-
Notifications
You must be signed in to change notification settings - Fork 5
/
Copy pathutils.py
144 lines (115 loc) · 4.93 KB
/
utils.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
import json
import logging
import os
import shutil
import matplotlib.pyplot as plt
import numpy as np
import torch
import cv2
class RunningAverage():
"""A simple class that maintains the running average of a quantity
Example:
```
loss_avg = RunningAverage()
loss_avg.update(2)
loss_avg.update(4)
loss_avg() = 3
```
"""
def __init__(self):
self.steps = 0
self.total = 0
def update(self, val):
self.total += val
self.steps += 1
def __call__(self):
return self.total/float(self.steps)
def set_logger(log_path):
"""Set the logger to log info in terminal and file `log_path`.
In general, it is useful to have a logger so that every output to the terminal is saved
in a permanent file. Here we save it to `model_dir/train.log`.
Example:
```
logging.info("Starting training...")
```
Args:
log_path: (string) where to log
"""
logger = logging.getLogger()
logger.setLevel(logging.INFO)
if not logger.handlers:
# Logging to a file
file_handler = logging.FileHandler(log_path)
file_handler.setFormatter(logging.Formatter('%(asctime)s:%(levelname)s: %(message)s'))
logger.addHandler(file_handler)
# Logging to console
stream_handler = logging.StreamHandler()
stream_handler.setFormatter(logging.Formatter('%(message)s'))
logger.addHandler(stream_handler)
def save_dict_to_json(d, json_path):
"""Saves dict of floats in json file
Args:
d: (dict) of float-castable values (np.float, int, float, etc.)
json_path: (string) path to json file
"""
with open(json_path, 'w') as f:
json.dump(d, f, indent=4)
def save_checkpoint(state, is_best, checkpoint):
"""Saves model and training parameters at checkpoint + 'last.pth.tar'. If is_best==True, also saves
checkpoint + 'best.pth.tar'
Args:
state: (dict) contains model's state_dict, may contain other keys such as epoch, optimizer state_dict
is_best: (bool) True if it is the best model seen till now
checkpoint: (string) folder where parameters are to be saved
"""
filepath = os.path.join(checkpoint, f"epoch{state['epoch']}.pth.tar")
if not os.path.exists(checkpoint):
print("Checkpoint Directory does not exist! Making directory {}".format(checkpoint))
os.mkdir(checkpoint)
else:
print("Checkpoint Directory exists! ")
torch.save(state, filepath)
if is_best:
shutil.copyfile(filepath, os.path.join(checkpoint, 'best.pth.tar'))
def load_checkpoint(checkpoint, model, optimizer=None):
"""Loads model parameters (state_dict) from file_path. If optimizer is provided, loads state_dict of
optimizer assuming it is present in checkpoint.
Args:
checkpoint: (string) filename which needs to be loaded
model: (torch.nn.Module) model for which the parameters are loaded
optimizer: (torch.optim) optional: resume optimizer from checkpoint
"""
if not os.path.exists(checkpoint):
raise("File doesn't exist {}".format(checkpoint))
checkpoint = torch.load(checkpoint)
model.load_state_dict(checkpoint['state_dict'])
if optimizer:
optimizer.load_state_dict(checkpoint['optim_dict'])
return checkpoint
# https://github.com/albu/albumentations/blob/master/notebooks/example_bboxes.ipynb
# Functions to visualize bounding boxes and class labels on an image.
# Based on https://github.com/facebookresearch/Detectron/blob/master/detectron/utils/vis.py
BOX_COLOR = {0:(255, 0, 0), 1:(0, 255, 0)}
TEXT_COLOR = (255, 255, 255)
# Available formats are: coco, pascal_voc.
# The coco format of a bounding box looks like [x_min, y_min, width, height], e.g. [97, 12, 150, 200].
# The pascal_voc format of a bounding box looks like [x_min, y_min, x_max, y_max], e.g. [97, 12, 247, 212].
def visualize_bbox(img, bbox, class_id, class_idx_to_name, color=BOX_COLOR, thickness=2, pascal=True):
if pascal:
x_min, x_max, y_min, y_max = bbox
else:
x_min, y_min, w, h = bbox
x_min, x_max, y_min, y_max = int(x_min), int(x_min + w), int(y_min), int(y_min + h)
boxcolor = BOX_COLOR[class_id]
cv2.rectangle(img, (x_min, y_min), (x_max, y_max), color=boxcolor, thickness=thickness)
class_name = class_idx_to_name[class_id]
((text_width, text_height), _) = cv2.getTextSize(class_name, cv2.FONT_HERSHEY_SIMPLEX, 0.35, 1)
cv2.rectangle(img, (x_min, y_min - int(1.3 * text_height)), (x_min + text_width, y_min), boxcolor, -1)
cv2.putText(img, class_name, (x_min, y_min - int(0.3 * text_height)), cv2.FONT_HERSHEY_SIMPLEX, 0.35,TEXT_COLOR, lineType=cv2.LINE_AA)
return img
def visualize(annotations, category_id_to_name):
img = annotations['image'].copy()
for idx, bbox in enumerate(annotations['bboxes']):
img = visualize_bbox(img, bbox, annotations['category_id'][idx], category_id_to_name)
plt.figure(figsize=(12, 12))
plt.imshow(img)