rsp-ml 0.0.69

Machine Learning

RSProduction MachineLearning

This project provides some usefull machine learning functionality.

Table of Contents

• 1 metrics
  • 1.1 AUROC
  • 1.2 F1_Score
  • 1.3 FN
  • 1.4 FP
  • 1.5 FPR
  • 1.6 ROC
  • 1.7 TN
  • 1.8 TP
  • 1.9 TPR
  • 1.10 confusion_matrix
  • 1.11 plot_ROC
  • 1.12 plot_confusion_matrix
  • 1.13 precision
  • 1.14 recall
  • 1.15 top_10_accuracy
  • 1.16 top_1_accuracy
  • 1.17 top_2_accuracy
  • 1.18 top_3_accuracy
  • 1.19 top_5_accuracy
  • 1.20 top_k_accuracy
• 2 model
  • 2.2 Constants
  • 2.1 load_model
• 3 multi_transforms
  • 3.1 BGR2GRAY : MultiTransform
    • 3.1.1 __call__
    • 3.1.2 __init__
  • 3.2 BGR2RGB : MultiTransform
    • 3.2.1 __call__
    • 3.2.2 __init__
  • 3.3 Brightness : MultiTransform
    • 3.3.1 __call__
    • 3.3.2 __init__
  • 3.4 CenterCrop : MultiTransform
    • 3.4.1 __call__
    • 3.4.2 __init__
  • 3.5 Color : MultiTransform
    • 3.5.1 __call__
    • 3.5.2 __init__
  • 3.6 Compose : builtins.object
    • 3.6.1 __call__
    • 3.6.2 __init__
  • 3.7 GaussianNoise : MultiTransform
    • 3.7.1 __call__
    • 3.7.2 __init__
  • 3.8 MultiTransform : builtins.object
    • 3.8.1 __call__
    • 3.8.2 __init__
  • 3.9 Normalize : MultiTransform
    • 3.9.1 __call__
    • 3.9.2 __init__
  • 3.10 RGB2BGR : BGR2RGB
    • 3.10.1 __call__
    • 3.10.2 __init__
  • 3.11 RandomCrop : MultiTransform
    • 3.11.1 __call__
    • 3.11.2 __init__
  • 3.12 RandomHorizontalFlip : MultiTransform
    • 3.12.1 __call__
    • 3.12.2 __init__
  • 3.13 RandomVerticalFlip : MultiTransform
    • 3.13.1 __call__
    • 3.13.2 __init__
  • 3.14 Resize : MultiTransform
    • 3.14.1 __call__
    • 3.14.2 __init__
  • 3.15 Rotate : MultiTransform
    • 3.15.1 __call__
    • 3.15.2 __init__
  • 3.16 Satturation : MultiTransform
    • 3.16.1 __call__
    • 3.16.2 __init__
  • 3.17 Scale : MultiTransform
    • 3.17.1 __call__
    • 3.17.2 __init__
  • 3.18 Stack : MultiTransform
    • 3.18.1 __call__
    • 3.18.2 __init__
  • 3.19 ToCVImage : MultiTransform
    • 3.19.1 __call__
    • 3.19.2 __init__
  • 3.20 ToNumpy : MultiTransform
    • 3.20.1 __call__
    • 3.20.2 __init__
  • 3.21 ToPILImage : MultiTransform
    • 3.21.1 __call__
    • 3.21.2 __init__
  • 3.22 ToTensor : MultiTransform
    • 3.22.1 __call__
    • 3.22.2 __init__
• 4 run
  • 4.1 Run : builtins.object
    • 4.1.1 __init__
    • 4.1.2 append
    • 4.1.3 get_avg
    • 4.1.4 get_val
    • 4.1.5 len
    • 4.1.6 load_best_state_dict
    • 4.1.7 load_state_dict
    • 4.1.8 pickle_dump
    • 4.1.9 pickle_load
    • 4.1.10 plot
    • 4.1.11 recalculate_moving_average
    • 4.1.12 save
    • 4.1.13 save_best_state_dict
    • 4.1.14 save_state_dict

1 metrics

TOC

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

1.1 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

1.2 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

1.3 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

1.4 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

1.5 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

1.6 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)

1.7 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

1.8 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

1.9 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

1.10 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]
])

1.11 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

1.12 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

1.13 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

1.14 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

1.15 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

1.16 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

1.17 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

1.18 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

1.19 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

1.20 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

2 model

TOC

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

2.2 Constants

TOC

Name	Value	Description
TUC_ActionPrediction_model004	TUC/ActionPrediction/Model4	TUC Action prediction model 4 CNN with Multihead-Self-Attention Input - batch size - sequence length = 30 - channels = 3 - width = 200 - height = 200 Output - batch size - number of classes = 10
TUC_ActionPrediction_model005	TUC/ActionPrediction/Model5	TUC Action prediction model 5 CNN with Multihead-Self-Attention Input - batch size - sequence length = 30 - channels = 3 - width = 300 - height = 300 Output - batch size - number of classes = 10
URL	https://drive.google.com/drive/folders/1ulNnPqg-5wvenRl2CuJMxMMcaiYfHjQ9?usp=share_link	Google Drive URL

2.1 load_model

TOC

Description

Loads a model from an pretrained PyTorch external source into memory.

See Constants for available models

Parameters

Name	Type	Description
model_id	str	ID of the model
force_reload	bool	Overwrite local file -> forces downlad.

Returns

Pretrained PyTorch model : torch.nn.Module

Example

import rsp.ml.model as model

model004 = model.load_model(model.TUC_ActionPrediction_model004)

3 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.

3.1 BGR2GRAY : MultiTransform

TOC

Description

Converts a sequence of BGR images to grayscale images.

3.1.1 __call__

TOC

Description

Call self as a function.

Parameters

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

3.1.2 __init__

TOC

Description

Initializes a new instance.

3.2 BGR2RGB : MultiTransform

TOC

Description

Converts sequence of BGR images to RGB images.

3.2.1 __call__

TOC

Description

Call self as a function.

Parameters

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

3.2.2 __init__

TOC

Description

Initializes a new instance.

3.3 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.

3.3.1 __call__

TOC

Description

Call self as a function.

Parameters

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

3.3.2 __init__

TOC

Description

Initializes a new instance.

3.4 CenterCrop : MultiTransform

TOC

Description

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

3.4.1 __call__

TOC

Description

Call self as a function.

Parameters

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

3.4.2 __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.

3.5 Color : 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.

3.5.1 __call__

TOC

Description

Call self as a function.

Parameters

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

3.5.2 __init__

TOC

Description

Initializes a new instance.

3.6 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)
])

3.6.1 __call__

TOC

Description

Call self as a function.

3.6.2 __init__

TOC

Description

Initializes a new instance.

Parameters

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

3.7 GaussianNoise : 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.

3.7.1 __call__

TOC

Description

Call self as a function.

Parameters

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

3.7.2 __init__

TOC

Description

Initializes a new instance.

3.8 MultiTransform : builtins.object

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.

3.8.1 __call__

TOC

Description

Call self as a function.

Parameters

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

3.8.2 __init__

TOC

Description

Initializes a new instance.

3.9 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

3.9.1 __call__

TOC

Description

Call self as a function.

Parameters

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

3.9.2 __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.

3.10 RGB2BGR : BGR2RGB

TOC

Description

Converts sequence of RGB images to BGR images.

3.10.1 __call__

TOC

Description

Call self as a function.

Parameters

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

3.10.2 __init__

TOC

Description

Initializes a new instance.

3.11 RandomCrop : MultiTransform

TOC

Description

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

3.11.1 __call__

TOC

Description

Call self as a function.

Parameters

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

3.11.2 __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.

3.12 RandomHorizontalFlip : 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.

3.12.1 __call__

TOC

Description

Call self as a function.

Parameters

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

3.12.2 __init__

TOC

Description

Initializes a new instance.

3.13 RandomVerticalFlip : 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.

3.13.1 __call__

TOC

Description

Call self as a function.

Parameters

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

3.13.2 __init__

TOC

Description

Initializes a new instance.

3.14 Resize : 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.

3.14.1 __call__

TOC

Description

Call self as a function.

Parameters

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

3.14.2 __init__

TOC

Description

Initializes a new instance.

3.15 Rotate : MultiTransform

TOC

Description

Randomly rotates images.

Equations

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

3.15.1 __call__

TOC

Description

Call self as a function.

Parameters

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

3.15.2 __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.

3.16 Satturation : 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.

3.16.1 __call__

TOC

Description

Call self as a function.

Parameters

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

3.16.2 __init__

TOC

Description

Initializes a new instance.

3.17 Scale : 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.

3.17.1 __call__

TOC

Description

Call self as a function.

Parameters

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

3.17.2 __init__

TOC

Description

Initializes a new instance.

3.18 Stack : 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.

3.18.1 __call__

TOC

Description

Call self as a function.

Parameters

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

3.18.2 __init__

TOC

Description

Initializes a new instance.

3.19 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.

3.19.1 __call__

TOC

Description

Call self as a function.

Parameters

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

3.19.2 __init__

TOC

Description

Initializes a new instance.

3.20 ToNumpy : MultiTransform

TOC

Description

Converts a torch.Tensorto numpy

3.20.1 __call__

TOC

Description

Call self as a function.

Parameters

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

3.20.2 __init__

TOC

Description

Initializes a new instance.

3.21 ToPILImage : MultiTransform

TOC

Description

Converts sequence of images to sequence of PIL.Image.

3.21.1 __call__

TOC

Description

Call self as a function.

Parameters

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

3.21.2 __init__

TOC

Description

Initializes a new instance.

3.22 ToTensor : MultiTransform

TOC

Description

Converts a sequence of images to torch.Tensor.

3.22.1 __call__

TOC

Description

Call self as a function.

Parameters

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

3.22.2 __init__

TOC

Description

Initializes a new instance.

4 run

TOC

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

4.1 Run : builtins.object

TOC

4.1.1 __init__

TOC

Description

Initialize self. See help(type(self)) for accurate signature.

4.1.2 append

TOC

4.1.3 get_avg

TOC

4.1.4 get_val

TOC

4.1.5 len

TOC

4.1.6 load_best_state_dict

TOC

4.1.7 load_state_dict

TOC

4.1.8 pickle_dump

TOC

4.1.9 pickle_load

TOC

4.1.10 plot

TOC

4.1.11 recalculate_moving_average

TOC

4.1.12 save

TOC

4.1.13 save_best_state_dict

TOC

4.1.14 save_state_dict

TOC