learning framework's code works before they are ultra-optimized (which all modern ml libraries are).
+```froog``` is an easy-to-read tensor library (<a href="https://www.pepy.tech/projects/froog">16k pip installs!</a>) meant for those looking to get into machine learning and who want to understand how the underlying machine learning framework's code works before they are ultra-optimized (which all modern ml libraries are).
 
 ```froog``` encapsulates everything from <a href="https://github.com/kevbuh/froog/blob/main/models/linear_regression.py">linear regression</a> to <a href="https://github.com/kevbuh/froog/blob/main/models/efficientnet.py">convolutional neural networks </a> in under 1000 lines.
 
@@ -108,13 +108,13 @@ Tensors are the fundamental datatype in froog, and one of the two main classes.
 - ```shape(self)```: this returns the tensor shape
 
 *Methods*
-- ``def zeros(*shape)```: this returns a tensor full of zeros with any shape that you pass in. Defaults to np.float32
+- ```def zeros(*shape)```: this returns a tensor full of zeros with any shape that you pass in. Defaults to np.float32
 
 - ```def ones(*shape)```: this returns a tensor full of ones with any shape that you pass in. Defaults to np.float32
 
 - ```def randn(*shape):```: this returns a randomly initialized Tensor of *shape
 
-*Froog gradient calculations*
+*Gradient calculations*
 
 - ```froog``` computes gradients automatically through a process called automatic differentiation. it has a variable ```_ctx```, which stores the chain of operations. it will take the current operation, lets say a dot product, and go to the dot product definition in ```froog/ops.py```, which contains a backward pass specfically for dot products. all methods, from add to 2x2 maxpools, have this backward pass implemented.
 
@@ -276,7 +276,7 @@ blocks_args = [
 
 ## Linear regression 
 
-Doing linear regression in froog is pretty easy, check out the entire <a href="https://github.com/kevbuh/froog/blob/main/models/linear_regression.py">code</a>.
+Doing linear regression in ```froog``` is pretty easy, check out the entire <a href="https://github.com/kevbuh/froog/blob/main/models/linear_regression.py">code</a>.
 
 ```bash
 VIZ=1 python3 linear_regression.py

froog-0.3.2.dist-info/RECORD

@@ -0,0 +1,13 @@
+froog/__init__.py,sha256=Mzxgj9bA2G4kcmbmY8fY0KCKgimPucn3hTVRWBJ-5_Q,57
+froog/gradcheck.py,sha256=HlA0VDKE-c44o0E73QsUTIVoNs-w_C9FyKFlHfoagIQ,2415
+froog/nn.py,sha256=_5dzIoxz1L4yEnYfONVc8xIs8vqRpUBBwZwHLvBu9yY,2023
+froog/ops.py,sha256=t0P0OzzlhYBgAhM3urLsXLl9LJNff_7Yiyc_pYgP5B4,14388
+froog/ops_gpu.py,sha256=CJ-kXvY3TS1lHOBOhR3IlMnZMLtrOEAeM78rTnk-lIc,15482
+froog/optim.py,sha256=m8Q1xe3WwU41obGSMVjRMIs3rWqfqRWfhlbhF9oJyWA,2450
+froog/tensor.py,sha256=Wix4pE5-OIY8Pvv3bqNCSU_-c_wZV2HrmAtBwMPmAfE,7636
+froog/utils.py,sha256=vs9bmBOyfy0_NR8jPl2DMWBCAqIacJ6a75Lbso2MAKs,3347
+froog-0.3.2.dist-info/LICENSE,sha256=k_856uNmcNUoLC_HkI18c1WomqvQ1Ioqk6gwYfWQiaM,31
+froog-0.3.2.dist-info/METADATA,sha256=mjq5LtJXs29JzF-_cLLDTaGnczJ15RucQityVAyNzCE,13898
+froog-0.3.2.dist-info/WHEEL,sha256=yQN5g4mg4AybRjkgi-9yy4iQEFibGQmlz78Pik5Or-A,92
+froog-0.3.2.dist-info/top_level.txt,sha256=XPz35C_JWu20LlsVxIMdMZn8DD58Ak78LwgWFBGYZwY,6
+froog-0.3.2.dist-info/RECORD,,

froog-0.3.0.dist-info/RECORD

@@ -1,13 +0,0 @@
-froog/__init__.py,sha256=Mzxgj9bA2G4kcmbmY8fY0KCKgimPucn3hTVRWBJ-5_Q,57
-froog/gradcheck.py,sha256=HlA0VDKE-c44o0E73QsUTIVoNs-w_C9FyKFlHfoagIQ,2415
-froog/nn.py,sha256=VeUpmjrv1XrH786GEOc9ruzDAHULiVHKpDtn187EQgI,2076
-froog/ops.py,sha256=PEXZb3lNeYwFpRfcEvEs-KLB4rQqHHUdraR1qOgw5Zs,14389
-froog/ops_gpu.py,sha256=bQ2bzMqmvY2xLEaTjOIXN3KOb-7yZEDjmliV8tWlC6g,15469
-froog/optim.py,sha256=m8Q1xe3WwU41obGSMVjRMIs3rWqfqRWfhlbhF9oJyWA,2450
-froog/tensor.py,sha256=Dacd2UQVfl7RsjADjrhBO1rMVcDVaeJuI55sFfxonhk,7685
-froog/utils.py,sha256=zWquIwvOUBfCzaoA7eAOov7C5NbGxus5RXx9JPM1jeg,3325
-froog-0.3.0.dist-info/LICENSE,sha256=k_856uNmcNUoLC_HkI18c1WomqvQ1Ioqk6gwYfWQiaM,31
-froog-0.3.0.dist-info/METADATA,sha256=GFxLv1Yex0CfNdZWjCvkBJxZNzo60wyVQa_fKutSey0,13897
-froog-0.3.0.dist-info/WHEEL,sha256=yQN5g4mg4AybRjkgi-9yy4iQEFibGQmlz78Pik5Or-A,92
-froog-0.3.0.dist-info/top_level.txt,sha256=XPz35C_JWu20LlsVxIMdMZn8DD58Ak78LwgWFBGYZwY,6
-froog-0.3.0.dist-info/RECORD,,