File size: 4,061 Bytes
4c65bff |
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 |
import torch
import torch.nn as nn
import torch.optim as optim
import numpy as np
import torch.nn.functional as F
class MLP(nn.Module):
def __init__(self, input_size, hidden_size, num_classes, dropout_prob=0.1):
super(MLP, self).__init__()
self.fc1 = nn.Linear(input_size, hidden_size)
self.relu = nn.ReLU()
self.dropout = nn.Dropout(dropout_prob)
self.fc2 = nn.Linear(hidden_size, num_classes)
def forward(self, x):
out = self.fc1(x)
out = self.relu(out)
out = self.dropout(out)
out = self.fc2(out)
return out
def show_anns(anns, color_code='auto'):
if len(anns) == 0:
return
sorted_anns = sorted(anns, key=(lambda x: x['area']), reverse=True)
ax = plt.gca()
ax.set_autoscale_on(False)
polygons = []
color = []
for ann in sorted_anns:
m = ann['segmentation']
img = np.ones((m.shape[0], m.shape[1], 3))
color_mask = np.random.random((1, 3)).tolist()[0]
if color_code == 'auto':
for i in range(3):
img[:,:,i] = color_mask[i]
elif color_code == 'red':
for i in range(3):
img[:,:,0] = 1
img[:,:,1] = 0
img[:,:,2] = 0
else:
for i in range(3):
img[:,:,0] = 0
img[:,:,1] = 0
img[:,:,2] = 1
return np.dstack((img, m*0.35))
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 ram_show_mask(m):
img = np.ones((m.shape[0], m.shape[1], 3))
color_mask = np.random.random((1, 3)).tolist()[0]
for i in range(3):
img[:,:,0] = 1
img[:,:,1] = 0
img[:,:,2] = 0
return np.dstack((img, m*0.35))
def iou(mask1, mask2):
intersection = np.logical_and(mask1, mask2)
union = np.logical_or(mask1, mask2)
iou_score = np.sum(intersection) / np.sum(union)
return iou_score
def sort_and_deduplicate(sam_masks, iou_threshold=0.8):
# Sort the sam_masks list based on the area value
sorted_masks = sorted(sam_masks, key=lambda x: x['area'], reverse=True)
# Deduplicate masks based on the given iou_threshold
filtered_masks = []
for mask in sorted_masks:
duplicate = False
for filtered_mask in filtered_masks:
if iou(mask['segmentation'], filtered_mask['segmentation']) > iou_threshold:
duplicate = True
break
if not duplicate:
filtered_masks.append(mask)
return filtered_masks
relation_classes = ['over',
'in front of',
'beside',
'on',
'in',
'attached to',
'hanging from',
'on back of',
'falling off',
'going down',
'painted on',
'walking on',
'running on',
'crossing',
'standing on',
'lying on',
'sitting on',
'flying over',
'jumping over',
'jumping from',
'wearing',
'holding',
'carrying',
'looking at',
'guiding',
'kissing',
'eating',
'drinking',
'feeding',
'biting',
'catching',
'picking',
'playing with',
'chasing',
'climbing',
'cleaning',
'playing',
'touching',
'pushing',
'pulling',
'opening',
'cooking',
'talking to',
'throwing',
'slicing',
'driving',
'riding',
'parked on',
'driving on',
'about to hit',
'kicking',
'swinging',
'entering',
'exiting',
'enclosing',
'leaning on',]
|