Machine Learning

These details have not been verified by PyPI

Project links

Homepage

Development Status
- 3 - Alpha
Intended Audience
- Education
Operating System
Programming Language
- Python :: 2
- Python :: 3

Project description

RSProduction MachineLearning

This project provides some usefull machine learning functionality.

1 dataset
2 metrics
3 model
4 multi_transforms
5 run
- 5.1 Run : builtins.object

1 dataset

TOC

1.1 HMDB51 : torch.utils.data.dataset.Dataset

TOC

Description

Dataset class for HMDB51.

Example

from rsp.ml.dataset import HMDB51
import rsp.ml.multi_transforms as multi_transforms
import cv2 as cv

transforms = multi_transforms.Compose([
    multi_transforms.Color(1.5, p=0.5),
    multi_transforms.Stack()
])
ds = HMDB51('train', fold=1, transforms=transforms)

for X, T in ds:
  for x in X.permute(0, 2, 3, 1):
    img_color = x[:, :, :3].numpy()
    img_depth = x[:, :, 3].numpy()

    cv.imshow('color', img_color)
    cv.imshow('depth', img_depth)

    cv.waitKey(30)

1.1.1 init

TOC

Description

Initializes a new instance.

Parameters

Name	Type	Description
split	str	Dataset split [train
fold	int	Fold number. The dataset is split into 3 folds. If fold is None, all folds will be loaded.
cache_dir	str, default = None	Directory to store the downloaded files. If set to `None`, the default cache directory will be used
force_reload	bool, default = False	If set to `True`, the dataset will be reloaded
target_size	(int, int), default = (400, 400)	Size of the frames. The frames will be resized to this size.
sequence_length	int, default = 30	Length of the sequences
transforms	rsp.ml.multi_transforms.Compose = default = rsp.ml.multi_transforms.Compose([])	Transformations, that will be applied to each input sequence. See documentation of `rsp.ml.multi_transforms` for more details.
verbose	bool, default = False	If set to `True`, the progress will be printed.

1.2 Kinetics : torch.utils.data.dataset.Dataset

TOC

Description

Dataset class for the Kinetics dataset.

Example

from rsp.ml.dataset import Kinetics

ds = Kinetics(split='train', type=400)

for X, T in ds:
    print(X)

1.2.1 init

TOC

Description

Initializes a new instance.

Parameters

Name	Type	Description
split	str	Dataset split [train
type	int, default = 400	Type of the kineticts dataset. Currently only 400 is supported.
frame_size	(int, int), default = (400, 400)	Size of the frames. The frames will be resized to this size.
transforms	rsp.ml.multi_transforms.Compose = default = rsp.ml.multi_transforms.Compose([])	Transformations, that will be applied to each input sequence. See documentation of `rsp.ml.multi_transforms` for more details.
cache_dir	str, default = None	Directory to store the downloaded files. If set to `None`, the default cache directory will be used
num_threads	int, default = 0	Number of threads to use for downloading the files.

1.3 TUCRID : torch.utils.data.dataset.Dataset

TOC

Description

Dataset class for the Robot Interaction Dataset by University of Technology Chemnitz (TUCRID).

Example

from rsp.ml.dataset import TUCRID
from rsp.ml.dataset import ReplaceBackgroundRGBD
import rsp.ml.multi_transforms as multi_transforms
import cv2 as cv

backgrounds = TUCRID.load_backgrounds_color()
transforms = multi_transforms.Compose([
    ReplaceBackgroundRGBD(backgrounds),
    multi_transforms.Stack()
])

ds = TUCRID('train', transforms=transforms)

for X, T in ds:
  for x in X.permute(0, 2, 3, 1):
    img_color = x[:, :, :3].numpy()
    img_depth = x[:, :, 3].numpy()

    cv.imshow('color', img_color)
    cv.imshow('depth', img_depth)

    cv.waitKey(30)

1.3.1 init

TOC

Description

Initializes a new instance.

Parameters

Name	Type	Description
phase	str	Dataset phase [train
load_depth_data	bool, default = True	Load depth data
sequence_length	int, default = 30	Length of the sequences
num_classes	int, default = 10	Number of classes
transforms	rsp.ml.multi_transforms.Compose = default = rsp.ml.multi_transforms.Compose([])	Transformations, that will be applied to each input sequence. See documentation of `rsp.ml.multi_transforms` for more details.

1.3.2 get_uniform_sampler

TOC

1.3.3 load_backgrounds

TOC

Description

Loads the background images.

Parameters

Name	Type	Description
load_depth_data	bool, default = True	If set to `True`, the depth images will be loaded as well.

1.4 UCF101 : torch.utils.data.dataset.Dataset

TOC

Description

An abstract class representing a :class:Dataset.

All datasets that represent a map from keys to data samples should subclass it. All subclasses should overwrite :meth:__getitem__, supporting fetching a data sample for a given key. Subclasses could also optionally overwrite :meth:__len__, which is expected to return the size of the dataset by many :class:~torch.utils.data.Sampler implementations and the default options of :class:~torch.utils.data.DataLoader. Subclasses could also optionally implement :meth:__getitems__, for speedup batched samples loading. This method accepts list of indices of samples of batch and returns list of samples.

.. note:: :class:~torch.utils.data.DataLoader by default constructs an index sampler that yields integral indices. To make it work with a map-style dataset with non-integral indices/keys, a custom sampler must be provided.

Example

from rsp.ml.dataset import UCF101
import rsp.ml.multi_transforms as multi_transforms
import cv2 as cv

transforms = multi_transforms.Compose([
    multi_transforms.Color(1.5, p=0.5),
    multi_transforms.Stack()
])
ds = UCF101('train', fold=1, transforms=transforms)

for X, T in ds:
  for x in X.permute(0, 2, 3, 1):
    img_color = x[:, :, :3].numpy()
    img_depth = x[:, :, 3].numpy()

    cv.imshow('color', img_color)
    cv.imshow('depth', img_depth)

    cv.waitKey(30)

1.4.1 init

TOC

Description

Initializes a new instance.

Parameters

Name	Type	Description
split	str	Dataset split [train
fold	int	Fold number. The dataset is split into 3 folds. If fold is None, all folds will be loaded.
cache_dir	str, default = None	Directory to store the downloaded files. If set to `None`, the default cache directory will be used
force_reload	bool, default = False	If set to `True`, the dataset will be reloaded
target_size	(int, int), default = (400, 400)	Size of the frames. The frames will be resized to this size.
sequence_length	int, default = 30	Length of the sequences
transforms	rsp.ml.multi_transforms.Compose = default = rsp.ml.multi_transforms.Compose([])	Transformations, that will be applied to each input sequence. See documentation of `rsp.ml.multi_transforms` for more details.
verbose	bool, default = False	If set to `True`, the progress will be printed.

2 metrics

TOC

The module rsp.ml.metrics provides some functionality to quantify the quality of predictions.

2.1 AUROC

TOC

Description

Calculates the Area under the Receiver Operation Chracteristic Curve.

Parameters

Name	Type	Description
Y	torch.Tensor	Prediction
T	torch.Tensor	True values
num_thresholds	int, default = 100	Number of thresholds to compute.

Returns

Receiver Operation Chracteristic Area under the Curve : float

2.2 F1_Score

TOC

Description

F1 Score. Expected input shape: (batch_size, num_classes)

Parameters

Name	Type	Description
Y	torch.Tensor	Prediction
T	torch.Tensor	True values
threshold	float	All values that are greater than or equal to the threshold are considered a positive class.

Returns

F1 Score : float

Equations

$precision = \frac{TP}{TP + FP}$

$recall = \frac{TP}{TP + FN}$

$F_1 = \frac{2 \cdot precision \cdot recall}{precision + recall} = \frac{2 \cdot TP}{2 \cdot TP + FP + FN}$

Example

import rsp.ml.metrics as m

Y = torch.tensor([
  [0.1, 0.1, 0.8],
  [0.03, 0.95, 0.02],
  [0.05, 0.9, 0.05],
  [0.01, 0.87, 0.12],
  [0.04, 0.03, 0.93],
  [0.94, 0.02, 0.06]
])
T = torch.tensor([
  [0, 0, 1],
  [1, 0, 0],
  [0, 1, 0],
  [0, 1, 0],
  [0, 0, 1],
  [1, 0, 0]
])

f1score = m.F1_Score(Y, T)

print(f1score) --> 0.5

2.3 FN

TOC

Description

False negatives. Expected input shape: (batch_size, num_classes)

Parameters

Name	Type	Description
Y	torch.Tensor	Prediction
T	torch.Tensor	True values
threshold	float	All values that are greater than or equal to the threshold are considered a positive class.

Returns

False negatives : int

Example

import rsp.ml.metrics as m
import torch

Y = torch.tensor([
  [0.1, 0.1, 0.8],
  [0.03, 0.95, 0.02],
  [0.05, 0.9, 0.05],
  [0.01, 0.87, 0.12],
  [0.04, 0.03, 0.93],
  [0.94, 0.02, 0.06]
])
T = torch.tensor([
  [0, 0, 1],
  [1, 0, 0],
  [0, 1, 0],
  [0, 1, 0],
  [0, 0, 1],
  [1, 0, 0]
])

fn = m.FN(Y, T)
print(fn) -> 1

2.4 FP

TOC

Description

False positives. Expected input shape: (batch_size, num_classes)

Parameters

Name	Type	Description
Y	torch.Tensor	Prediction
T	torch.Tensor	True values
threshold	float	All values that are greater than or equal to the threshold are considered a positive class.

Returns

False positives : int

Example

import rsp.ml.metrics as m
import torch

Y = torch.tensor([
  [0.1, 0.1, 0.8],
  [0.03, 0.95, 0.02],
  [0.05, 0.9, 0.05],
  [0.01, 0.87, 0.12],
  [0.04, 0.03, 0.93],
  [0.94, 0.02, 0.06]
])
T = torch.tensor([
  [0, 0, 1],
  [1, 0, 0],
  [0, 1, 0],
  [0, 1, 0],
  [0, 0, 1],
  [1, 0, 0]
])

fp = m.FP(Y, T)
print(fp) -> 1

2.5 FPR

TOC

Description

False positive rate. Expected input shape: (batch_size, num_classes)

Parameters

Name	Type	Description
Y	torch.Tensor	Prediction
T	torch.Tensor	True values
threshold	float	All values that are greater than or equal to the threshold are considered a positive class.

Returns

False positive rate : float

Example

import rsp.ml.metrics as m
import torch

Y = torch.tensor([
  [0.1, 0.1, 0.8],
  [0.03, 0.95, 0.02],
  [0.05, 0.9, 0.05],
  [0.01, 0.87, 0.12],
  [0.04, 0.03, 0.93],
  [0.94, 0.02, 0.06]
])
T = torch.tensor([
  [0, 0, 1],
  [1, 0, 0],
  [0, 1, 0],
  [0, 1, 0],
  [0, 0, 1],
  [1, 0, 0]
])

fpr = m.FPR(Y, T)
print(fpr) -> 0.08333333333333333

2.6 ROC

TOC

Description

Calculates the receiver operating characteristic: computes False Positive Rates and True positive Rates for num_thresholds aligned between 0 and 1

Parameters

Name	Type	Description
Y	torch.Tensor	Prediction
T	torch.Tensor	True values
num_thresholds	int, default = 100	Number of thresholds to compute.

Returns

(False Positive Rates, True Positive Rates) for 100 different thresholds : (List[float], List[float])

Example

import rsp.ml.metrics as m
import torch
import torch.nn.functional as F

num_elements = 100000
num_classes = 7

T = []
for i in range(num_elements):
  true_class = torch.randint(0, num_classes, (1,))
  t = F.one_hot(true_class, num_classes=num_classes)
  T.append(t)
T = torch.cat(T)

dist = torch.normal(T.float(), 1.5)
Y = F.softmax(dist, dim = 1)
FPRs, TPRs = m.ROC(Y, T)

2.7 TN

TOC

Description

True negatives. Expected input shape: (batch_size, num_classes)

Parameters

Name	Type	Description
Y	torch.Tensor	Prediction
T	torch.Tensor	True values
threshold	float	All values that are greater than or equal to the threshold are considered a positive class.

Returns

True negatives : int

Example

import rsp.ml.metrics as m
import torch

Y = torch.tensor([
  [0.1, 0.1, 0.8],
  [0.03, 0.95, 0.02],
  [0.05, 0.9, 0.05],
  [0.01, 0.87, 0.12],
  [0.04, 0.03, 0.93],
  [0.94, 0.02, 0.06]
])
T = torch.tensor([
  [0, 0, 1],
  [1, 0, 0],
  [0, 1, 0],
  [0, 1, 0],
  [0, 0, 1],
  [1, 0, 0]
])

tn = m.TN(Y, T)
print(tn) -> 11

2.8 TP

TOC

Description

True positives. Expected input shape: (batch_size, num_classes)

Parameters

Name	Type	Description
Y	torch.Tensor	Prediction
T	torch.Tensor	True values
threshold	float	All values that are greater than or equal to the threshold are considered a positive class.

Returns

True positives : int

Example

import rsp.ml.metrics as m
import torch

Y = torch.tensor([
  [0.1, 0.1, 0.8],
  [0.03, 0.95, 0.02],
  [0.05, 0.9, 0.05],
  [0.01, 0.87, 0.12],
  [0.04, 0.03, 0.93],
  [0.94, 0.02, 0.06]
])
T = torch.tensor([
  [0, 0, 1],
  [1, 0, 0],
  [0, 1, 0],
  [0, 1, 0],
  [0, 0, 1],
  [1, 0, 0]
])

tp = m.TP(Y, T)
print(tp) -> 5

2.9 TPR

TOC

Description

True positive rate. Expected input shape: (batch_size, num_classes)

Parameters

Name	Type	Description
Y	torch.Tensor	Prediction
T	torch.Tensor	True values
threshold	float	All values that are greater than or equal to the threshold are considered a positive class.

Returns

True positive rate : float

Example

import rsp.ml.metrics as m
import torch

Y = torch.tensor([
  [0.1, 0.1, 0.8],
  [0.03, 0.95, 0.02],
  [0.05, 0.9, 0.05],
  [0.01, 0.87, 0.12],
  [0.04, 0.03, 0.93],
  [0.94, 0.02, 0.06]
])
T = torch.tensor([
  [0, 0, 1],
  [1, 0, 0],
  [0, 1, 0],
  [0, 1, 0],
  [0, 0, 1],
  [1, 0, 0]
])

tpr = m.TPR(Y, T)
print(tpr) -> 0.8333333333333334

2.10 confusion_matrix

TOC

Description

Calculates the confusion matrix. Expected input shape: (batch_size, num_classes)

Parameters

Name	Type	Description
Y	torch.Tensor	Prediction
T	torch.Tensor	True values

Returns

Confusion matrix : torch.Tensor

Example

import rsp.ml.metrics as m
import torch

Y = torch.tensor([
  [0.1, 0.1, 0.8],
  [0.03, 0.95, 0.02],
  [0.05, 0.9, 0.05],
  [0.01, 0.87, 0.12],
  [0.04, 0.03, 0.93],
  [0.94, 0.02, 0.06]
])
T = torch.tensor([
  [0, 0, 1],
  [1, 0, 0],
  [0, 1, 0],
  [0, 1, 0],
  [0, 0, 1],
  [1, 0, 0]
])

conf_mat = m.confusion_matrix(Y, T)
print(conf_mat) -> tensor([
  [1, 1, 0],
  [0, 2, 0],
  [0, 0, 2]
])

2.11 plot_ROC

TOC

Description

Plot the receiver operating characteristic.

Parameters

Name	Type	Description
Y	torch.Tensor	Prediction
T	torch.Tensor	True values
num_thresholds	int, default = 100	Number of thresholds to compute.
title	str, optional, default = 'Confusion Matrix'	Title of the plot
class_curves	bool, default = False	Plot ROC curve for each class
labels	str, optional, default = None	Class labels -> automatic labeling C000, ..., CXXX if labels is None
plt_show	bool, optional, default = False	Set to True to show the plot
save_file_name	str, optional, default = None	If not None, the plot is saved under the specified save_file_name.

Returns

Image of the confusion matrix : np.array

2.12 plot_confusion_matrix

TOC

Description

Plot the confusion matrix

Parameters

Name	Type	Description
confusion_matrix	torch.Tensor	Confusion matrix
labels	str, optional, default = None	Class labels -> automatic labeling C000, ..., CXXX if labels is None
cmap	str, optional, default = 'Blues'	Seaborn cmap, see https://r02b.github.io/seaborn_palettes/
xlabel	str, optional, default = 'Predicted label'	X-Axis label
ylabel	str, optional, default = 'True label'	Y-Axis label
title	str, optional, default = 'Confusion Matrix'	Title of the plot
plt_show	bool, optional, default = False	Set to True to show the plot
save_file_name	str, optional, default = None	If not None, the plot is saved under the specified save_file_name.

Returns

Image of the confusion matrix : np.array

2.13 precision

TOC

Description

Precision. Expected input shape: (batch_size, num_classes)

Parameters

Name	Type	Description
Y	torch.Tensor	Prediction
T	torch.Tensor	True values
threshold	float	All values that are greater than or equal to the threshold are considered a positive class.

Returns

Precision : float

Equations

$precision = \frac{TP}{TP + FP}$

Example

import rsp.ml.metrics as m
import torch

Y = torch.tensor([
  [0.1, 0.1, 0.8],
  [0.03, 0.95, 0.02],
  [0.05, 0.9, 0.05],
  [0.01, 0.87, 0.12],
  [0.04, 0.03, 0.93],
  [0.94, 0.02, 0.06]
])
T = torch.tensor([
  [0, 0, 1],
  [1, 0, 0],
  [0, 1, 0],
  [0, 1, 0],
  [0, 0, 1],
  [1, 0, 0]
])

precision = m.precision(Y, T)
print(precision) -> 0.8333333333333334

2.14 recall

TOC

Description

Recall. Expected input shape: (batch_size, num_classes)

Parameters

Name	Type	Description
Y	torch.Tensor	Prediction
T	torch.Tensor	True values
threshold	float	All values that are greater than or equal to the threshold are considered a positive class.

Returns

Recall : float

Equations

$recall = \frac{TP}{TP + FN}$

Example

import rsp.ml.metrics as m
import torch

Y = torch.tensor([
  [0.1, 0.1, 0.8],
  [0.03, 0.95, 0.02],
  [0.05, 0.9, 0.05],
  [0.01, 0.87, 0.12],
  [0.04, 0.03, 0.93],
  [0.94, 0.02, 0.06]
])
T = torch.tensor([
  [0, 0, 1],
  [1, 0, 0],
  [0, 1, 0],
  [0, 1, 0],
  [0, 0, 1],
  [1, 0, 0]
])

recall = m.recall(Y, T)
print(recall) -> 0.8333333333333334

2.15 top_10_accuracy

TOC

Description

Top 10 accuracy. Expected input shape: (batch_size, num_classes)

Parameters

Name	Type	Description
Y	torch.Tensor	Prediction
T	torch.Tensor	True values

Returns

Top 10 accuracy -> top k accuracy | k = 10 : float

Example

import rsp.ml.metrics as m

Y = torch.tensor([
  [0.1, 0.1, 0.8],
  [0.03, 0.95, 0.02],
  [0.05, 0.9, 0.05],
  [0.01, 0.87, 0.12],
  [0.04, 0.03, 0.93],
  [0.94, 0.02, 0.06]
])
T = torch.tensor([
  [0, 0, 1],
  [1, 0, 0],
  [0, 1, 0],
  [0, 1, 0],
  [0, 0, 1],
  [1, 0, 0]
])

top_10_accuracy = m.top_10_accuracy(Y, T, k = 3)

print(top_10_accuracy) --> 1.0

2.16 top_1_accuracy

TOC

Description

Top 1 accuracy. Expected input shape: (batch_size, num_classes)

Parameters

Name	Type	Description
Y	torch.Tensor	Prediction
T	torch.Tensor	True values

Returns

Top 1 accuracy -> top k accuracy | k = 1 : float

Example

import rsp.ml.metrics as m

Y = torch.tensor([
  [0.1, 0.1, 0.8],
  [0.03, 0.95, 0.02],
  [0.05, 0.9, 0.05],
  [0.01, 0.87, 0.12],
  [0.04, 0.03, 0.93],
  [0.94, 0.02, 0.06]
])
T = torch.tensor([
  [0, 0, 1],
  [1, 0, 0],
  [0, 1, 0],
  [0, 1, 0],
  [0, 0, 1],
  [1, 0, 0]
])

top_1_accuracy = m.top_1_accuracy(Y, T, k = 3)

print(top_1_accuracy) --> 0.8333333333333334

2.17 top_2_accuracy

TOC

Description

Top 2 accuracy. Expected input shape: (batch_size, num_classes)

Parameters

Name	Type	Description
Y	torch.Tensor	Prediction
T	torch.Tensor	True values

Returns

Top 2 accuracy -> top k accuracy | k = 2 : float

Example

import rsp.ml.metrics as m

Y = torch.tensor([
  [0.1, 0.1, 0.8],
  [0.03, 0.95, 0.02],
  [0.05, 0.9, 0.05],
  [0.01, 0.87, 0.12],
  [0.04, 0.03, 0.93],
  [0.94, 0.02, 0.06]
])
T = torch.tensor([
  [0, 0, 1],
  [1, 0, 0],
  [0, 1, 0],
  [0, 1, 0],
  [0, 0, 1],
  [1, 0, 0]
])

top_2_accuracy = m.top_2_accuracy(Y, T, k = 3)

print(top_2_accuracy) --> 1.0

2.18 top_3_accuracy

TOC

Description

Top 3 accuracy. Expected input shape: (batch_size, num_classes)

Parameters

Name	Type	Description
Y	torch.Tensor	Prediction
T	torch.Tensor	True values

Returns

Top 3 accuracy -> top k accuracy | k = 3 : float

Example

import rsp.ml.metrics as m

Y = torch.tensor([
  [0.1, 0.1, 0.8],
  [0.03, 0.95, 0.02],
  [0.05, 0.9, 0.05],
  [0.01, 0.87, 0.12],
  [0.04, 0.03, 0.93],
  [0.94, 0.02, 0.06]
])
T = torch.tensor([
  [0, 0, 1],
  [1, 0, 0],
  [0, 1, 0],
  [0, 1, 0],
  [0, 0, 1],
  [1, 0, 0]
])

top_3_accuracy = m.top_3_accuracy(Y, T, k = 3)

print(top_3_accuracy) --> 1.0

2.19 top_5_accuracy

TOC

Description

Top 5 accuracy. Expected input shape: (batch_size, num_classes)

Parameters

Name	Type	Description
Y	torch.Tensor	Prediction
T	torch.Tensor	True values

Returns

Top 5 accuracy -> top k accuracy | k = 5 : float

Example

import rsp.ml.metrics as m

Y = torch.tensor([
  [0.1, 0.1, 0.8],
  [0.03, 0.95, 0.02],
  [0.05, 0.9, 0.05],
  [0.01, 0.87, 0.12],
  [0.04, 0.03, 0.93],
  [0.94, 0.02, 0.06]
])
T = torch.tensor([
  [0, 0, 1],
  [1, 0, 0],
  [0, 1, 0],
  [0, 1, 0],
  [0, 0, 1],
  [1, 0, 0]
])

top_5_accuracy = m.top_5_accuracy(Y, T, k = 3)

print(top_5_accuracy) --> 1.0

2.20 top_k_accuracy

TOC

Description

Top k accuracy. Expected input shape: (batch_size, num_classes)

Parameters

Name	Type	Description
Y	torch.Tensor	Prediction
T	torch.Tensor	True values

Returns

Top k accuracy : float

Example

import rsp.ml.metrics as m

Y = torch.tensor([
  [0.1, 0.1, 0.8],
  [0.03, 0.95, 0.02],
  [0.05, 0.9, 0.05],
  [0.01, 0.87, 0.12],
  [0.04, 0.03, 0.93],
  [0.94, 0.02, 0.06]
])
T = torch.tensor([
  [0, 0, 1],
  [1, 0, 0],
  [0, 1, 0],
  [0, 1, 0],
  [0, 0, 1],
  [1, 0, 0]
])

top_k_accuracy = m.top_k_accuracy(Y, T, k = 3)

print(top_k_accuracy) --> 1.0

3 model

TOC

The module rsp.ml.model provides some usefull functionality to store and load pytorch models.

3.1 MODELS : enum.Enum

TOC

Description

Create a collection of name/value pairs.

Example enumeration:

class Color(Enum): ... RED = 1 ... BLUE = 2 ... GREEN = 3

Access them by:

attribute access::

Color.RED <Color.RED: 1>

value lookup:

Color(1) <Color.RED: 1>

name lookup:

Color['RED'] <Color.RED: 1>

Enumerations can be iterated over, and know how many members they have:

len(Color) 3

list(Color) [<Color.RED: 1>, <Color.BLUE: 2>, <Color.GREEN: 3>]

Methods can be added to enumerations, and members can have their own attributes -- see the documentation for details.

3.2 WEIGHTS : enum.Enum

TOC

Description

Create a collection of name/value pairs.

Example enumeration:

class Color(Enum): ... RED = 1 ... BLUE = 2 ... GREEN = 3

Access them by:

attribute access::

Color.RED <Color.RED: 1>

value lookup:

Color(1) <Color.RED: 1>

name lookup:

Color['RED'] <Color.RED: 1>

Enumerations can be iterated over, and know how many members they have:

len(Color) 3

list(Color) [<Color.RED: 1>, <Color.BLUE: 2>, <Color.GREEN: 3>]

Methods can be added to enumerations, and members can have their own attributes -- see the documentation for details.

3.3 list_model_weights

TOC

Description

Lists all available weight files.

Returns

List of (MODEL:str, WEIGHT:str) : List[Tuple(str, str)]

Example

import rsp.ml.model as model

model_weight_files = model.list_model_weights()

3.4 load_model

TOC

Description

Loads a pretrained PyTorch model from HuggingFace.

Parameters

Name	Type	Description
model	MODELS	ID of the model
weights	WEIGHTS	ID of the weights

Returns

Pretrained PyTorch model : torch.nn.Module

Example

import rsp.ml.model as model

action_recognition_model = model.load_model(MODEL.TUCARC3D, WEIGHTS.TUCAR)

3.5 publish_model

TOC

4 multi_transforms

TOC

The module rsp.ml.multi_transforms is based on torchvision.transforms, which is made for single images. rsp.ml.multi_transforms extends this functionality by providing transformations for sequences of images, which could be usefull for video augmentation.

4.1 BGR2GRAY : MultiTransform

TOC

Description

Converts a sequence of BGR images to grayscale images.

4.1.1 call

TOC

Description

Call self as a function.

Parameters

Name	Type	Description
input	torch.Tensor List[PIL.Image] List[numpy.array]	Sequence of images

4.1.2 init

TOC

Description

Initializes a new instance.

4.2 BGR2RGB : MultiTransform

TOC

Description

Converts sequence of BGR images to RGB images.

4.2.1 call

TOC

Description

Call self as a function.

Parameters

Name	Type	Description
input	torch.Tensor List[PIL.Image] List[numpy.array]	Sequence of images

4.2.2 init

TOC

Description

Initializes a new instance.

4.3 Brightness : MultiTransform

TOC

Description

MultiTransform is an extension to keep the same transformation over a sequence of images instead of initializing a new transformation for every single image. It is inspired by torchvision.transforms and could be used for video augmentation. Use rsp.ml.multi_transforms.Composeto combine multiple image sequence transformations.

Note rsp.ml.multi_transforms.MultiTransform is a base class and should be inherited.

4.3.1 call

TOC

Description

Call self as a function.

Parameters

Name	Type	Description
input	torch.Tensor List[PIL.Image] List[numpy.array]	Sequence of images

4.3.2 init

TOC

Description

Initializes a new instance.

4.4 CenterCrop : MultiTransform

TOC

Description

Crops Images at the center after upscaling them. Dimensions kept the same.

4.4.1 call

TOC

Description

Call self as a function.

Parameters

Name	Type	Description
input	torch.Tensor List[PIL.Image] List[numpy.array]	Sequence of images

4.4.2 init

TOC

Description

Initializes a new instance.

Parameters

Name	Type	Description
max_scale	float	Images are scaled randomly between 1. and max_scale before cropping to original size.

4.5 Color : MultiTransform

TOC

Description

Note rsp.ml.multi_transforms.MultiTransform is a base class and should be inherited.

4.5.1 call

TOC

Description

Call self as a function.

Parameters

Name	Type	Description
input	torch.Tensor List[PIL.Image] List[numpy.array]	Sequence of images

4.5.2 init

TOC

Description

Initializes a new instance.

4.6 Compose : builtins.object

TOC

Description

Composes several MultiTransforms together.

Example

import rsp.ml.multi_transforms as t

transforms = t.Compose([
  t.BGR2GRAY(),
  t.Scale(0.5)
])

4.6.1 call

TOC

Description

Call self as a function.

4.6.2 init

TOC

Description

Initializes a new instance.

Parameters

Name	Type	Description
children	List[MultiTransform]	List of MultiTransforms to compose.

4.7 GaussianNoise : MultiTransform

TOC

Description

Note rsp.ml.multi_transforms.MultiTransform is a base class and should be inherited.

4.7.1 call

TOC

Description

Call self as a function.

Parameters

Name	Type	Description
input	torch.Tensor List[PIL.Image] List[numpy.array]	Sequence of images

4.7.2 init

TOC

Description

Initializes a new instance.

4.8 MultiTransform : builtins.object

TOC

Description

Note rsp.ml.multi_transforms.MultiTransform is a base class and should be inherited.

4.8.1 call

TOC

Description

Call self as a function.

Parameters

Name	Type	Description
input	torch.Tensor List[PIL.Image] List[numpy.array]	Sequence of images

4.8.2 init

TOC

Description

Initializes a new instance.

4.9 Normalize : MultiTransform

TOC

Description

Normalize images with mean and standard deviation. Given mean: (mean[1],...,mean[n]) and std: (std[1],..,std[n]) for n channels, this transform will normalize each channel of the input torch.*Tensor i.e., output[channel] = (input[channel] - mean[channel]) / std[channel]

Based on torchvision.transforms.Normalize

4.9.1 call

TOC

Description

Call self as a function.

Parameters

Name	Type	Description
input	torch.Tensor List[PIL.Image] List[numpy.array]	Sequence of images

4.9.2 init

TOC

Description

Initializes a new instance.

Parameters

Name	Type	Description
mean	List[float]	Sequence of means for each channel.
std	List[float]	Sequence of standard deviations for each channel.
inplace	bool	Set to True make this operation in-place.

4.10 RGB2BGR : BGR2RGB

TOC

Description

Converts sequence of RGB images to BGR images.

4.10.1 call

TOC

Description

Call self as a function.

Parameters

Name	Type	Description
input	torch.Tensor List[PIL.Image] List[numpy.array]	Sequence of images

4.10.2 init

TOC

Description

Initializes a new instance.

4.11 RandomCrop : MultiTransform

TOC

Description

Crops Images at a random location after upscaling them. Dimensions kept the same.

4.11.1 call

TOC

Description

Call self as a function.

Parameters

Name	Type	Description
input	torch.Tensor List[PIL.Image] List[numpy.array]	Sequence of images

4.11.2 init

TOC

Description

Initializes a new instance.

Parameters

Name	Type	Description
max_scale	float	Images are scaled randomly between 1. and max_scale before cropping to original size.

4.12 RandomHorizontalFlip : MultiTransform

TOC

Description

Note rsp.ml.multi_transforms.MultiTransform is a base class and should be inherited.

4.12.1 call

TOC

Description

Call self as a function.

Parameters

Name	Type	Description
input	torch.Tensor List[PIL.Image] List[numpy.array]	Sequence of images

4.12.2 init

TOC

Description

Initializes a new instance.

4.13 RandomVerticalFlip : MultiTransform

TOC

Description

Note rsp.ml.multi_transforms.MultiTransform is a base class and should be inherited.

4.13.1 call

TOC

Description

Call self as a function.

Parameters

Name	Type	Description
input	torch.Tensor List[PIL.Image] List[numpy.array]	Sequence of images

4.13.2 init

TOC

Description

Initializes a new instance.

4.14 ReplaceBackground : MultiTransform

TOC

Description

Transformation for background replacement based on HSV values. Supports depth background replacement. backgrounds have to be passed as list of tuples of rgb and depth images.

Example

from rsp.nl.dataset import TUCRID
import rsp.ml.multi_transforms as multi_transforms

USE_DEPTH_DATA = False
backgrounds = TUCRID.load_backgrounds(USE_DEPTH_DATA)
tranforms_train = multi_transforms.Compose([
    multi_transforms.ReplaceBackground(
        backgrounds = backgrounds,
        hsv_filter=[(69, 87, 139, 255, 52, 255)],
        p = 0.8
    ),
    multi_transforms.Stack()
])
tucrid = TUCRID('train', load_depth_data=USE_DEPTH_DATA, transforms=tranforms_train)

for X, T in tucrid:
    for x in X:
        img = x.permute(1, 2, 0).numpy()

        cv.imshow('img', img)
        cv.waitKey(30)

4.14.1 call

TOC

Description

Call self as a function.

Parameters

Name	Type	Description
input	torch.Tensor List[PIL.Image] List[numpy.array]	Sequence of images

4.14.2 init

TOC

Description

Transformation for background replacement based on HSV values. Supports depth background replacement. backgrounds have to be passed as list of tuples of rgb and depth images.

Parameters

Name	Type	Description
backgrounds	List[np.array]	List of background images
hsv_filter	List[tuple[int, int, int, int, int, int]]	List of HSV filters
p	float, default = 1.	Probability of applying the transformation
rotate	float, default = 5	Maximum rotation angle
max_scale	float, default = 2	Maximum scaling factor
max_noise	float, default = 0.002	Maximum noise level

4.15 Resize : MultiTransform

TOC

Description

Note rsp.ml.multi_transforms.MultiTransform is a base class and should be inherited.

4.15.1 call

TOC

Description

Call self as a function.

Parameters

Name	Type	Description
input	torch.Tensor List[PIL.Image] List[numpy.array]	Sequence of images

4.15.2 init

TOC

Description

Initializes a new instance.

4.16 Rotate : MultiTransform

TOC

Description

Randomly rotates images.

Equations

$angle = -max_angle + 2 \cdot random() \cdot max_angle$

4.16.1 call

TOC

Description

Call self as a function.

Parameters

Name	Type	Description
input	torch.Tensor List[PIL.Image] List[numpy.array]	Sequence of images

4.16.2 init

TOC

Description

Iitializes a new instance.

Parameters

Name	Type	Description
max_angle	float	Maximal rotation in degrees
auto_scale	bool, default = True	Image will be resized when auto scale is activated to avoid black margins.

4.17 Satturation : MultiTransform

TOC

Description

Note rsp.ml.multi_transforms.MultiTransform is a base class and should be inherited.

4.17.1 call

TOC

Description

Call self as a function.

Parameters

Name	Type	Description
input	torch.Tensor List[PIL.Image] List[numpy.array]	Sequence of images

4.17.2 init

TOC

Description

Initializes a new instance.

4.18 Scale : MultiTransform

TOC

Description

Note rsp.ml.multi_transforms.MultiTransform is a base class and should be inherited.

4.18.1 call

TOC

Description

Call self as a function.

Parameters

Name	Type	Description
input	torch.Tensor List[PIL.Image] List[numpy.array]	Sequence of images

4.18.2 init

TOC

Description

Initializes a new instance.

4.19 Stack : MultiTransform

TOC

Description

Note rsp.ml.multi_transforms.MultiTransform is a base class and should be inherited.

4.19.1 call

TOC

Description

Call self as a function.

Parameters

Name	Type	Description
input	torch.Tensor List[PIL.Image] List[numpy.array]	Sequence of images

4.19.2 init

TOC

Description

Initializes a new instance.

4.20 ToCVImage : MultiTransform

TOC

Description

Converts a torch.Tensorto Open CV image by changing dimensions (d0, d1, d2) -> (d1, d2, d0) and converting torch.Tensor to numpy.

4.20.1 call

TOC

Description

Call self as a function.

Parameters

Name	Type	Description
input	torch.Tensor List[PIL.Image] List[numpy.array]	Sequence of images

4.20.2 init

TOC

Description

Initializes a new instance.

4.21 ToNumpy : MultiTransform

TOC

Description

Converts a torch.Tensorto numpy

4.21.1 call

TOC

Description

Call self as a function.

Parameters

Name	Type	Description
input	torch.Tensor List[PIL.Image] List[numpy.array]	Sequence of images

4.21.2 init

TOC

Description

Initializes a new instance.

4.22 ToPILImage : MultiTransform

TOC

Description

Converts sequence of images to sequence of PIL.Image.

4.22.1 call

TOC

Description

Call self as a function.

Parameters

Name	Type	Description
input	torch.Tensor List[PIL.Image] List[numpy.array]	Sequence of images

4.22.2 init

TOC

Description

Initializes a new instance.

4.23 ToTensor : MultiTransform

TOC

Description

Converts a sequence of images to torch.Tensor.

4.23.1 call

TOC

Description

Call self as a function.

Parameters

Name	Type	Description
input	torch.Tensor List[PIL.Image] List[numpy.array]	Sequence of images

4.23.2 init

TOC

Description

Initializes a new instance.

5 run

TOC

The module rsp.ml.run provides some tools for storing, loading and visualizing data during training of models using PyTorch.

5.1 Run : builtins.object

TOC

Description

Run class to store and manage training

Example

from rsp.ml.run import Run
import rsp.ml.metrics as m

metrics = [
    m.top_1_accuracy
]
config = {
    m.top_1_accuracy.__name__: {
        'ymin': 0,
        'ymax': 1
    }
}
run = Run(id='run0001', metrics=metrics, config=config, ignore_outliers_in_chart_scaling=True)

for epoch in range(100):
    """here goes some training code, giving us inputs, predictions and targets"""
    acc = m.top_1_accuracy(predictions, targets)
    run.append(m.top_1_accuracy.__name__, 'train', acc)

5.1.1 init

TOC

Description

Run class to store and manage training

Parameters

Name	Type	Description
id	str, default = None	Id of the run. If None, a new id is generated
moving_average_epochs	int, default = 1	Number of epochs to average over
metrics	list, default = None	List of metrics to compute. Each metric should be a function that takes Y and T as input.
device	str, default = None	torch device to run on
ignore_outliers_in_chart_scaling	bool, default = False	Ignore outliers when scaling charts
config	dict, default = {}	Configuration dictionary. Keys are metric names and values are dictionaries with keys 'ymin' and 'ymax'

5.1.2 append

TOC

Description

Append value to key in phase.

Parameters

Name	Type	Description
key	str	Key to append to
phase	str	Phase to append to
value	float	Value to append

5.1.3 get_avg

TOC

Description

Get last average value of key in phase

Parameters

Name	Type	Description
key	str	Key to get
phase	str	Phase to get from

Returns

Last average value of key in phase : value : float

5.1.4 get_val

TOC

Description

Get last value of key in phase

Parameters

Name	Type	Description
key	str	Key to get
phase	str	Phase to get from

Returns

Last value of key in phase : value : float

5.1.5 len

TOC

Description

Get length of longest phase

5.1.6 load_best_state_dict

TOC

Description

Load best state_dict from runs/{id}/{fname}

Parameters

Name	Type	Description
model	torch.nn.Module	Model to load state_dict into
fname	str, default = 'state_dict.pt'	Filename to load from
verbose	bool, default = False	Print loaded file

5.1.7 load_state_dict

TOC

Description

Load state_dict from runs/{id}/{fname}

Parameters

Name	Type	Description
model	torch.nn.Module	Model to load state_dict into
fname	str, default = None	Filename to load from

5.1.8 pickle_dump

TOC

Description

Pickle model to runs/{id}/{fname}

Parameters

Name	Type	Description
model	torch.nn.Module	Model to pickle
fname	str, default = 'model.pkl'	Filename to save to

5.1.9 pickle_load

TOC

Description

Load model from runs/{id}/{fname}

Parameters

Name	Type	Description
fname	str, default = 'model.pkl'	Filename to load from

5.1.10 plot

TOC

Description

Plot all keys to runs/{id}/plot/{key}.jpg

5.1.11 recalculate_moving_average

TOC

Description

Recalculate moving average

5.1.12 save

TOC

Description

Save data to runs/{id}/data.json

5.1.13 save_best_state_dict

TOC

Description

Save state_dict if new_acc is better than previous best

Parameters

Name	Type	Description
state_dict	dict	State dict to save
new_acc	float	New accuracy
epoch	int, default = None	Epoch to save
fname	str, default = 'state_dict.pt'	Filename to save to

5.1.14 save_state_dict

TOC

Description

Save state_dict to runs/{id}/{fname}

Parameters

Name	Type	Description
state_dict	dict	State dict to save
fname	str, default = 'state_dict.pt'	Filename to save to

5.1.15 train_epoch

TOC

Description

Train one epoch.

Parameters

Name	Type	Description
dataloader	DataLoader	DataLoader to train on
model	torch.nn.Module	Model to train
optimizer	torch.optim.Optimizer	Optimizer to use
criterion	torch.nn.Module	Criterion to use
num_batches	int, default = None	Number of batches to train on. If None, train on all batches
return_YT	bool, default = False	Append Y and T to results

Returns

Dictionary with results : results : dict

5.1.16 validate_epoch

TOC

Description

Validate one epoch.

Parameters

Name	Type	Description
dataloader	DataLoader	DataLoader to validate on
model	torch.nn.Module	Model to validate
optimizer	torch.optim.Optimizer	Optimizer to use
criterion	torch.nn.Module	Criterion to use
num_batches	int, default = None	Number of batches to validate on. If None, validate on all batches
return_YT	bool, default = False	Append Y and T to results

Returns

Dictionary with results : results : dict

Project details

These details have not been verified by PyPI

Project links

Homepage

Development Status
- 3 - Alpha
Intended Audience
- Education
Operating System
Programming Language
- Python :: 2
- Python :: 3

Release history Release notifications | RSS feed

0.0.149

Apr 10, 2025

0.0.148

Apr 10, 2025

0.0.147

Mar 31, 2025

0.0.146

Mar 27, 2025

0.0.145

Mar 26, 2025

0.0.144

Mar 26, 2025

0.0.143

Mar 26, 2025

0.0.142

Mar 26, 2025

0.0.141

Mar 25, 2025

0.0.140

Mar 25, 2025

0.0.139

Mar 25, 2025

0.0.138

Mar 25, 2025

0.0.137

Mar 24, 2025

0.0.136

Mar 24, 2025

0.0.135

Mar 19, 2025

0.0.134

Mar 18, 2025

0.0.133

Mar 18, 2025

0.0.132

Mar 18, 2025

0.0.131

Mar 16, 2025

0.0.130

Mar 15, 2025

0.0.129

Mar 15, 2025

0.0.128

Mar 15, 2025

0.0.127

Mar 15, 2025

0.0.126

Mar 14, 2025

0.0.125

Mar 12, 2025

0.0.124

Mar 12, 2025

0.0.123

Mar 12, 2025

This version

0.0.122

Mar 11, 2025

0.0.121

Mar 11, 2025

0.0.120

Mar 10, 2025

0.0.119

Mar 10, 2025

0.0.118

Mar 10, 2025

0.0.116

Mar 10, 2025

0.0.115

Mar 10, 2025

0.0.114

Mar 10, 2025

0.0.113

Mar 3, 2025

0.0.112

Mar 3, 2025

0.0.111

Mar 3, 2025

0.0.110

Mar 3, 2025

0.0.109

Mar 3, 2025

0.0.108

Feb 27, 2025

0.0.107

Feb 27, 2025

0.0.106

Feb 27, 2025

0.0.105

Feb 27, 2025

0.0.104

Feb 27, 2025

0.0.103

Feb 25, 2025

0.0.102

Feb 25, 2025

0.0.101

Feb 25, 2025

0.0.100

Feb 25, 2025

0.0.99

Feb 25, 2025

0.0.98

Feb 25, 2025

0.0.97

Feb 25, 2025

0.0.96

Feb 25, 2025

0.0.95

Feb 24, 2025

0.0.94

Feb 24, 2025

0.0.93

Feb 24, 2025

0.0.92

Feb 18, 2025

0.0.91

Feb 17, 2025

0.0.90

Feb 17, 2025

0.0.89

Feb 14, 2025

0.0.88

Feb 14, 2025

0.0.87

Feb 14, 2025

0.0.86

Feb 14, 2025

0.0.85

Feb 14, 2025

0.0.84

Feb 14, 2025

0.0.83

Feb 14, 2025

0.0.82

Feb 14, 2025

0.0.81

Feb 5, 2025

0.0.80

Feb 5, 2025

0.0.79

Feb 5, 2025

0.0.78

Feb 5, 2025

0.0.77

Feb 5, 2025

0.0.76

Feb 1, 2025

0.0.75

Feb 1, 2025

0.0.74

Feb 1, 2025

0.0.73

Jan 31, 2025

0.0.72

Dec 6, 2024

0.0.71

Dec 6, 2024

0.0.70

Dec 4, 2024

0.0.69

Nov 27, 2024

0.0.68

Nov 25, 2024

0.0.67

Nov 19, 2024

0.0.66

Nov 15, 2024

0.0.65

Nov 14, 2024

0.0.64

Nov 14, 2024

0.0.63

Nov 14, 2024

0.0.62

Nov 14, 2024

0.0.61

Nov 14, 2024

0.0.60

Nov 14, 2024

0.0.59

Nov 14, 2024

0.0.58

Nov 13, 2024

0.0.57

Nov 13, 2024

0.0.56

Nov 13, 2024

0.0.55

Nov 13, 2024

0.0.54

Nov 13, 2024

0.0.53

Nov 13, 2024

0.0.52

Nov 12, 2024

0.0.51

Nov 12, 2024

0.0.50

Nov 12, 2024

0.0.49

Nov 12, 2024

0.0.48

Nov 6, 2024

0.0.47

Nov 4, 2024

0.0.46

Nov 4, 2024

0.0.45

Nov 4, 2024

0.0.44

Nov 2, 2024

0.0.43

Nov 1, 2024

0.0.42

Nov 1, 2024

0.0.41

Oct 25, 2024

0.0.40

Oct 23, 2024

0.0.39

Oct 23, 2024

0.0.38

Oct 22, 2024

0.0.37

Oct 22, 2024

0.0.36

Oct 22, 2024

0.0.35

Oct 22, 2024

0.0.34

Oct 22, 2024

0.0.33

Oct 22, 2024

0.0.32

Oct 22, 2024

0.0.31

Oct 21, 2024

0.0.30

Oct 21, 2024

0.0.29

Oct 21, 2024

0.0.28

Oct 21, 2024

0.0.27

Oct 21, 2024

0.0.26

Oct 17, 2024

0.0.25

Oct 17, 2024

0.0.24

Oct 16, 2024

0.0.23

Oct 16, 2024

0.0.22

Oct 16, 2024

0.0.21

Oct 16, 2024

0.0.20

Oct 16, 2024

0.0.19

Oct 16, 2024

0.0.18

Oct 15, 2024

0.0.17

Oct 15, 2024

0.0.16

Oct 15, 2024

0.0.15

Oct 10, 2024

0.0.14

Oct 10, 2024

0.0.13

Oct 10, 2024

0.0.12

Oct 10, 2024

0.0.11

Oct 10, 2024

0.0.10

Oct 10, 2024

0.0.9

Oct 10, 2024

0.0.8

Oct 10, 2024

0.0.7

Oct 10, 2024

0.0.6

Oct 9, 2024

0.0.5

Oct 9, 2024

0.0.4

Oct 9, 2024

0.0.3

Oct 9, 2024

0.0.2

Oct 9, 2024

0.0.1

Oct 9, 2024

0.0.0

Oct 9, 2024

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

rsp_ml-0.0.122.tar.gz (51.5 kB view details)

Uploaded Mar 11, 2025 Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

rsp_ml-0.0.122-py3-none-any.whl (37.0 kB view details)

Uploaded Mar 11, 2025 Python 3

File details

Details for the file rsp_ml-0.0.122.tar.gz.

File metadata

Download URL: rsp_ml-0.0.122.tar.gz
Upload date: Mar 11, 2025
Size: 51.5 kB
Tags: Source
Uploaded using Trusted Publishing? No
Uploaded via: twine/5.1.1 CPython/3.11.0

File hashes

Hashes for rsp_ml-0.0.122.tar.gz
Algorithm	Hash digest
SHA256	`16f1feef927602affbee0239fbe3daee4b8fbe581502070cea340f9603215d6f`
MD5	`c81c0c5474295cdaca8bf80b84339307`
BLAKE2b-256	`81d6771129d60b7680e1ef2560a1977fc6602cc602e21af330624735ea88cd2d`

See more details on using hashes here.

File details

Details for the file rsp_ml-0.0.122-py3-none-any.whl.

File metadata

Download URL: rsp_ml-0.0.122-py3-none-any.whl
Upload date: Mar 11, 2025
Size: 37.0 kB
Tags: Python 3
Uploaded using Trusted Publishing? No
Uploaded via: twine/5.1.1 CPython/3.11.0

File hashes

Hashes for rsp_ml-0.0.122-py3-none-any.whl
Algorithm	Hash digest
SHA256	`f6875fc855cee1cb101cd7f1db7deb0aa4341efcb2cd3652f08bc745d6cb4548`
MD5	`2ee58e26d89da0cbc40b718c4b590875`
BLAKE2b-256	`99999e64a9ad85b30a9b024bea6d5d1fcf70e2b6226db5be4019ff9f76c7eca3`

See more details on using hashes here.

rsp-ml 0.0.122

Navigation

Verified details

Maintainers

Unverified details

Project links

Meta

Classifiers

Project description

RSProduction MachineLearning

Table of Contents

1 dataset

1.1 HMDB51 : torch.utils.data.dataset.Dataset

1.1.1 __init__

1.2 Kinetics : torch.utils.data.dataset.Dataset

1.2.1 __init__

1.3 TUCRID : torch.utils.data.dataset.Dataset

1.3.1 __init__

1.3.2 get_uniform_sampler

1.3.3 load_backgrounds

1.4 UCF101 : torch.utils.data.dataset.Dataset

1.4.1 __init__

2 metrics

2.1 AUROC

2.2 F1_Score

2.3 FN

2.4 FP

2.5 FPR

2.6 ROC

2.7 TN

2.8 TP

2.9 TPR

2.10 confusion_matrix

2.11 plot_ROC

2.12 plot_confusion_matrix

2.13 precision

2.14 recall

2.15 top_10_accuracy

2.16 top_1_accuracy

2.17 top_2_accuracy

2.18 top_3_accuracy

2.19 top_5_accuracy

2.20 top_k_accuracy

3 model

3.1 MODELS : enum.Enum

3.2 WEIGHTS : enum.Enum

3.3 list_model_weights

3.4 load_model

3.5 publish_model

4 multi_transforms

4.1 BGR2GRAY : MultiTransform

4.1.1 __call__

4.1.2 __init__

4.2 BGR2RGB : MultiTransform

4.2.1 __call__

4.2.2 __init__

4.3 Brightness : MultiTransform

4.3.1 __call__

4.3.2 __init__

4.4 CenterCrop : MultiTransform

4.4.1 __call__

4.4.2 __init__

4.5 Color : MultiTransform

4.5.1 __call__

4.5.2 __init__

4.6 Compose : builtins.object

4.6.1 __call__

4.6.2 __init__

4.7 GaussianNoise : MultiTransform

4.7.1 __call__

4.7.2 __init__

4.8 MultiTransform : builtins.object

4.8.1 __call__

4.8.2 __init__

4.9 Normalize : MultiTransform

4.9.1 __call__

4.9.2 __init__

4.10 RGB2BGR : BGR2RGB

4.10.1 __call__

4.10.2 __init__

1.1.1 init

1.2.1 init

1.3.1 init

1.4.1 init

4.1.1 call

4.1.2 init

4.2.1 call

4.2.2 init

4.3.1 call

4.3.2 init

4.4.1 call

4.4.2 init

4.5.1 call

4.5.2 init

4.6.1 call

4.6.2 init

4.7.1 call

4.7.2 init

4.8.1 call

4.8.2 init

4.9.1 call

4.9.2 init

4.10.1 call

4.10.2 init

4.11.1 call

4.11.2 init

4.12.1 call

4.12.2 init

4.13.1 call

4.13.2 init

4.14.1 call

4.14.2 init

4.15.1 call

4.15.2 init

4.16.1 call

4.16.2 init

4.17.1 call

4.17.2 init

4.18.1 call

4.18.2 init

4.19.1 call

4.19.2 init

4.20.1 call

4.20.2 init

4.21.1 call

4.21.2 init

4.22.1 call

4.22.2 init

4.23.1 call

4.23.2 init

5.1.1 init