froog 0.5.1__py3-none-any.whl → 0.5.2__py3-none-any.whl

{froog-0.5.1.dist-info → froog-0.5.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: froog
-Version: 0.5.1
+Version: 0.5.2
 Summary: tensor library with opencl and metal support
 Author: Kevin Buhler
 License: MIT
@@ -16,23 +16,21 @@ Requires-Dist: matplotlib
 <div align="center" >
   <img src="https://raw.githubusercontent.com/kevbuh/froog/main/assets/froog.png" alt="froog the frog" height="200">
   <br/>
-  froog: fast real-time optimization of gradients 
-  <br/>
-  a beautifully compact tensor library
+  froog: a gpu accelerated tensor library
   <br/>
   <a href="https://github.com/kevbuh/froog">homepage</a> | <a href="https://github.com/kevbuh/froog/tree/main/DOCS.md">documentation</a> | <a href="https://pypi.org/project/froog/">pip</a>
   <br/>
   <br/>
 </div>
 
-```froog``` is an easy-to-read tensor library (<a href="https://www.pepy.tech/projects/froog">25k pip installs!</a>) with support for GPU acceleration. Inspired by pytorch, tinygrad, and micrograd.
+```froog``` is an easy-to-read tensor library (<a href="https://www.pepy.tech/projects/froog">27k pip installs!</a>) with support for GPU acceleration with [OpenCL](https://www.khronos.org/opencl/) and [Apple Metal](https://developer.apple.com/metal/). Inspired by [tinygrad](https://github.com/tinygrad/tinygrad), and [micrograd](https://github.com/karpathy/micrograd).
 
-# Installation
+## Installation
 ```bash
 pip install froog
 ```
 
-# Features
+## Features
 - <a href="https://github.com/kevbuh/froog/blob/main/froog/tensor.py">Custom Tensors</a> 
   - Backpropagation
   - Automatic Differentiation (autograd)
@@ -43,11 +41,9 @@ pip install froog
   - Acceleration methods (Adam)
   - Avg & Max pooling
 - <a href="https://github.com/kevbuh/froog/blob/main/models/efficientnet.py">EfficientNet</a> inference
-- <a href="https://github.com/kevbuh/froog/blob/main/froog/gpu/ops_gpu.py">GPU Support</a> 
-- <a href="https://github.com/kevbuh/froog/blob/main/docs/env.md">Configuration via Environment Variables</a>
-- and a bunch <a href="https://github.com/kevbuh/froog/tree/main/froog">more</a> 
+- <a href="https://github.com/kevbuh/froog/blob/main/froog/gpu">GPU Support</a> 
 
-# Example
+## Quick Example
 
 Here's how you set up a simple multilayer perceptron for classification on MNIST. Looks pretty similar to pytorch, right?
 
@@ -69,7 +65,7 @@ model = mnistMLP() # create model
 optim = optim.SGD([model.l1, model.l2], lr=0.001) # stochastic gradient descent optimizer
 ```
 
-# GPU Support
+## GPU Support
 
 Device management is handled transparently and will automatically select one of ```[METAL, OPENCL, CPU]```. To use the GPU:
 
@@ -105,11 +101,12 @@ from froog import set_device
 set_device("METAL")  # or "OPENCL"
 ```
 
-# EfficientNet in froog!
+## EfficientNet in froog!
+
+<img src="https://github.com/kevbuh/froog/blob/main/assets/efficientnet_pug.png" alt="pug" height="200">
 
-<img src="https://github.com/kevbuh/froog/blob/main/assets/efficientnet_pug.png" alt="pug" height="300">
+We have an implementation of [EfficientNet v2](https://arxiv.org/abs/2104.00298) built entirely in ```froog``` using the official PyTorch weights! Running inference on this pug...
 
-We have an implementation of [EfficientNet v2](https://arxiv.org/abs/2104.00298) built entirely in ```froog``` using the official PyTorch weights! Run inference with:
 
 ```bash
 python3 models/efficientnet.py <https://optional_image_url>
@@ -119,25 +116,25 @@ inference 4.34 s
 
 imagenet class: 254
 prediction    : pug, pug-dog
-probability   : 0.8902361
+probability   : 0.9402361
 ******************************
 ```
 
 I would recommend checking out the <a href="https://github.com/kevbuh/froog/blob/main/models/efficientnet.py">code</a>, it's highly documented and pretty cool.
 
-# Contributing
+<!-- ## Contributing -->
 <!-- THERES LOT OF STUFF TO WORK ON! VISIT THE <a href="https://github.com/kevbuh/froog/blob/main/docs/bounties.md">BOUNTY SHOP</a>  -->
 
-Pull requests will be merged if they:
+<!-- Pull requests will be merged if they:
 * increase simplicity
 * increase functionality
 * increase efficiency
 
-More info on <a href="https://github.com/kevbuh/froog/blob/main/docs/contributing.md">contributing</a>. Make sure to run ```python -m pytest``` before creating a PR.
+More info on <a href="https://github.com/kevbuh/froog/blob/main/docs/contributing.md">contributing</a>. Make sure to run ```python -m pytest``` before creating a PR. -->
 
-# API
+## API
 
-## Basic Math Operations
+MATH
 - ```.add(y)``` - Addition with y
 - ```.sub(y)``` - Subtraction with y
 - ```.mul(y)``` - Multiplication with y
@@ -146,12 +143,10 @@ More info on <a href="https://github.com/kevbuh/froog/blob/main/docs/contributin
 - ```.sum()``` - Sum all elements
 - ```.mean()``` - Mean of all elements
 - ```.sqrt()``` - Square root
-
-## Linear Algebra Operations
 - ```.dot(y)``` - Matrix multiplication with y
 - ```.matmul(y)``` - Alias for dot
 
-## Neural Network Operations
+MACHINE LEARNING
 - ```.relu()``` - Rectified Linear Unit activation
 - ```.sigmoid()``` - Sigmoid activation
 - ```.dropout(p=0.5, training=True)``` - Dropout regularization
@@ -159,22 +154,17 @@ More info on <a href="https://github.com/kevbuh/froog/blob/main/docs/contributin
 - ```.swish()``` - Swish activation function (x * sigmoid(x))
 - ```.conv2d(w, stride=1, groups=1)``` - 2D convolution
 - ```.im2col2dconv(w)``` - Image to column for convolution
-
-## Pooling Operations
 - ```.max_pool2d(kernel_size=(2,2))``` - 2D max pooling
 - ```.avg_pool2d(kernel_size=(2,2))``` - 2D average pooling
 
-## Tensor Manipulation
-- ```.reshape(*shape)``` - Change tensor shape
-- ```.view(*shape)``` - Alternative to reshape
-- ```.pad2d(padding=None)``` - Pad 2D tensors
-- ```.flatten()``` - Returns a flattened 1D copy of the tensor
-- ```.unsqueeze(dim)``` - Add dimension of size 1 at specified position
-- ```.squeeze(dim=None)``` - Remove dimensions of size 1
-- ```.detach()``` - Returns a tensor detached from computation graph
-- ```.assign(x)``` - Assign values from tensor x to this tensor
+TENSOR
+- ```Tensor.zeros(*shape)``` - Create tensor of zeros
+- ```Tensor.ones(*shape)``` - Create tensor of ones
+- ```Tensor.randn(*shape)``` - Create tensor with random normal values
+- ```Tensor.eye(dim)``` - Create identity matrix
+- ```Tensor.arange(start, stop=None, step=1)``` - Create tensor with evenly spaced values
 
-## Tensor Properties
+TENSOR PROPERTIES
 - ```.shape``` - The shape of the tensor as a tuple
 - ```.size``` - Total number of elements in the tensor
 - ```.ndim``` - Number of dimensions (rank) of the tensor
@@ -183,23 +173,22 @@ More info on <a href="https://github.com/kevbuh/froog/blob/main/docs/contributin
 - ```.is_gpu``` - Whether tensor is on GPU
 - ```.grad``` - Gradient of tensor with respect to some scalar value
 - ```.data``` - Underlying NumPy array (or GPU buffer)
+- ```.to_float()``` - Converts tensor to float32 data type
+- ```.to_int()``` - Converts tensor to int32 data type
+- ```.to_bool()``` - Converts tensor to boolean data type
+- ```.reshape(*shape)``` - Change tensor shape
+- ```.view(*shape)``` - Alternative to reshape
+- ```.pad2d(padding=None)``` - Pad 2D tensors
+- ```.flatten()``` - Returns a flattened 1D copy of the tensor
+- ```.unsqueeze(dim)``` - Add dimension of size 1 at specified position
+- ```.squeeze(dim=None)``` - Remove dimensions of size 1
+- ```.detach()``` - Returns a tensor detached from computation graph
+- ```.assign(x)``` - Assign values from tensor x to this tensor
 
-## Device Management
+GPU
 - ```.to_cpu()``` - Moves tensor to CPU
 - ```.to_gpu()``` - Moves tensor to GPU 
 - ```.gpu_()``` - In-place GPU conversion (modifies tensor)
 
-## Data Type Conversion
-- ```.to_float()``` - Converts tensor to float32 data type
-- ```.to_int()``` - Converts tensor to int32 data type
-- ```.to_bool()``` - Converts tensor to boolean data type
-
-## Autograd Operations
+AUTOGRAD
 - ```.backward(allow_fill=True)``` - Performs backpropagation
-
-## Tensor Creation Methods
-- ```Tensor.zeros(*shape)``` - Create tensor of zeros
-- ```Tensor.ones(*shape)``` - Create tensor of ones
-- ```Tensor.randn(*shape)``` - Create tensor with random normal values
-- ```Tensor.eye(dim)``` - Create identity matrix
-- ```Tensor.arange(start, stop=None, step=1)``` - Create tensor with evenly spaced values

{froog-0.5.1.dist-info → froog-0.5.2.dist-info}/RECORD

@@ -4,7 +4,7 @@ froog/ops.py,sha256=6CJWxZi9ksSVC_AWrXRBz_ndXC_b7lC206AbeaNYsdc,26241
 froog/optim.py,sha256=rkibUce0rG5O1O4fLsNuS54fd3fzdjQarAyTqK61-1I,5443
 froog/tensor.py,sha256=jD8rspVMFI__sFMAeKEu_hVhhnfvtgc92oAkNJVKEJg,9688
 froog/utils.py,sha256=SUXMWOka-yJmib1jeC6KgHI_hOtSzgrakiRA0tCk4vc,3657
-froog-0.5.1.dist-info/METADATA,sha256=z4iR-31at5r1ZJc0kLlQu7rCLlTWbKGIbwBSxY9xTiY,7377
-froog-0.5.1.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
-froog-0.5.1.dist-info/top_level.txt,sha256=XPz35C_JWu20LlsVxIMdMZn8DD58Ak78LwgWFBGYZwY,6
-froog-0.5.1.dist-info/RECORD,,
+froog-0.5.2.dist-info/METADATA,sha256=51IOhneQ4a8NUmrF-LREE945WNHE3_4UAp-mpt1_l6w,7148
+froog-0.5.2.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
+froog-0.5.2.dist-info/top_level.txt,sha256=XPz35C_JWu20LlsVxIMdMZn8DD58Ak78LwgWFBGYZwY,6
+froog-0.5.2.dist-info/RECORD,,