def check_dc_generator():
"""Checks the output and number of parameters of the DCGenerator class.
"""
state = torch.load('checker_files/dc_generator.pt')
G = DCGenerator(noise_size=100, conv_dim=32)
G.load_state_dict(state['state_dict'])
noise = state['input']
dc_generator_expected = state['output']
output = G(noise)
output_np = output.data.cpu().numpy()
if np.allclose(output_np, dc_generator_expected):
print('DCGenerator output: EQUAL')
else:
print('DCGenerator output: NOT EQUAL')
num_params = count_parameters(G)
expected_params = 370624
print('DCGenerator #params = {}, expected #params = {}, {}'.format(
num_params, expected_params,
'EQUAL' if num_params == expected_params else 'NOT EQUAL'))
print('-' * 80)
def check_dc_generator():
"""Checks the output and number of parameters of the DCGenerator class.
"""
state = torch.load('/home/love_you/Documents/Study/deep_learning/a4-code/a4-code-v2-updated/checker_files/dc_generator.pt')
# print(state['state_dict'].keys())
G = DCGenerator(noise_size=100, conv_dim=32)
# for name, param in G.named_parameters():
# print(name)
# summary(G, input_size=(100, 1, 1))
G.load_state_dict(state['state_dict'])
noise = state['input']
dc_generator_expected = state['output']
output = G(noise)
output_np = output.data.cpu().numpy()
if np.allclose(output_np, dc_generator_expected):
print('DCGenerator output: EQUAL')
else:
print('DCGenerator output: NOT EQUAL')
num_params = count_parameters(G)
expected_params = 370624
print('DCGenerator #params = {}, expected #params = {}, {}'.format(
num_params, expected_params, 'EQUAL' if num_params == expected_params else 'NOT EQUAL'))
print('-' * 80)