# create res_file res_file_path = out_folder + "/res.res" res_file = open(res_file_path, "w") res_file.close() # Learning rates and architecture-specific optimization parameters arch_lst = get_all_archs(config) lr = {} auto_lr_annealing = {} improvement_threshold = {} halving_factor = {} pt_files = {} for arch in arch_lst: lr[arch] = expand_str_ep(config[arch]["arch_lr"], "float", N_ep, "|", "*") if len(config[arch]["arch_lr"].split("|")) > 1: auto_lr_annealing[arch] = False else: auto_lr_annealing[arch] = True improvement_threshold[arch] = float(config[arch]["arch_improvement_threshold"]) halving_factor[arch] = float(config[arch]["arch_halving_factor"]) pt_files[arch] = config[arch]["arch_pretrain_file"] # If production, skip training and forward directly from last saved models if is_production: ep = N_ep - 1 N_ep = 0 model_files = {}
# create res_file res_file_path = out_folder + '/res.res' res_file = open(res_file_path, "w") res_file.close() # Learning rates and architecture-specific optimization parameters arch_lst = get_all_archs(config) lr = {} auto_lr_annealing = {} improvement_threshold = {} halving_factor = {} pt_files = {} for arch in arch_lst: lr[arch] = expand_str_ep(config[arch]['arch_lr'], 'float', N_ep, '|', '*') if len(config[arch]['arch_lr'].split('|')) > 1: auto_lr_annealing[arch] = False else: auto_lr_annealing[arch] = True improvement_threshold[arch] = float( config[arch]['arch_improvement_threshold']) halving_factor[arch] = float(config[arch]['arch_halving_factor']) pt_files[arch] = config[arch]['arch_pretrain_file'] # If production, skip training and forward directly from last saved models if is_production: ep = N_ep - 1 N_ep = 0 model_files = {}