File size: 6,559 Bytes
556d554
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
import io
import matplotlib.pyplot as plt
import requests
import inflect
from PIL import Image

def load_image_from_url(url):
    return Image.open(requests.get(url, stream=True).raw)

def render_results_in_image(in_pil_img, in_results):
    plt.figure(figsize=(16, 10))
    plt.imshow(in_pil_img)

    ax = plt.gca()

    for prediction in in_results:

        x, y = prediction['box']['xmin'], prediction['box']['ymin']
        w = prediction['box']['xmax'] - prediction['box']['xmin']
        h = prediction['box']['ymax'] - prediction['box']['ymin']

        ax.add_patch(plt.Rectangle((x, y),
                                   w,
                                   h,
                                   fill=False,
                                   color="green",
                                   linewidth=2))
        ax.text(
           x,
           y,
           f"{prediction['label']}: {round(prediction['score']*100, 1)}%",
           color='red'
        )

    plt.axis("off")

    # Save the modified image to a BytesIO object
    img_buf = io.BytesIO()
    plt.savefig(img_buf, format='png',
                bbox_inches='tight',
                pad_inches=0)
    img_buf.seek(0)
    modified_image = Image.open(img_buf)

    # Close the plot to prevent it from being displayed
    plt.close()

    return modified_image

def summarize_predictions_natural_language(predictions):
    summary = {}
    p = inflect.engine()

    for prediction in predictions:
        label = prediction['label']
        if label in summary:
            summary[label] += 1
        else:
            summary[label] = 1

    result_string = "In this image, there are "
    for i, (label, count) in enumerate(summary.items()):
        count_string = p.number_to_words(count)
        result_string += f"{count_string} {label}"
        if count > 1:
          result_string += "s"

        result_string += " "

        if i == len(summary) - 2:
          result_string += "and "

    # Remove the trailing comma and space
    result_string = result_string.rstrip(', ') + "."

    return result_string


##### To ignore warnings #####
import warnings
import logging
from transformers import logging as hf_logging

def ignore_warnings():
    # Ignore specific Python warnings
    warnings.filterwarnings("ignore", message="Some weights of the model checkpoint")
    warnings.filterwarnings("ignore", message="Could not find image processor class")
    warnings.filterwarnings("ignore", message="The `max_size` parameter is deprecated")

    # Adjust logging for libraries using the logging module
    logging.basicConfig(level=logging.ERROR)
    hf_logging.set_verbosity_error()

########

import numpy as np
import torch
import matplotlib.pyplot as plt

def show_mask(mask, ax, random_color=False):
    if random_color:
        color = np.concatenate([np.random.random(3),
                                np.array([0.6])],
                               axis=0)
    else:
        color = np.array([30/255, 144/255, 255/255, 0.6])
    h, w = mask.shape[-2:]
    mask_image = mask.reshape(h, w, 1) * color.reshape(1, 1, -1)
    ax.imshow(mask_image)


def show_box(box, ax):
    x0, y0 = box[0], box[1]
    w, h = box[2] - box[0], box[3] - box[1]
    ax.add_patch(plt.Rectangle((x0, y0),
                               w,
                               h, edgecolor='green',
                               facecolor=(0,0,0,0),
                               lw=2))

def show_boxes_on_image(raw_image, boxes):
    plt.figure(figsize=(10,10))
    plt.imshow(raw_image)
    for box in boxes:
      show_box(box, plt.gca())
    plt.axis('on')
    plt.show()

def show_points_on_image(raw_image, input_points, input_labels=None):
    plt.figure(figsize=(10,10))
    plt.imshow(raw_image)
    input_points = np.array(input_points)
    if input_labels is None:
      labels = np.ones_like(input_points[:, 0])
    else:
      labels = np.array(input_labels)
    show_points(input_points, labels, plt.gca())
    plt.axis('on')
    plt.show()

def show_points_and_boxes_on_image(raw_image,
                                   boxes,
                                   input_points,
                                   input_labels=None):
    plt.figure(figsize=(10,10))
    plt.imshow(raw_image)
    input_points = np.array(input_points)
    if input_labels is None:
      labels = np.ones_like(input_points[:, 0])
    else:
      labels = np.array(input_labels)
    show_points(input_points, labels, plt.gca())
    for box in boxes:
      show_box(box, plt.gca())
    plt.axis('on')
    plt.show()


def show_points_and_boxes_on_image(raw_image,
                                   boxes,
                                   input_points,
                                   input_labels=None):
    plt.figure(figsize=(10,10))
    plt.imshow(raw_image)
    input_points = np.array(input_points)
    if input_labels is None:
      labels = np.ones_like(input_points[:, 0])
    else:
      labels = np.array(input_labels)
    show_points(input_points, labels, plt.gca())
    for box in boxes:
      show_box(box, plt.gca())
    plt.axis('on')
    plt.show()


def show_points(coords, labels, ax, marker_size=375):
    pos_points = coords[labels==1]
    neg_points = coords[labels==0]
    ax.scatter(pos_points[:, 0],
               pos_points[:, 1],
               color='green',
               marker='*',
               s=marker_size,
               edgecolor='white',
               linewidth=1.25)
    ax.scatter(neg_points[:, 0],
               neg_points[:, 1],
               color='red',
               marker='*',
               s=marker_size,
               edgecolor='white',
               linewidth=1.25)


def fig2img(fig):
    """Convert a Matplotlib figure to a PIL Image and return it"""
    import io
    buf = io.BytesIO()
    fig.savefig(buf)
    buf.seek(0)
    img = Image.open(buf)
    return img


def show_mask_on_image(raw_image, mask, return_image=False):
    if not isinstance(mask, torch.Tensor):
      mask = torch.Tensor(mask)

    if len(mask.shape) == 4:
      mask = mask.squeeze()

    fig, axes = plt.subplots(1, 1, figsize=(15, 15))

    mask = mask.cpu().detach()
    axes.imshow(np.array(raw_image))
    show_mask(mask, axes)
    axes.axis("off")
    plt.show()

    if return_image:
      fig = plt.gcf()
      return fig2img(fig)

def show_pipe_masks_on_image(raw_image, outputs):
  plt.imshow(np.array(raw_image))
  ax = plt.gca()
  for mask in outputs["masks"]:
      show_mask(mask, ax=ax, random_color=True)
  plt.axis("off")
  plt.show()