def __init__(self, args):
action_space = args.action_space
hidden_state_sz = args.hidden_state_sz
super(MJOLNIR_O, self).__init__()
# get and normalize adjacency matrix.
np.seterr(divide='ignore')
A_raw = torch.load("./data/gcn/adjmat.dat")
A = normalize_adj(A_raw).tocsr().toarray()
self.A = torch.nn.Parameter(torch.Tensor(A))
n = int(A.shape[0])
self.n = n
self.embed_action = nn.Linear(action_space, 10)
lstm_input_sz = 10 + n * 5 + 512
self.hidden_state_sz = hidden_state_sz
self.lstm = nn.LSTMCell(lstm_input_sz, hidden_state_sz)
num_outputs = action_space
self.critic_linear = nn.Linear(hidden_state_sz, 1)
self.actor_linear = nn.Linear(hidden_state_sz, num_outputs)
self.apply(weights_init)
relu_gain = nn.init.calculate_gain("relu")
self.actor_linear.weight.data = norm_col_init(
self.actor_linear.weight.data, 0.01)
self.actor_linear.bias.data.fill_(0)
self.critic_linear.weight.data = norm_col_init(
self.critic_linear.weight.data, 1.0)
self.critic_linear.bias.data.fill_(0)
self.lstm.bias_ih.data.fill_(0)
self.lstm.bias_hh.data.fill_(0)
self.action_predict_linear = nn.Linear(2 * lstm_input_sz, action_space)
self.dropout = nn.Dropout(p=args.dropout_rate)
# glove embeddings for all the objs.
with open("./data/gcn/objects.txt") as f:
objects = f.readlines()
self.objects = [o.strip() for o in objects]
all_glove = torch.zeros(n, 300)
glove = Glove(args.glove_file)
for i in range(n):
all_glove[i, :] = torch.Tensor(
glove.glove_embeddings[self.objects[i]][:])
self.all_glove = nn.Parameter(all_glove)
self.all_glove.requires_grad = False
self.W0 = nn.Linear(401, 401, bias=False)
self.W1 = nn.Linear(401, 401, bias=False)
self.W2 = nn.Linear(401, 5, bias=False)
self.W3 = nn.Linear(10, 1, bias=False)
self.final_mapping = nn.Linear(n, 512)
def __init__(self, args):
action_space = args.action_space
target_embedding_sz = args.target_dim
resnet_embedding_sz = args.hidden_state_sz
hidden_state_sz = args.hidden_state_sz
super(BaseModel, self).__init__()
self.conv1 = nn.Conv2d(
resnet_embedding_sz, 64,
1) # Conv2d(512, 64, kernel_size=(1, 1), stride=(1, 1))
self.maxp1 = nn.MaxPool2d(
2, 2
) # MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
self.embed_glove = nn.Linear(
target_embedding_sz,
64) # Linear(in_features=300, out_features=64, bias=True)
self.embed_action = nn.Linear(
action_space,
10) # Linear(in_features=7, out_features=10, bias=True)
pointwise_in_channels = 138
self.pointwise = nn.Conv2d(
pointwise_in_channels, 64, 1,
1) # Conv2d(138, 64, kernel_size=(1, 1), stride=(1, 1))
lstm_input_sz = 7 * 7 * 64
self.hidden_state_sz = hidden_state_sz
self.lstm = nn.LSTMCell(lstm_input_sz,
hidden_state_sz) # LSTMCell(3136, 512)
num_outputs = action_space
self.critic_linear = nn.Linear(
hidden_state_sz,
1) #Linear(in_features=512, out_features=1, bias=True)
self.actor_linear = nn.Linear(
hidden_state_sz,
num_outputs) # Linear(in_features=6272, out_features=7, bias=True)
self.apply(weights_init)
relu_gain = nn.init.calculate_gain("relu")
self.conv1.weight.data.mul_(relu_gain)
self.actor_linear.weight.data = norm_col_init(
self.actor_linear.weight.data, 0.01)
self.actor_linear.bias.data.fill_(0)
self.critic_linear.weight.data = norm_col_init(
self.critic_linear.weight.data, 1.0)
self.critic_linear.bias.data.fill_(0)
self.lstm.bias_ih.data.fill_(0)
self.lstm.bias_hh.data.fill_(0)
self.action_predict_linear = nn.Linear(2 * lstm_input_sz, action_space)
self.dropout = nn.Dropout(p=args.dropout_rate)
def __init__(self, args):
action_space = args.action_space
# target_embedding_sz = args.target_dim
resnet_embedding_sz = args.hidden_state_sz
hidden_state_sz = args.hidden_state_sz
super(ProtoModel, self).__init__()
# self.conv1 = nn.Conv2d(resnet_embedding_sz, 64, 1) # Conv2d(512, 64, kernel_size=(1, 1), stride=(1, 1))
self.conv1 = nn.Sequential(
nn.Conv2d(resnet_embedding_sz, 64, kernel_size=1),
nn.BatchNorm2d(64, momentum=1, affine=True), nn.ReLU())
self.fusion_block = nn.Sequential(
nn.Conv2d(fusion_channels, 64,
kernel_size=match_block_kernel_size),
nn.BatchNorm2d(64, momentum=1, affine=True),
nn.ReLU()) # [64, 5,5]/[64, 7, 7]
self.embed_action = nn.Linear(
action_space, action_channels
) # Linear(in_features=7, out_features=10, bias=True)
# pointwise_in_channels = 64 + 10
#
# self.pointwise = nn.Conv2d(pointwise_in_channels, 64, 1, 1) # Conv2d(138, 64, kernel_size=(1, 1), stride=(1, 1))
lstm_input_sz = feature_map_size * feature_map_size * 64
self.hidden_state_sz = hidden_state_sz
self.lstm = nn.LSTMCell(lstm_input_sz,
hidden_state_sz) # LSTMCell(1600, 512)
num_outputs = action_space
self.critic_linear = nn.Linear(
hidden_state_sz,
1) #Linear(in_features=512, out_features=1, bias=True)
self.actor_linear = nn.Linear(
hidden_state_sz,
num_outputs) # Linear(in_features=6272, out_features=7, bias=True)
self.apply(weights_init)
# relu_gain = nn.init.calculate_gain("relu")
# self.conv1.weight.data.mul_(relu_gain)
self.actor_linear.weight.data = norm_col_init(
self.actor_linear.weight.data, 0.01)
self.actor_linear.bias.data.fill_(0)
self.critic_linear.weight.data = norm_col_init(
self.critic_linear.weight.data, 1.0)
self.critic_linear.bias.data.fill_(0)
self.lstm.bias_ih.data.fill_(0)
self.lstm.bias_hh.data.fill_(0)
# self.action_predict_linear = nn.Linear(2 * lstm_input_sz, action_space)
self.dropout = nn.Dropout(p=args.dropout_rate)
def __init__(self, args):
action_space = args.action_space
target_embedding_sz = args.glove_dim
resnet_embedding_sz = args.hidden_state_sz
hidden_state_sz = args.hidden_state_sz
resnet_embedding_sz = 512
hidden_state_sz = 512
super(GcnBaseModel, self).__init__()
self.conv1 = nn.Conv2d(resnet_embedding_sz, 64, 1)
self.maxp1 = nn.MaxPool2d(2, 2)
self.embed_glove = nn.Linear(target_embedding_sz, 64)
self.embed_action = nn.Linear(action_space, 10)
# GCN layer
self.gcn_size = 64
self.gcn = GCN()
self.gcn_embed = nn.Linear(512, self.gcn_size)#也可以考虑把512reshape成三维tensor后点卷积
pointwise_in_channels = 138 + self.gcn_size
self.pointwise = nn.Conv2d(pointwise_in_channels, 64, 1, 1)
lstm_input_sz = 7 * 7 * 64
self.hidden_state_sz = hidden_state_sz
self.lstm = nn.LSTMCell(lstm_input_sz, hidden_state_sz)
num_outputs = action_space
self.critic_linear = nn.Linear(hidden_state_sz, 1)
self.actor_linear = nn.Linear(hidden_state_sz, num_outputs)
self.apply(weights_init)
relu_gain = nn.init.calculate_gain("relu")
self.conv1.weight.data.mul_(relu_gain)
self.actor_linear.weight.data = norm_col_init(
self.actor_linear.weight.data, 0.01
)
self.actor_linear.bias.data.fill_(0)
self.critic_linear.weight.data = norm_col_init(
self.critic_linear.weight.data, 1.0
)
self.critic_linear.bias.data.fill_(0)
self.lstm.bias_ih.data.fill_(0)
self.lstm.bias_hh.data.fill_(0)
#self.action_predict_linear = nn.Linear(2 * lstm_input_sz, action_sz)
self.dropout = nn.Dropout(p=args.dropout_rate)
def __init__(self, args):
action_space = args.action_space
target_embedding_sz = args.glove_dim
resnet_embedding_sz = 512
hidden_state_sz = args.hidden_state_sz
super(GCN_MLP, self).__init__()
self.conv1 = nn.Conv2d(resnet_embedding_sz, 64, 1)
self.maxp1 = nn.MaxPool2d(2, 2)
self.embed_glove = nn.Linear(target_embedding_sz, 64)
self.embed_action = nn.Linear(action_space, 10)
pointwise_in_channels = 138
self.pointwise = nn.Conv2d(pointwise_in_channels, 64, 1, 1)
lstm_input_sz = 7 * 7 * 64 + 512
mlp_input_sz = lstm_input_sz
self.hidden_state_sz = hidden_state_sz
num_outputs = action_space
self.critic_linear = nn.Linear(hidden_state_sz, 1)
self.actor_linear = nn.Linear(hidden_state_sz, num_outputs)
self.apply(weights_init)
relu_gain = nn.init.calculate_gain("relu")
self.conv1.weight.data.mul_(relu_gain)
self.actor_linear.weight.data = norm_col_init(
self.actor_linear.weight.data, 0.01)
self.actor_linear.bias.data.fill_(0)
self.critic_linear.weight.data = norm_col_init(
self.critic_linear.weight.data, 1.0)
self.critic_linear.bias.data.fill_(0)
self.action_predict_linear = nn.Linear(2 * lstm_input_sz, action_space)
self.dropout = nn.Dropout(p=args.dropout_rate)
n = 83
self.n = n
# get and normalize adjacency matrix.
A_raw = torch.load("./data/gcn/adjmat.dat")
A = normalize_adj(A_raw).tocsr().toarray()
self.A = torch.nn.Parameter(torch.Tensor(A))
# last layer of resnet18.
resnet18 = models.resnet18(pretrained=True)
modules = list(resnet18.children())[-2:]
self.resnet18 = nn.Sequential(*modules)
for p in self.resnet18.parameters():
p.requires_grad = False
# glove embeddings for all the objs.
objects = open("./data/gcn/objects.txt").readlines()
objects = [o.strip() for o in objects]
all_glove = torch.zeros(n, 300)
glove = Glove(args.glove_file)
for i in range(n):
all_glove[i, :] = torch.Tensor(
glove.glove_embeddings[objects[i]][:])
self.all_glove = nn.Parameter(all_glove)
self.all_glove.requires_grad = False
self.get_word_embed = nn.Linear(300, 512)
self.get_class_embed = nn.Linear(1000, 512)
self.W0 = nn.Linear(1024, 1024, bias=False)
self.W1 = nn.Linear(1024, 1024, bias=False)
self.W2 = nn.Linear(1024, 1, bias=False)
self.final_mapping = nn.Linear(n, 512)
hidden_o = mlp_input_sz // 2
self.W0m = nn.Linear(mlp_input_sz, 512, bias=False)
def __init__(self, args):
action_space = args.action_space
# target_embedding_sz = args.glove_dim
target_embedding_sz = 95
resnet_embedding_sz = args.hidden_state_sz
hidden_state_sz = args.hidden_state_sz
super(BaseModel, self).__init__()
self.conv1 = nn.Conv2d(resnet_embedding_sz, 64, 1)
self.maxp1 = nn.MaxPool2d(2, 2)
# self.embed_glove = nn.Linear(19*262, 64*7*7)
# self.embed_glove = nn.Linear(target_embedding_sz, 64)
# self.embed_glove = nn.Conv2d(256, 64, 1, 1)
self.embed_action = nn.Linear(action_space, 10)
# self.embed_action = nn.Linear(10, 10)
self.detection_appearance_linear_1 = nn.Linear(512, 128)
self.detection_other_info_linear_1 = nn.Linear(6, 19)
self.detection_other_info_linear_2 = nn.Linear(19, 19)
self.detection_appearance_linear_2 = nn.Linear(128, 49)
# self.graph = nn.Linear(19, 19)
# pointwise_in_channels = 138
pointwise_in_channels = 93
self.pointwise = nn.Conv2d(pointwise_in_channels, 64, 1, 1)
lstm_input_sz = 7 * 7 * 64
self.hidden_state_sz = hidden_state_sz
self.lstm = nn.LSTMCell(lstm_input_sz, hidden_state_sz)
num_outputs = action_space
# self.critic_linear = nn.Linear(hidden_state_sz, 1)
self.critic_linear_1 = nn.Linear(hidden_state_sz, 64)
# self.critic_linear_2 = nn.Linear(72, 1)
self.critic_linear_2 = nn.Linear(64, 1)
self.actor_linear = nn.Linear(hidden_state_sz, num_outputs)
self.apply(weights_init)
relu_gain = nn.init.calculate_gain("relu")
self.conv1.weight.data.mul_(relu_gain)
self.actor_linear.weight.data = norm_col_init(
self.actor_linear.weight.data, 0.01)
self.actor_linear.bias.data.fill_(0)
# self.critic_linear.weight.data = norm_col_init(
# self.critic_linear.weight.data, 1.0
# )
# self.critic_linear.bias.data.fill_(0)
self.critic_linear_1.weight.data = norm_col_init(
self.critic_linear_1.weight.data, 1.0)
self.critic_linear_1.bias.data.fill_(0)
self.critic_linear_2.weight.data = norm_col_init(
self.critic_linear_2.weight.data, 1.0)
self.critic_linear_2.bias.data.fill_(0)
self.lstm.bias_ih.data.fill_(0)
self.lstm.bias_hh.data.fill_(0)
self.action_predict_linear = nn.Linear(2 * lstm_input_sz, action_space)
self.dropout = nn.Dropout(p=args.dropout_rate)
def __init__(self, args):
action_space = args.action_space
target_embedding_sz = args.glove_dim
resnet_embedding_sz = 512
hidden_state_sz = args.hidden_state_sz
super(MJOLNIR_R, self).__init__()
self.conv1 = nn.Conv2d(resnet_embedding_sz, 64, 1)
self.maxp1 = nn.MaxPool2d(2, 2)
self.embed_glove = nn.Linear(target_embedding_sz, 64)
self.embed_action = nn.Linear(action_space, 10)
pointwise_in_channels = 64 + 64 + 10
self.pointwise = nn.Conv2d(pointwise_in_channels, 64, 1, 1)
lstm_input_sz = 7 * 7 * 64 + 512
self.hidden_state_sz = hidden_state_sz
self.lstm = nn.LSTMCell(lstm_input_sz, hidden_state_sz)
num_outputs = action_space
self.critic_linear = nn.Linear(hidden_state_sz, 1)
self.actor_linear = nn.Linear(hidden_state_sz, num_outputs)
self.apply(weights_init)
relu_gain = nn.init.calculate_gain("relu")
self.conv1.weight.data.mul_(relu_gain)
self.actor_linear.weight.data = norm_col_init(
self.actor_linear.weight.data, 0.01)
self.actor_linear.bias.data.fill_(0)
self.critic_linear.weight.data = norm_col_init(
self.critic_linear.weight.data, 1.0)
self.critic_linear.bias.data.fill_(0)
self.lstm.bias_ih.data.fill_(0)
self.lstm.bias_hh.data.fill_(0)
self.action_predict_linear = nn.Linear(2 * lstm_input_sz, action_space)
self.dropout = nn.Dropout(p=args.dropout_rate)
# get and normalize adjacency matrix.
np.seterr(divide='ignore')
A_raw = torch.load("./data/gcn/adjmat.dat")
A = normalize_adj(A_raw).tocsr().toarray()
self.A = torch.nn.Parameter(torch.Tensor(A))
n = int(A.shape[0])
self.n = n
# last layer of resnet18.
resnet18 = models.resnet18(pretrained=True)
modules = list(resnet18.children())[-2:]
self.resnet18 = nn.Sequential(*modules)
for p in self.resnet18.parameters():
p.requires_grad = False
# glove embeddings for all the objs.
with open("./data/gcn/objects.txt") as f:
objects = f.readlines()
self.objects = [o.strip() for o in objects]
all_glove = torch.zeros(n, 300)
glove = Glove(args.glove_file)
for i in range(n):
all_glove[i, :] = torch.Tensor(
glove.glove_embeddings[self.objects[i]][:])
self.all_glove = nn.Parameter(all_glove)
self.all_glove.requires_grad = False
self.W0 = nn.Linear(401, 401, bias=False)
self.W1 = nn.Linear(401, 401, bias=False)
self.W2 = nn.Linear(401, 5, bias=False)
self.W3 = nn.Linear(10, 1, bias=False)
self.final_mapping = nn.Linear(n, 512)