image_num = len(image_path)
print("图片数量 ",image_num)
return image_path,image_num
if __name__ == '__main__':
start = time.time()
#提取image路径文件
# with open("image_reference_cache_amazon.defaultdict", "rb") as file:
# data = pk.load(file)
with open("result/imagenet_baidu_ref2000.pkl", "rb") as file:
data = pk.load(file)
image_path,image_num = get_image_path(data)
#上传原图到云服务器
# cloud_agent = FacePP()
cloud_agent = Baidu()
# cloud_agent = AmazonRekognition()
ref_quality = 75
cache = defaultdict(dict)
deepn_cache = defaultdict(dict)
compare_cache = defaultdict(dict)
# 导入之前结果
# with open("result/Origin_Baidu.defaultdict", 'rb') as file:
# cache = pk.load(file)
# with open("result/DeepN_Baidu.defaultdict", 'rb') as file:
# deepn_cache = pk.load(file)
# with open("result/Compare_Baidu.defaultdict", 'rb') as file:
# compare_cache = pk.load(file)
num1 = image_num
# num1 = 30
for i in range(num1):
def estimate(self):
if len(self.agent_memory['reward']) < self.recent_zone:
recent_reward = np.mean(self.agent_memory['reward'])
recent_acc = np.mean(self.agent_memory['accuracy'])
else:
recent_reward = np.mean(
self.agent_memory['reward'][-self.recent_zone:])
recent_acc = np.mean(
self.agent_memory['accuracy'][-self.recent_zone:])
return recent_acc, recent_reward
#
if __name__ == '__main__':
api = Baidu()
rm = ResultManager('evaluation_results')
running_agent = RunningAgent(
dqn_path='evaluation_results/agent_DQN_train_baidu_imagenet.h5',
banchmark_q=75,
cloud_backend=api,
)
imagenet_paths = _gen_sample_set_imagenet(
'/home/hsli/gnode02/imagenet-data/train/', 3)[-500:]
test_image_paths = imagenet_paths
for idx, path in enumerate(test_image_paths):
error_code, log_dict = running_agent.agent_upload(path)
x = feature_extractor.output
x = AveragePooling2D(pool_size=(4, 4))(x)
feature_extractor = Model(inputs=feature_extractor.input, outputs=x)
compute_memory(101)
# agent
agent = DQN_Agent(s_dim=1280,
a_dim=10,
epsilon_decay=0.99,
epsilon_min=0.02,
gamma=0.95,
replay_batchsize=256)
if __name__ == '__main__':
test_image_paths = imagenet_paths[:5] # FLIR[:1000]
# test_image_paths = FLIR[:1000]
cloud_agent = Baidu()
train_log = defaultdict(list)
ref_results = defaultdict(dict)
compress_results = defaultdict(dict)
choose_action_total_time = 0
feedback_total_time = 0
feature_total_time = 0
recent_accuracy = 0
recent_reward = 0
start_time = time.time()
if EVALUATION:
agent.model = load_model('compute_time_results/baidu_imagenet.h5')
# agent.model = load_model('compute_time_results/baidu_FLIR.h5')