def __init__(self, learningArgs, motionModelArgs):
lr = learningArgs[0]
lrDecay_stepSize = learningArgs[1]
lrDecay_gamma = learningArgs[2]
weight_decay = learningArgs[3]
self.device = 'cuda:0' if torch.cuda.is_available() else 'cpu'
self.MotionModel = probabilisticMotionModel(motionModelArgs).to(
self.device)
self.optimizer = Adam(self.MotionModel.parameters(),
lr=lr,
weight_decay=weight_decay)
self.lrScheduler = torch.optim.lr_scheduler.StepLR(
self.optimizer, step_size=lrDecay_stepSize, gamma=lrDecay_gamma)
self.criterion = torch.nn.MSELoss()
torch.tensor(startState[3]).unsqueeze(0).to(device))
predSequentialX = [startState[3][0]]
predSequentialY = [startState[3][1]]
if evalProbabilistic:
numParticles = 10
inStateDim = len(startState[0][0]) + 1
inActionDim = len(startState[0][2])
inMapDim = startState[0][1].shape[1]
outStateDim = len(startState[1][0])
argDim = [inStateDim, inMapDim, inActionDim, outStateDim]
convSizes = [[32, 5], [32, 4], [32, 3]]
fcSizes = [1024, 512, 256] #,128]
networkSizes = [convSizes, fcSizes]
dropout_ps = [0, 0, 0]
motionModelArgs = [argDim, networkSizes, dropout_ps]
motionModelProb = probabilisticMotionModel(motionModelArgs).to(device)
motionModelProb.load_state_dict(
torch.load('motionModels/sequentialProbailistic.pt'))
motionModelProb.eval()
cliffordStatePredProb = cliffordStateTransformation(
torch.tensor(startState[3]).unsqueeze(0).to(device),
numParticles=numParticles)
predProbabilisticX = [[startState[3][0]] for i in range(numParticles)]
predProbabilisticY = [[startState[3][1]] for i in range(numParticles)]
if evalLSTM:
inStateDim = 9
inActionDim = len(startState[0][2])
inMapDim = startState[0][1].shape[1]
outStateDim = 13
argDim = [inStateDim, inMapDim, inActionDim, outStateDim]
convSizes = [[32, 5], [32, 4], [32, 3]]