Spaces:
Sleeping
Sleeping
File size: 5,639 Bytes
281df87 |
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 |
CKPTS = [
dict(
path="/home/chunyl/azure_mount/yuhengdb/fine_tune_ldm/version5_branch6_output/GoldG+SBU+CC3M+CC12M+O365/second_stage_drop_both/tag01/checkpoint_00450001.pth",
feature_type=['before','after_reproject'],
save_folder_name="v5b6_drop_both",
),
# dict(
# path="/home/v-yuhengli/blobfuse/output/fine_tune_ldm/version5_branch6_output/GoldG+SBU+CC3M+CC12M+O365/second_stage_drop_none/tag00/checkpoint_00165001.pth",
# feature_type=['before','after_reproject'],
# save_folder_name="v5b6_drop_none",
# ),
]
# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = #
# if meta["has_image_mask"] == 0:
# image_embeddings = text_embeddings
# if meta["has_text_mask"] == 0:
# text_embeddings = image_embeddings
# out = {
# "boxes" : boxes.unsqueeze(0).repeat(batch,1,1),
# "masks" : masks.unsqueeze(0).repeat(batch,1),
# "text_masks" : masks.unsqueeze(0).repeat(batch,1),
# "image_masks" : masks.unsqueeze(0).repeat(batch,1),
# "text_embeddings" : text_embeddings.unsqueeze(0).repeat(batch,1,1),
# "image_embeddings" : image_embeddings.unsqueeze(0).repeat(batch,1,1)
# }
META = [
dict(
prompt = "a teddy bear sitting next to a red bird",
phrases = ['a teddy bear', 'a red bird'],
images = ['images/teddy.jpg', 'images/red_bird.jpg'],
locations = [ [0.0,0.09,0.33,0.76], [0.55,0.11,1.0,0.8] ],
alpha_type = [1.0, 0, 0.0],
has_text_mask = 1,
has_image_mask = 0,
save_folder_name="teddy_bird_1_1"
),
# dict(
# prompt = "a teddy bear sitting next to a bird",
# phrases = ['a teddy bear', 'a bird'],
# images = ['images/teddy.jpg', 'images/red_bird.jpg'],
# locations = [ [0.0,0.09,0.33,0.76], [0.55,0.11,1.0,0.8] ],
# alpha_type = [1.0, 0, 0.0],
# has_text_mask = 1,
# has_image_mask = 1,
# save_folder_name="teddy_bird_1_1"
# ),
# dict(
# prompt = "a teddy bear sitting next to a bird",
# phrases = ['a teddy bear', 'a bird'],
# images = ['images/teddy.jpg', 'images/red_bird.jpg'],
# locations = [ [0.0,0.09,0.33,0.76], [0.55,0.11,1.0,0.8] ],
# alpha_type = [0.5, 0, 0.5],
# has_text_mask = 1,
# has_image_mask = 0,
# save_folder_name="teddy_bird_1_0"
# ),
# dict(
# prompt = "",
# phrases = ['a teddy bear', 'an umbrella'],
# images = ['images/teddy.jpg', 'images/umbrella.png'],
# locations = [ [0.0,0.09,0.33,0.76], [0.55,0.11,1.0,0.8] ],
# alpha_type = [1.0, 0, 0.0],
# has_text_mask = 1,
# has_image_mask = 1,
# save_folder_name="empty_teddy_umbrella_1_1"
# ),
# dict(
# prompt = "hello kitty and bird hybrid",
# phrases = ['a hello kitty', 'a hello kitty'],
# images = ['images/red_bird.jpg', 'images/red_bird.jpg'],
# locations = [ [0.0,0.09,0.33,0.76], [0.55,0.11,1.0,0.8] ],
# has_text_mask = 1,
# has_image_mask = 1,
# save_folder_name="hello+bird_1_1"
# ),
# dict(
# prompt = "hello kitty and teddy bear hybrid",
# phrases = ['a hello kitty', 'a hello kitty'],
# images = ['images/teddy.jpg', 'images/teddy.jpg'],
# locations = [ [0.0,0.09,0.33,0.76], [0.55,0.11,1.0,0.8] ],
# has_text_mask = 1,
# has_image_mask = 1,
# save_folder_name="hello+teddy_1_1"
# ),
# dict(
# prompt = "bird and hello kitty hybrid",
# phrases = ['a bird', 'a bird'],
# images = ['images/hello.jpg', 'images/hello.jpg'],
# locations = [ [0.0,0.09,0.33,0.76], [0.55,0.11,1.0,0.8] ],
# alpha_type = [1.0, 0, 0.0],
# has_text_mask = 1,
# has_image_mask = 0.5,
# save_folder_name="bird+hello_1_1"
# ),
# dict(
# prompt = "a deer standing in front of a brick house in the woods, anime, oil painting, high resolution, cottagecore, ghibli inspired, 4k",
# phrases = ['a deer'],
# images = ['images/sky.jpg'],
# locations = [ [0.0,0.5,0.5,0.9] ],
# alpha_type = [1, 0, 0],
# has_text_mask = 1,
# has_image_mask = 1,
# save_folder_name="deer_sky"
# ),
# dict(
# prompt = "A woman sitting in a restaurant with a slice of pizza in front of her",
# phrases = ['dining table', 'pizza', 'person', 'wall', 'car', 'paper', 'chair', 'window', 'bottle', 'cup'],
# images = ['images/hello.jpg','images/hello.jpg','images/hello.jpg','images/hello.jpg','images/hello.jpg','images/hello.jpg','images/hello.jpg','images/hello.jpg','images/hello.jpg','images/hello.jpg'],
# locations = [ [0.0030, 0.3589, 1.0000, 1.0000],
# [0.0779, 0.6744, 0.9768, 1.0000],
# [0.2236, 0.0000, 0.7809, 0.4352],
# [0.0000, 0.0000, 0.4313, 0.4505],
# [0.6275, 0.1050, 0.9444, 0.2497],
# [0.0000, 0.3859, 0.1250, 0.6922],
# [0.7137, 0.2389, 0.8540, 0.4549],
# [0.0000, 0.0000, 0.4667, 0.0630],
# [0.3822, 0.4235, 0.4932, 0.6575],
# [0.6616, 0.3617, 0.7880, 0.5165] ],
# alpha_type = [0.0, 0, 1.0],
# has_text_mask = 1,
# has_image_mask = 0,
# save_folder_name="pizza_1_0"
# ),
] |