self.load_state_dict(torch.load('BEST_WS'))
os.remove('BEST_WS')
best_asd_path = os.path.join(
config.DATA_PATH, 'Trained_Models',
'Complex_Fully_Connected_WGAN_LPF_W',
time_stamp() + '|WS' + '|BC:' + str(batch_size) + '|g_eta:' +
str(g_eta) + '|d_eta:' + str(d_eta) + '|n_critic:' +
str(n_critic) + '|clip_value:' + str(clip_value))
torch.save(self.state_dict(), best_asd_path)
except:
pass
return
if __name__ == '__main__':
set_start_method('spawn') # To make dynamic reporter works
for eta in [0.0001, 0.00001, 0.001]:
for i in range(3):
report_path = os.path.join(
config.DATA_PATH, 'Training_Reports',
'Complex_Fully_Connected_WGAN_LPF_W',
time_stamp() + '|eta:' + str(eta) + '|n_critic:' + str(5) +
'|clip_value:' + str(0.01) + '.png')
init_dynamic_report(3, report_path)
gan = Complex_Fully_Connected_WGAN_LPF_W(dim)
gan.train(train_set, 10, 200, eta, eta, 5, 0.01, True)
stop_dynamic_report()
a[1]
# %%
a = np.array([])
# %%
a
# %%
a.shape
# %%
from dynamic_reporter import init_dynamic_report
from dynamic_reporter import stop_dynamic_report
import dynamic_reporter
import time
# %%
q = init_dynamic_report(10)
# %%
stop_dynamic_report(564)
# %%
q
# %%
q.qsize()
# %%
q.put({'wefwf': 58789874987.456})
# %%
def f():
global A
if 'A' in globals():
print('ok')
else:
print('no')