Create format.yml (#1)

Co-authored-by: UltralyticsAssistant <[email protected]>
ultralytics · May 31, 2024 · 4052703 · 4052703
1 parent 43c064a
commit 4052703
Show file tree

Hide file tree

Showing 21 changed files with 193 additions and 193 deletions.
diff --git a/.github/workflows/format.yml b/.github/workflows/format.yml
@@ -0,0 +1,29 @@
+# Ultralytics 🚀 - AGPL-3.0 license
+# Ultralytics Actions https://github.com/ultralytics/actions
+# This workflow automatically formats code and documentation in PRs to official Ultralytics standards
+
+name: Ultralytics Actions
+
+on:
+  push:
+    branches: [main]
+  pull_request_target:
+    branches: [main]
+    types: [opened, closed, synchronize]
+
+jobs:
+  format:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Run Ultralytics Formatting
+        uses: ultralytics/actions@main
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }} # automatically generated, do not modify
+          python: true # format Python code and docstrings
+          markdown: true # format Markdown
+          prettier: true # format YAML
+          spelling: true # check spelling
+          links: false # check broken links
+          summary: true # print PR summary with GPT4 (requires 'openai_api_key' or 'openai_azure_api_key' and 'openai_azure_endpoint')
+          openai_azure_api_key: ${{ secrets.OPENAI_AZURE_API_KEY }}
+          openai_azure_endpoint: ${{ secrets.OPENAI_AZURE_ENDPOINT }}
diff --git a/README.md b/README.md
@@ -1,43 +1,47 @@
 # THOP: PyTorch-OpCounter
 
-## How to install 
-    
-`pip install thop` (now continously intergrated on [Github actions](https://github.com/features/actions))
+## How to install
+
+`pip install thop` (now continuously integrated on [Github actions](https://github.com/features/actions))
 
 OR
 
 `pip install --upgrade git+https://github.com/Lyken17/pytorch-OpCounter.git`
-
-## How to use 
-* Basic usage 
+
+## How to use
+
+- Basic usage
+
     ```python
     from torchvision.models import resnet50
     from thop import profile
     model = resnet50()
     input = torch.randn(1, 3, 224, 224)
     macs, params = profile(model, inputs=(input, ))
-    ```    
+    ```
+
+- Define the rule for 3rd party module.
 
-* Define the rule for 3rd party module.
     ```python
     class YourModule(nn.Module):
         # your definition
     def count_your_model(model, x, y):
         # your rule here
-    
+
     input = torch.randn(1, 3, 224, 224)
-    macs, params = profile(model, inputs=(input, ), 
+    macs, params = profile(model, inputs=(input, ),
                             custom_ops={YourModule: count_your_model})
     ```
-    
-* Improve the output readability
+
+- Improve the output readability
 
     Call `thop.clever_format` to give a better format of the output.
+
     ```python
     from thop import clever_format
     macs, params = clever_format([macs, params], "%.3f")
-    ```    
-    
+    ```
+
 ## Results of Recent Models
 
 The implementation are adapted from `torchvision`. Following results can be obtained using [benchmark/evaluate_famous_models.py](benchmark/evaluate_famous_models.py).
@@ -47,48 +51,48 @@ The implementation are adapted from `torchvision`. Following results can be obta
 <tr>
 <td>
 
-Model | Params(M) | MACs(G)
----|---|---
-alexnet | 61.10 | 0.77
-vgg11 | 132.86 | 7.74
-vgg11_bn | 132.87 | 7.77
-vgg13 | 133.05 | 11.44
-vgg13_bn | 133.05 | 11.49
-vgg16 | 138.36 | 15.61
-vgg16_bn | 138.37 | 15.66
-vgg19 | 143.67 | 19.77
-vgg19_bn | 143.68 | 19.83
-resnet18 | 11.69 | 1.82
-resnet34 | 21.80 | 3.68
-resnet50 | 25.56 | 4.14
-resnet101 | 44.55 | 7.87
-resnet152 | 60.19 | 11.61
-wide_resnet101_2 | 126.89 | 22.84
-wide_resnet50_2 | 68.88 | 11.46
+| Model            | Params(M) | MACs(G) |
+| ---------------- | --------- | ------- |
+| alexnet          | 61.10     | 0.77    |
+| vgg11            | 132.86    | 7.74    |
+| vgg11_bn         | 132.87    | 7.77    |
+| vgg13            | 133.05    | 11.44   |
+| vgg13_bn         | 133.05    | 11.49   |
+| vgg16            | 138.36    | 15.61   |
+| vgg16_bn         | 138.37    | 15.66   |
+| vgg19            | 143.67    | 19.77   |
+| vgg19_bn         | 143.68    | 19.83   |
+| resnet18         | 11.69     | 1.82    |
+| resnet34         | 21.80     | 3.68    |
+| resnet50         | 25.56     | 4.14    |
+| resnet101        | 44.55     | 7.87    |
+| resnet152        | 60.19     | 11.61   |
+| wide_resnet101_2 | 126.89    | 22.84   |
+| wide_resnet50_2  | 68.88     | 11.46   |
 
 </td>
 <td>
 
-Model | Params(M) | MACs(G)
----|---|---
-resnext50_32x4d | 25.03 | 4.29
-resnext101_32x8d | 88.79 | 16.54
-densenet121 | 7.98 | 2.90
-densenet161 | 28.68 | 7.85
-densenet169 | 14.15 | 3.44
-densenet201 | 20.01 | 4.39
-squeezenet1_0 | 1.25 | 0.82
-squeezenet1_1 | 1.24 | 0.35
-mnasnet0_5 | 2.22 | 0.14
-mnasnet0_75 | 3.17 | 0.24
-mnasnet1_0 | 4.38 | 0.34
-mnasnet1_3 | 6.28 | 0.53
-mobilenet_v2 | 3.50 | 0.33
-shufflenet_v2_x0_5 | 1.37 | 0.05
-shufflenet_v2_x1_0 | 2.28 | 0.15
-shufflenet_v2_x1_5 | 3.50 | 0.31
-shufflenet_v2_x2_0 | 7.39 | 0.60
-inception_v3 | 27.16 | 5.75
+| Model              | Params(M) | MACs(G) |
+| ------------------ | --------- | ------- |
+| resnext50_32x4d    | 25.03     | 4.29    |
+| resnext101_32x8d   | 88.79     | 16.54   |
+| densenet121        | 7.98      | 2.90    |
+| densenet161        | 28.68     | 7.85    |
+| densenet169        | 14.15     | 3.44    |
+| densenet201        | 20.01     | 4.39    |
+| squeezenet1_0      | 1.25      | 0.82    |
+| squeezenet1_1      | 1.24      | 0.35    |
+| mnasnet0_5         | 2.22      | 0.14    |
+| mnasnet0_75        | 3.17      | 0.24    |
+| mnasnet1_0         | 4.38      | 0.34    |
+| mnasnet1_3         | 6.28      | 0.53    |
+| mobilenet_v2       | 3.50      | 0.33    |
+| shufflenet_v2_x0_5 | 1.37      | 0.05    |
+| shufflenet_v2_x1_0 | 2.28      | 0.15    |
+| shufflenet_v2_x1_5 | 3.50      | 0.31    |
+| shufflenet_v2_x2_0 | 7.39      | 0.60    |
+| inception_v3       | 27.16     | 5.75    |
 
 </td>
 </tr>

diff --git a/TODO.md b/TODO.md
@@ -1,7 +1,7 @@
 TODOs.
 
-1. A more user-friendly warning for un-defined modules. [Done]
+1. A more user-friendly warning for un-defined modules. \[Done\]
 2. Supports for models in torchvision (e.g., residual add).
 3. Layer wise printing
 
-Integration with torchprofile?
+Integration with torchprofile?
diff --git a/benchmark/README.md b/benchmark/README.md
@@ -1,33 +1,30 @@
 # MACs, FLOPs, what is the difference?
 
-`FLOPs` is abbreviation of **floating operations** which includes mul / add / div ... etc. 
+`FLOPs` is abbreviation of **floating operations** which includes mul / add / div ... etc.
 
-`MACs` stands for  **multiply–accumulate operation** that performs `a <- a + (b x c)`.
+`MACs` stands for **multiply–accumulate operation** that performs `a <- a + (b x c)`.
 
 As shown in the text, one `MACs` has one `mul` and one `add`. That is why in many places `FLOPs` is nearly two times as `MACs`.
 
-However, the application in real world is far more complex. Let's consider a matrix multiplication example. 
-`A` is an matrix of dimension `mxn` and `B` is an vector of `nx1`. 
+However, the application in real world is far more complex. Let's consider a matrix multiplication example. `A` is an matrix of dimension `mxn` and `B` is an vector of `nx1`.
 
 ```python
 for i in range(m):
     for j in range(n):
         C[i][j] += A[i][j] * B[j] # one mul-add
-```     
+```
 
 It would be `mn` `MACs` and `2mn` `FLOPs`. But such implementation is slow and parallelization is necessary to run faster
 
-
-  ```python
+```python
 for i in range(m):
-    parallelfor j in range(n):
-        d[j] = A[i][j] * B[j] # one mul
-    C[i][j] = sum(d) # n adds
+  parallelfor j in range(n):
+      d[j] = A[i][j] * B[j] # one mul
+  C[i][j] = sum(d) # n adds
 ```
 
-Then the number of `MACs` is no longer `mn` . 
-
+Then the number of `MACs` is no longer `mn` .
 
-When comparing MACs /FLOPs, we want the number to be implementation-agnostic and as general as possible. Therefore in THOP, **we only consider the number of multiplications** and ignore all other operations. 
+When comparing MACs /FLOPs, we want the number to be implementation-agnostic and as general as possible. Therefore in THOP, **we only consider the number of multiplications** and ignore all other operations.
 
-PS: The FLOPs is approximated by multiplying two.
+PS: The FLOPs is approximated by multiplying two.
diff --git a/benchmark/evaluate_famous_models.py b/benchmark/evaluate_famous_models.py
@@ -1,5 +1,6 @@
 import torch
 from torchvision import models
+
 from thop.profile import profile
 
 model_names = sorted(
@@ -24,6 +25,4 @@
         dsize = (1, 3, 299, 299)
     inputs = torch.randn(dsize).to(device)
     total_ops, total_params = profile(model, (inputs,), verbose=False)
-    print(
-        "%s | %.2f | %.2f" % (name, total_params / (1000 ** 2), total_ops / (1000 ** 3))
-    )
+    print("%s | %.2f | %.2f" % (name, total_params / (1000**2), total_ops / (1000**3)))
diff --git a/benchmark/evaluate_rnn_models.py b/benchmark/evaluate_rnn_models.py
@@ -1,5 +1,6 @@
 import torch
 import torch.nn as nn
+
 from thop.profile import profile
 
 input_size = 160
@@ -18,15 +19,9 @@
     "BiRNN": nn.Sequential(nn.RNN(input_size, hidden_size, bidirectional=True)),
     "BiGRU": nn.Sequential(nn.GRU(input_size, hidden_size, bidirectional=True)),
     "BiLSTM": nn.Sequential(nn.LSTM(input_size, hidden_size, bidirectional=True)),
-    "stacked-BiRNN": nn.Sequential(
-        nn.RNN(input_size, hidden_size, bidirectional=True, num_layers=4)
-    ),
-    "stacked-BiGRU": nn.Sequential(
-        nn.GRU(input_size, hidden_size, bidirectional=True, num_layers=4)
-    ),
-    "stacked-BiLSTM": nn.Sequential(
-        nn.LSTM(input_size, hidden_size, bidirectional=True, num_layers=4)
-    ),
+    "stacked-BiRNN": nn.Sequential(nn.RNN(input_size, hidden_size, bidirectional=True, num_layers=4)),
+    "stacked-BiGRU": nn.Sequential(nn.GRU(input_size, hidden_size, bidirectional=True, num_layers=4)),
+    "stacked-BiLSTM": nn.Sequential(nn.LSTM(input_size, hidden_size, bidirectional=True, num_layers=4)),
 }
 
 print("{} | {} | {}".format("Model", "Params(M)", "FLOPs(G)"))
@@ -49,9 +44,7 @@
 
 # validate batch_first support
 inputs = torch.randn(100, 32, input_size)
-ops_time_first = profile(
-    nn.Sequential(nn.LSTM(input_size, hidden_size)), (inputs,), verbose=False
-)[0]
+ops_time_first = profile(nn.Sequential(nn.LSTM(input_size, hidden_size)), (inputs,), verbose=False)[0]
 ops_batch_first = profile(
     nn.Sequential(nn.LSTM(input_size, hidden_size, batch_first=True)),
     (inputs.transpose(0, 1),),

diff --git a/setup.py b/setup.py
@@ -1,9 +1,10 @@
 #!/usr/bin/env python
-import os, sys
-import shutil
 import datetime
+import os
+import shutil
+import sys
 
-from setuptools import setup, find_packages
+from setuptools import find_packages, setup
 from setuptools.command.install import install
 
 readme = open("README.md").read()

diff --git a/tests/test_conv2d.py b/tests/test_conv2d.py
@@ -1,13 +1,14 @@
-from jinja2 import StrictUndefined
 import pytest
 import torch
 import torch.nn as nn
+from jinja2 import StrictUndefined
+
 from thop import profile
 
 
 class TestUtils:
     def test_conv2d_no_bias(self):
-        n, in_c, ih, iw =  1, 3, 32, 32   # torch.randint(1, 10, (4,)).tolist()
+        n, in_c, ih, iw = 1, 3, 32, 32  # torch.randint(1, 10, (4,)).tolist()
         out_c, kh, kw = 12, 5, 5
         s, p, d, g = 1, 1, 1, 1
 
@@ -17,11 +18,11 @@ def test_conv2d_no_bias(self):
 
         _, _, oh, ow = out.shape
 
-        flops, params = profile(net, inputs=(data, ))
+        flops, params = profile(net, inputs=(data,))
         assert flops == 810000, f"{flops} v.s. {810000}"
 
     def test_conv2d(self):
-        n, in_c, ih, iw =  1, 3, 32, 32   # torch.randint(1, 10, (4,)).tolist()
+        n, in_c, ih, iw = 1, 3, 32, 32  # torch.randint(1, 10, (4,)).tolist()
         out_c, kh, kw = 12, 5, 5
         s, p, d, g = 1, 1, 1, 1
 
@@ -31,14 +32,14 @@ def test_conv2d(self):
 
         _, _, oh, ow = out.shape
 
-        flops, params = profile(net, inputs=(data, ))
+        flops, params = profile(net, inputs=(data,))
         assert flops == 810000, f"{flops} v.s. {810000}"
-    
+
     def test_conv2d_random(self):
         for i in range(10):
-            out_c, kh, kw = torch.randint(1, 20, (3,)).tolist() 
-            n, in_c, ih, iw =  torch.randint(1, 20, (4,)).tolist()   # torch.randint(1, 10, (4,)).tolist()
-            ih += kh 
+            out_c, kh, kw = torch.randint(1, 20, (3,)).tolist()
+            n, in_c, ih, iw = torch.randint(1, 20, (4,)).tolist()  # torch.randint(1, 10, (4,)).tolist()
+            ih += kh
             iw += kw
             s, p, d, g = 1, 1, 1, 1
 
@@ -48,6 +49,8 @@ def test_conv2d_random(self):
 
             _, _, oh, ow = out.shape
 
-            flops, params = profile(net, inputs=(data, ))
+            flops, params = profile(net, inputs=(data,))
             print(flops, params)
-            assert flops == n * out_c * oh * ow // g * in_c * kh * kw , f"{flops} v.s. {n * out_c * oh * ow // g * in_c * kh * kw}"
+            assert (
+                flops == n * out_c * oh * ow // g * in_c * kh * kw
+            ), f"{flops} v.s. {n * out_c * oh * ow // g * in_c * kh * kw}"
diff --git a/tests/test_matmul.py b/tests/test_matmul.py
@@ -1,29 +1,29 @@
 import pytest
 import torch
 import torch.nn as nn
+
 from thop import profile
 
 
 class TestUtils:
     def test_matmul_case2(self):
         n, in_c, out_c = 1, 100, 200
         net = nn.Linear(in_c, out_c)
-        flops, params = profile(net, inputs=(torch.randn(n, in_c), ))
+        flops, params = profile(net, inputs=(torch.randn(n, in_c),))
         print(flops, params)
         assert flops == n * in_c * out_c
 
     def test_matmul_case2(self):
         for i in range(10):
             n, in_c, out_c = torch.randint(1, 500, (3,)).tolist()
             net = nn.Linear(in_c, out_c)
-            flops, params = profile(net, inputs=(torch.randn(n, in_c), ))
+            flops, params = profile(net, inputs=(torch.randn(n, in_c),))
             print(flops, params)
             assert flops == n * in_c * out_c
-    
+
     def test_conv2d(self):
         n, in_c, out_c = torch.randint(1, 500, (3,)).tolist()
         net = nn.Linear(in_c, out_c)
-        flops, params = profile(net, inputs=(torch.randn(n, in_c), ))
+        flops, params = profile(net, inputs=(torch.randn(n, in_c),))
         print(flops, params)
         assert flops == n * in_c * out_c
-