# PyTorch Model Parameters Summary
#### Install using pip
```
pip install pytorchsummary
```
## Example 1
```python
from torch import nn
from pytorchsummary import summary
class CNNET(nn.Module):
def __init__(self):
super(CNNET,self).__init__()
self.layer = nn.Sequential(
nn.Conv2d(3,16,5), # 28-5+1
nn.ReLU(), #24
nn.MaxPool2d(2,2), # 12
nn.Conv2d(16,32,3), # 12+1-3
nn.ReLU(), # 10
nn.MaxPool2d(2,2), # 5
nn.Conv2d(32,64,5), # 11-3+1
nn.ReLU(),
nn.Conv2d(64,10,1)
)
def forward(self,x):
x = self.layer(x)
return x
m = CNNET()
summary((3,128,128),m)
```
### Output
``` Layer Output Shape Kernal Shape #params #(weights + bias) requires_grad
------------------------------------------------------------------------------------------------------------------------------------------------------
Conv2d-1 [1, 16, 124, 124] [16, 3, 5, 5] 1216 (1200 + 16) True True
ReLU-2 [1, 16, 124, 124]
MaxPool2d-3 [1, 16, 62, 62]
Conv2d-4 [1, 32, 60, 60] [32, 16, 3, 3] 4640 (4608 + 32) True True
ReLU-5 [1, 32, 60, 60]
MaxPool2d-6 [1, 32, 30, 30]
Conv2d-7 [1, 64, 26, 26] [64, 32, 5, 5] 51264 (51200 + 64) True True
ReLU-8 [1, 64, 26, 26]
Conv2d-9 [1, 10, 26, 26] [10, 64, 1, 1] 650 (640 + 10) True True
______________________________________________________________________________________________________________________________________________________
Total parameters 57,770
Total Non-Trainable parameters 0
Total Trainable parameters 57,770
(57770, 57770, 0)
```
```python
for i,j in enumerate(m.parameters()):
if i==2:
break
j.requires_grad=False
summary((3,128,128),m,border=True)
```
```
Layer Output Shape Kernal Shape #params #(weights + bias) requires_grad
------------------------------------------------------------------------------------------------------------------------------------------------------
Conv2d-1 [1, 16, 124, 124] [16, 3, 5, 5] 1216 (1200 + 16) False False
______________________________________________________________________________________________________________________________________________________
ReLU-2 [1, 16, 124, 124]
______________________________________________________________________________________________________________________________________________________
MaxPool2d-3 [1, 16, 62, 62]
______________________________________________________________________________________________________________________________________________________
Conv2d-4 [1, 32, 60, 60] [32, 16, 3, 3] 4640 (4608 + 32) True True
______________________________________________________________________________________________________________________________________________________
ReLU-5 [1, 32, 60, 60]
______________________________________________________________________________________________________________________________________________________
MaxPool2d-6 [1, 32, 30, 30]
______________________________________________________________________________________________________________________________________________________
Conv2d-7 [1, 64, 26, 26] [64, 32, 5, 5] 51264 (51200 + 64) True True
______________________________________________________________________________________________________________________________________________________
ReLU-8 [1, 64, 26, 26]
______________________________________________________________________________________________________________________________________________________
Conv2d-9 [1, 10, 26, 26] [10, 64, 1, 1] 650 (640 + 10) True True
______________________________________________________________________________________________________________________________________________________
______________________________________________________________________________________________________________________________________________________
Total parameters 57,770
Total Non-Trainable parameters 1,216
Total Trainable parameters 56,554
(56554, 57770, 1216)
```
## Example 2
```python
from torchvision import models
from pytorchsummary import summary
m = models.alexnet(False)
summary((3,224,224),m)
# this function returns the total number of
# parameters (int) in a model
```
### ouput
```
Layer Output Shape Kernal Shape #params #(weights + bias) requires_grad
------------------------------------------------------------------------------------------------------------------------------------------------------
Conv2d-1 [1, 64, 55, 55] [64, 3, 11, 11] 23296 (23232 + 64) True True
ReLU-2 [1, 64, 55, 55]
MaxPool2d-3 [1, 64, 27, 27]
Conv2d-4 [1, 192, 27, 27] [192, 64, 5, 5] 307392 (307200 + 192) True True
ReLU-5 [1, 192, 27, 27]
MaxPool2d-6 [1, 192, 13, 13]
Conv2d-7 [1, 384, 13, 13] [384, 192, 3, 3] 663936 (663552 + 384) True True
ReLU-8 [1, 384, 13, 13]
Conv2d-9 [1, 256, 13, 13] [256, 384, 3, 3] 884992 (884736 + 256) True True
ReLU-10 [1, 256, 13, 13]
Conv2d-11 [1, 256, 13, 13] [256, 256, 3, 3] 590080 (589824 + 256) True True
ReLU-12 [1, 256, 13, 13]
MaxPool2d-13 [1, 256, 6, 6]
AdaptiveAvgPool2d-14 [1, 256, 6, 6]
Dropout-15 [1, 9216]
Linear-16 [1, 4096] [4096, 9216] 37752832 (37748736 + 4096) True True
ReLU-17 [1, 4096]
Dropout-18 [1, 4096]
Linear-19 [1, 4096] [4096, 4096] 16781312 (16777216 + 4096) True True
ReLU-20 [1, 4096]
Linear-21 [1, 1000] [1000, 4096] 4097000 (4096000 + 1000) True True
______________________________________________________________________________________________________________________________________________________
Total parameters 61,100,840
Total Non-Trainable parameters 0
Total Trainable parameters 61,100,840
(61100840, 61100840, 0)
```
### Calculating the number of specific layer, or layer frequencies
```python
from pytorchsummary import get_num_layers
print(get_num_layers(m)) # alexnet model
```
Output:
```
{'Conv2d': 5,
'ReLU': 7,
'MaxPool2d': 3,
'AdaptiveAvgPool2d': 1,
'Dropout': 2,
'Linear': 3}
```
Raw data
{
"_id": null,
"home_page": "https://github.com/GSAUC3/pytorch-model-details",
"name": "pytorchsummary",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "python,PyTorch,Pytorch model summary,Pytorch parameter summary",
"author": "Rajarshi Banerjee",
"author_email": "raju.banerjee.720@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/ba/14/488e8a6489c802c5544580faf0a3cc6a572ed8462c64deca4e382ede4120/pytorchsummary-1.3.0.tar.gz",
"platform": null,
"description": "# PyTorch Model Parameters Summary\n\n#### Install using pip\n```\npip install pytorchsummary\n```\n## Example 1\n\n```python\nfrom torch import nn\nfrom pytorchsummary import summary\n\nclass CNNET(nn.Module):\n def __init__(self):\n super(CNNET,self).__init__()\n\n self.layer = nn.Sequential(\n nn.Conv2d(3,16,5), # 28-5+1\n nn.ReLU(), #24\n nn.MaxPool2d(2,2), # 12\n\n nn.Conv2d(16,32,3), # 12+1-3\n nn.ReLU(), # 10\n nn.MaxPool2d(2,2), # 5\n \n\n nn.Conv2d(32,64,5), # 11-3+1\n nn.ReLU(),\n\n nn.Conv2d(64,10,1) \n )\n \n def forward(self,x):\n x = self.layer(x)\n return x\n\nm = CNNET()\nsummary((3,128,128),m) \n```\n\n### Output\n``` Layer\tOutput Shape \t Kernal Shape \t#params \t#(weights + bias) \trequires_grad\n------------------------------------------------------------------------------------------------------------------------------------------------------\n Conv2d-1\t[1, 16, 124, 124] \t [16, 3, 5, 5] \t1216 \t(1200 + 16) \tTrue True \n ReLU-2\t[1, 16, 124, 124] \t \t \t \t \n MaxPool2d-3\t[1, 16, 62, 62] \t \t \t \t \n Conv2d-4\t[1, 32, 60, 60] \t [32, 16, 3, 3] \t4640 \t(4608 + 32) \tTrue True \n ReLU-5\t[1, 32, 60, 60] \t \t \t \t \n MaxPool2d-6\t[1, 32, 30, 30] \t \t \t \t \n Conv2d-7\t[1, 64, 26, 26] \t [64, 32, 5, 5] \t51264 \t(51200 + 64) \tTrue True \n ReLU-8\t[1, 64, 26, 26] \t \t \t \t \n Conv2d-9\t[1, 10, 26, 26] \t [10, 64, 1, 1] \t650 \t(640 + 10) \tTrue True \n______________________________________________________________________________________________________________________________________________________\n\nTotal parameters 57,770\nTotal Non-Trainable parameters 0\nTotal Trainable parameters 57,770\n(57770, 57770, 0)\n```\n\n```python\nfor i,j in enumerate(m.parameters()):\n if i==2:\n break\n j.requires_grad=False \nsummary((3,128,128),m,border=True) \n\n```\n```\n Layer\tOutput Shape \t Kernal Shape \t#params \t#(weights + bias) \trequires_grad\n------------------------------------------------------------------------------------------------------------------------------------------------------\n Conv2d-1\t[1, 16, 124, 124] \t [16, 3, 5, 5] \t1216 \t(1200 + 16) \tFalse False\n______________________________________________________________________________________________________________________________________________________\n ReLU-2\t[1, 16, 124, 124] \t \t \t \t \n______________________________________________________________________________________________________________________________________________________\n MaxPool2d-3\t[1, 16, 62, 62] \t \t \t \t \n______________________________________________________________________________________________________________________________________________________\n Conv2d-4\t[1, 32, 60, 60] \t [32, 16, 3, 3] \t4640 \t(4608 + 32) \tTrue True \n______________________________________________________________________________________________________________________________________________________\n ReLU-5\t[1, 32, 60, 60] \t \t \t \t \n______________________________________________________________________________________________________________________________________________________\n MaxPool2d-6\t[1, 32, 30, 30] \t \t \t \t \n______________________________________________________________________________________________________________________________________________________\n Conv2d-7\t[1, 64, 26, 26] \t [64, 32, 5, 5] \t51264 \t(51200 + 64) \tTrue True \n______________________________________________________________________________________________________________________________________________________\n ReLU-8\t[1, 64, 26, 26] \t \t \t \t \n______________________________________________________________________________________________________________________________________________________\n Conv2d-9\t[1, 10, 26, 26] \t [10, 64, 1, 1] \t650 \t(640 + 10) \tTrue True \n______________________________________________________________________________________________________________________________________________________\n______________________________________________________________________________________________________________________________________________________\n\nTotal parameters 57,770\nTotal Non-Trainable parameters 1,216\nTotal Trainable parameters 56,554\n(56554, 57770, 1216)\n```\n\n\n\n## Example 2\n```python\nfrom torchvision import models\nfrom pytorchsummary import summary\n\nm = models.alexnet(False)\nsummary((3,224,224),m)\n# this function returns the total number of \n# parameters (int) in a model\n```\n### ouput\n```\n Layer\tOutput Shape \t Kernal Shape \t#params \t#(weights + bias) \trequires_grad\n------------------------------------------------------------------------------------------------------------------------------------------------------\n Conv2d-1\t[1, 64, 55, 55] \t [64, 3, 11, 11] \t23296 \t(23232 + 64) \tTrue True \n ReLU-2\t[1, 64, 55, 55] \t \t \t \t \n MaxPool2d-3\t[1, 64, 27, 27] \t \t \t \t \n Conv2d-4\t[1, 192, 27, 27] \t [192, 64, 5, 5] \t307392 \t(307200 + 192) \tTrue True \n ReLU-5\t[1, 192, 27, 27] \t \t \t \t \n MaxPool2d-6\t[1, 192, 13, 13] \t \t \t \t \n Conv2d-7\t[1, 384, 13, 13] \t [384, 192, 3, 3] \t663936 \t(663552 + 384) \tTrue True \n ReLU-8\t[1, 384, 13, 13] \t \t \t \t \n Conv2d-9\t[1, 256, 13, 13] \t [256, 384, 3, 3] \t884992 \t(884736 + 256) \tTrue True \n ReLU-10\t[1, 256, 13, 13] \t \t \t \t \n Conv2d-11\t[1, 256, 13, 13] \t [256, 256, 3, 3] \t590080 \t(589824 + 256) \tTrue True \n ReLU-12\t[1, 256, 13, 13] \t \t \t \t \n MaxPool2d-13\t[1, 256, 6, 6] \t \t \t \t \nAdaptiveAvgPool2d-14\t[1, 256, 6, 6] \t \t \t \t \n Dropout-15\t[1, 9216] \t \t \t \t \n Linear-16\t[1, 4096] \t [4096, 9216] \t37752832 \t(37748736 + 4096) \tTrue True \n ReLU-17\t[1, 4096] \t \t \t \t \n Dropout-18\t[1, 4096] \t \t \t \t \n Linear-19\t[1, 4096] \t [4096, 4096] \t16781312 \t(16777216 + 4096) \tTrue True \n ReLU-20\t[1, 4096] \t \t \t \t \n Linear-21\t[1, 1000] \t [1000, 4096] \t4097000 \t(4096000 + 1000) \tTrue True \n______________________________________________________________________________________________________________________________________________________\n\nTotal parameters 61,100,840\nTotal Non-Trainable parameters 0\nTotal Trainable parameters 61,100,840\n(61100840, 61100840, 0)\n```\n\n### Calculating the number of specific layer, or layer frequencies\n```python\nfrom pytorchsummary import get_num_layers\nprint(get_num_layers(m)) # alexnet model \n```\nOutput:\n```\n{'Conv2d': 5,\n 'ReLU': 7,\n 'MaxPool2d': 3,\n 'AdaptiveAvgPool2d': 1,\n 'Dropout': 2,\n 'Linear': 3}\n ```\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Summary of PyTorch Models just like `model.summary() in Keras",
"version": "1.3.0",
"split_keywords": [
"python",
"pytorch",
"pytorch model summary",
"pytorch parameter summary"
],
"urls": [
{
"comment_text": "",
"digests": {
"md5": "8038266d54fbdb6f60dac2068fecbe66",
"sha256": "0463ee021c92a5144e956f5edabb74e44d796cad627454d4829488b77fc64b9b"
},
"downloads": -1,
"filename": "pytorchsummary-1.3.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "8038266d54fbdb6f60dac2068fecbe66",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 5010,
"upload_time": "2022-08-10T11:09:53",
"upload_time_iso_8601": "2022-08-10T11:09:53.142951Z",
"url": "https://files.pythonhosted.org/packages/d9/4c/03701317ba3a23deb99b3ce8c8581103c19c0d83ba4bea6a9613f6717798/pytorchsummary-1.3.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"md5": "178bf240b5c876e8056d7dc0df0abeae",
"sha256": "60139081ede1db84178507059572482bed47ff67cc686a0173ddde09a81a3025"
},
"downloads": -1,
"filename": "pytorchsummary-1.3.0.tar.gz",
"has_sig": false,
"md5_digest": "178bf240b5c876e8056d7dc0df0abeae",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 4567,
"upload_time": "2022-08-10T11:09:55",
"upload_time_iso_8601": "2022-08-10T11:09:55.162860Z",
"url": "https://files.pythonhosted.org/packages/ba/14/488e8a6489c802c5544580faf0a3cc6a572ed8462c64deca4e382ede4120/pytorchsummary-1.3.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2022-08-10 11:09:55",
"github": true,
"gitlab": false,
"bitbucket": false,
"github_user": "GSAUC3",
"github_project": "pytorch-model-details",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "pytorchsummary"
}
JSON
