'val':deepcopy(Mode),
'Inputs':inputs,
'Targets':targets,
}
C['val']['loss_color'] = 'r'
C['train']['all_indicies'], C['val']['all_indicies'] = \
utils.get_train_and_val_indicies(len(C['Targets']),100)
cg("C['val']['all_indicies'] =",len(C['val']['all_indicies']))
cg("C['train']['all_indicies'] =",len(C['train']['all_indicies']))
"""
chain_net = Chain_net()
if A['load_net']:
#best_path = find_best_net(A['net_path'])
best_path = most_recent_file_in_folder(A['net_path'])
cg("Loading net from",best_path)
chain_net.load_state_dict(torch.load(best_path))
#chain_net = torch.nn.DataParallel(chain_net)
chain_net.to(device)
cg('chain_net.to(device)')
criterion = nn.MSELoss()
optimizer = optim.Adam(chain_net.parameters(), A['learning_rate']) #, lr=0.001)
os_system('mkdir -p',A['net_path'])
'val': deepcopy(Mode),
'Inputs': inputs,
'Targets': targets,
}
C['val']['loss_color'] = 'r'
C['train']['all_indicies'], C['val']['all_indicies'] = \
utils.get_train_and_val_indicies(len(C['Targets']),100)
cg("C['val']['all_indicies'] =", len(C['val']['all_indicies']))
cg("C['train']['all_indicies'] =", len(C['train']['all_indicies']))
modes = ['train', 'val']
chain_net = Chain_net()
if A['load_net']:
#best_path = find_best_net(A['net_path'])
best_path = most_recent_file_in_folder(A['net_path'])
cg("Loading net from", best_path)
chain_net.load_state_dict(torch.load(best_path))
#chain_net = torch.nn.DataParallel(chain_net)
chain_net.to(device)
criterion = nn.MSELoss()
optimizer = optim.Adam(chain_net.parameters(),
A['learning_rate']) #, lr=0.001)
os_system('mkdir -p', A['net_path'])
A[m] = deepcopy(Mode)
A['data_file_paths'] = sggo(A['data_path'], '*.h5py')
A['train']['opened_data_files'] = []
A['val']['opened_data_files'] = []
for f in A['data_file_paths']:
for mode in ['val', 'train']:
if mode + '_' in fname(f):
A[mode]['opened_data_files'].append(h5r(f))
A['val']['loss_color'] = 'r'
A['train']['loss_color'] = 'b'
A['val']['current_index'] = -1
A['train']['current_index'] = -1
chain_net_original = Chain_net()
backend = 'fbgemm'
#backend = 'FakeQuantize'
chain_net_original.train()
chain_net_original.qconfig = torch.quantization.get_default_qat_qconfig(
backend)
chain_net_original.aa.qconfig = torch.quantization.get_default_qat_qconfig(
backend)
chain_net_original.aa.d.qconfig = torch.quantization.get_default_qat_qconfig(
backend)
chain_net_original.aa.e.qconfig = torch.quantization.get_default_qat_qconfig(
backend)