def __init__(self, model, task, result, report, n_session, n_block, seed=None): self.model_file = model self.task_file = task self.result_file = result self.report_file = report self.n_session = n_session self.n_block = n_block self.seed = seed if self.seed is None: self.seed = random.randint(0, 1000) np.random.seed(seed), random.seed(seed) self.model = Model(self.model_file) self.task = Task(self.task_file) self.n_trial = len(self.task)
import numpy as np import matplotlib.pyplot as plt from task_single import Task from model_single import Model import os folder = "data/figures/" if not os.path.exists(folder): os.makedirs(folder) seed = random.randint(0,1000) np.random.seed(seed) random.seed(seed) # seed = 448,380,325 model = Model("model-topalidou.json") task = Task("tasks/task-topalidou.json") print("-"*30) print("Seed: %d" % seed) print("Model: %s" % model.filename) print("Task: %s" % task.filename) print("-"*30) trial = task[0] model.process(task, trial, stop=False, debug=False, cortical_activity=True) cog = model["CTX"]["cog"].history[:3000] mot = model["CTX"]["mot"].history[:3000]
import matplotlib.pyplot as plt from task_single import Task from model_single import Model import os folder = "data/figures/" if not os.path.exists(folder): os.makedirs(folder) # seed = random.randint(0,1000) # np.random.seed(seed) # random.seed(seed) seed = 749 model = Model("model-topalidou-thomas.json") task = Task("tasks/task-topalidou.json") print("-" * 30) print("Seed: %d" % seed) print("Model: %s" % model.filename) print("Task: %s" % task.filename) print("-" * 30) model["CTX:cog → STR:cog"].gain = 0 model["CTX:mot → STR:mot"].gain = 0 model["CTX:cog → STR:ass"].gain = 0 model["CTX:mot → STR:ass"].gain = 0 trial = task[0] model.process(task, trial, stop=False, debug=False)
import numpy as np import matplotlib.pyplot as plt from task_single import Task from model_single import Model import os folder = "data/figures/" if not os.path.exists(folder): os.makedirs(folder) seed = random.randint(0, 1000) np.random.seed(seed) random.seed(seed) # seed = 448,380,325 model = Model("model-topalidou.json") task = Task("tasks/task-topalidou.json") print("-" * 30) print("Seed: %d" % seed) print("Model: %s" % model.filename) print("Task: %s" % task.filename) print("-" * 30) trial = task[0] model.process(task, trial, stop=False, debug=False, cortical_activity=True) cog = model["CTX"]["cog"].history[:3000] mot = model["CTX"]["mot"].history[:3000] duration = 3.0
import matplotlib.pyplot as plt from task_single import Task from model_single import Model import os folder = "data/figures/" if not os.path.exists(folder): os.makedirs(folder) # seed = random.randint(0,1000) # np.random.seed(seed) # random.seed(seed) seed = 749 model = Model("model-topalidou-thomas.json") task = Task("tasks/task-topalidou.json") print("-"*30) print("Seed: %d" % seed) print("Model: %s" % model.filename) print("Task: %s" % task.filename) print("-"*30) model["CTX:cog → STR:cog"].gain = 0 model["CTX:mot → STR:mot"].gain = 0 model["CTX:cog → STR:ass"].gain = 0 model["CTX:mot → STR:ass"].gain = 0 trial = task[0] model.process(task, trial, stop=False, debug=False)
type=str, help='pretrained model checkpoint') parser.add_argument('--epochs', default=101, type=int, help='train epochs') parser.add_argument('--train', default=True, type=bool, help='train') args = parser.parse_args() save_path = args.save_path + f'{args.message}_{time_str}' if not os.path.exists(save_path): os.mkdir(save_path) logger = Logger(f'{save_path}/log.log') logger.Print(args.message) train_data, val_data, test_data = load_cisia_surf(train_size=args.batch_size, test_size=args.test_size) model = Model(pretrained=False, num_classes=2) criterion = nn.CrossEntropyLoss() optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.9, weight_decay=5e-4) scheduler = lr_scheduler.ExponentialLR(optimizer, gamma=0.95) if use_cuda: model = model.cuda() criterion = criterion.cuda() loss_history = [] eval_history = []