diff --git a/README.md b/README.md index 4b1f93a58901a89a3b70bf42c2216165fff00f20..5ba660971efae976629f9198d0fa8bc6261fe8b4 100644 --- a/README.md +++ b/README.md @@ -1,5 +1,16 @@ # 概述 -PaddlePaddle是百度开源的机器学习框架，广泛支持各种深度学习模型的定制化开发; Paddle serving是Paddle的在线预测部分，与Paddle模型训练环节无缝衔接，提供机器学习预测云服务。 +PaddlePaddle是百度开源的机器学习框架，广泛支持各种深度学习模型的定制化开发; Paddle serving是PaddlePaddle的在线预估服务框架，通过加载PaddlePaddle训练得到的模型，利用PaddlePaddle的预测库，提供机器学习预测云服务。 + +# 文档 + +[设计文档](doc/DESIGN.md) + +[从零开始写一个预测服务](doc/CREATING.md) + +[编译安装](doc/INSTALL.md) + +[FAQ](doc/FAQ.md) + # 框架简介 @@ -80,13 +91,3 @@ Paddle serving框架为策略工程师提供以下三层面的功能性扩展： `-- tools # CI工具 `-- codestyle ``` - -# 文档 - -[设计文档](doc/DESIGN.md) - -[从零开始写一个预测服务](doc/CREATING.md) - -[编译安装](doc/INSTALL.md) - -[FAQ](doc/FAQ.md) diff --git a/cube/cube-transfer/src/transfer/deployer.go b/cube/cube-transfer/src/transfer/deployer.go index e054f1fbd89cb08884b1b80b45adc4770af0dd00..2c677de1a61ea6f5846e3a174795e4c4aa2225d1 100755 --- a/cube/cube-transfer/src/transfer/deployer.go +++ b/cube/cube-transfer/src/transfer/deployer.go @@ -81,16 +81,17 @@ func CmdInstsDownload() { } } for i, inst := range Dict.Instances { - err := <-chs[i] - logex.Noticef("[instance resp]download:%v", Dict.Instances) - if err != nil || keyAndRespSlice[i].Success != "0" { - logex.Warningf("cmd cube online downlaod of %v:%v, shard:%v failed", inst.AgentIp, inst.AgentPort, inst.Shard) - continue - } - if inst.Status < dict.Instance_Status_Download_Succ { - Dict.Instances[i].Status = dict.Instance_Status_Download_Succ - Dict.Instances[i].DownloadedTime = int(time.Now().Unix()) - Dict.DownloadSuccInsts++ + if inst.Status != dict.Instance_Status_Download_Succ { + err := <-chs[i] + if err != nil || keyAndRespSlice[i].Success != "0" { + logex.Warningf("cmd cube online downlaod of %v:%v, shard:%v failed", inst.AgentIp, inst.AgentPort, inst.Shard) + continue + } + if inst.Status < dict.Instance_Status_Download_Succ { + Dict.Instances[i].Status = dict.Instance_Status_Download_Succ + Dict.Instances[i].DownloadedTime = int(time.Now().Unix()) + Dict.DownloadSuccInsts++ + } } } if Dict.DownloadSuccInsts == Dict.InstancesNum { @@ -130,16 +131,18 @@ func CmdInstsReload() { } } for i, inst := range Dict.Instances { - err := <-chs[i] - logex.Noticef("[instance resp]reload:%v", Dict.Instances) - if err != nil || keyAndRespSlice[i].Success != "0" { - logex.Warningf("cmd cube online reload of %v:%v, shard:%v failed", inst.AgentIp, inst.AgentPort, inst.Shard) - continue - } - if inst.Status < dict.Instance_Status_Reload_Succ { - Dict.Instances[i].Status = dict.Instance_Status_Reload_Succ - Dict.Instances[i].ReloadedTime = int(time.Now().Unix()) - Dict.ReloadSuccInsts++ + if inst.Status != dict.Instance_Status_Reload_Succ { + err := <-chs[i] + logex.Noticef("[instance resp]reload:%v", Dict.Instances) + if err != nil || keyAndRespSlice[i].Success != "0" { + logex.Warningf("cmd cube online reload of %v:%v, shard:%v failed", inst.AgentIp, inst.AgentPort, inst.Shard) + continue + } + if inst.Status < dict.Instance_Status_Reload_Succ { + Dict.Instances[i].Status = dict.Instance_Status_Reload_Succ + Dict.Instances[i].ReloadedTime = int(time.Now().Unix()) + Dict.ReloadSuccInsts++ + } } } if Dict.ReloadSuccInsts == Dict.InstancesNum { @@ -179,16 +182,18 @@ func CmdInstsEnable() { } } for i, inst := range Dict.Instances { - err := <-chs[i] - logex.Noticef("[instance resp]enable:%v", Dict.Instances) - if err != nil || keyAndRespSlice[i].Success != "0" { - logex.Warningf("cmd cube online enable of %v:%v, shard:%v failed", inst.AgentIp, inst.AgentPort, inst.Shard) - continue - } - if inst.Status < dict.Instance_Status_Enable_Succ { - Dict.Instances[i].Status = dict.Instance_Status_Enable_Succ - Dict.Instances[i].EnabledTime = int(time.Now().Unix()) - Dict.EnableSuccInsts++ + if inst.Status != dict.Instance_Status_Enable_Succ { + err := <-chs[i] + logex.Noticef("[instance resp]enable:%v", Dict.Instances) + if err != nil || keyAndRespSlice[i].Success != "0" { + logex.Warningf("cmd cube online enable of %v:%v, shard:%v failed", inst.AgentIp, inst.AgentPort, inst.Shard) + continue + } + if inst.Status < dict.Instance_Status_Enable_Succ { + Dict.Instances[i].Status = dict.Instance_Status_Enable_Succ + Dict.Instances[i].EnabledTime = int(time.Now().Unix()) + Dict.EnableSuccInsts++ + } } } if Dict.EnableSuccInsts == Dict.InstancesNum { diff --git a/elastic-ctr/client/demo/elastic_ctr.py b/elastic-ctr/client/demo/elastic_ctr.py index 91695fd6656345b26a76807e0d3c258ba3adf81f..87d442c39d8015458467f9d0ad7703724cc67290 100644 --- a/elastic-ctr/client/demo/elastic_ctr.py +++ b/elastic-ctr/client/demo/elastic_ctr.py @@ -19,7 +19,7 @@ import os from elastic_ctr_api import ElasticCTRAPI -BATCH_SIZE = 3 +BATCH_SIZE = 10 SERVING_IP = "127.0.0.1" SLOT_CONF_FILE = "./conf/slot.conf" CTR_EMBEDDING_TABLE_SIZE = 100000001 @@ -33,6 +33,59 @@ def str2long(str): return int(str) +def tied_rank(x): + """ + Computes the tied rank of elements in x. + This function computes the tied rank of elements in x. + Parameters + ---------- + x : list of numbers, numpy array + Returns + ------- + score : list of numbers + The tied rank f each element in x + """ + sorted_x = sorted(zip(x,range(len(x)))) + r = [0 for k in x] + cur_val = sorted_x[0][0] + last_rank = 0 + for i in range(len(sorted_x)): + if cur_val != sorted_x[i][0]: + cur_val = sorted_x[i][0] + for j in range(last_rank, i): + r[sorted_x[j][1]] = float(last_rank+1+i)/2.0 + last_rank = i + if i==len(sorted_x)-1: + for j in range(last_rank, i+1): + r[sorted_x[j][1]] = float(last_rank+i+2)/2.0 + return r + + +def auc(actual, posterior): + """ + Computes the area under the receiver-operater characteristic (AUC) + This function computes the AUC error metric for binary classification. + Parameters + ---------- + actual : list of binary numbers, numpy array + The ground truth value + posterior : same type as actual + Defines a ranking on the binary numbers, from most likely to + be positive to least likely to be positive. + Returns + ------- + score : double + The mean squared error between actual and posterior + """ + r = tied_rank(posterior) + num_positive = len([0 for x in actual if x==1]) + num_negative = len(actual)-num_positive + sum_positive = sum([r[i] for i in range(len(r)) if actual[i]==1]) + auc = ((sum_positive - num_positive*(num_positive+1)/2.0) / + (num_negative*num_positive)) + return auc + + def data_reader(data_file, samples, labels): if not os.path.exists(data_file): print("Path %s not exist" % data_file) @@ -66,7 +119,7 @@ def data_reader(data_file, samples, labels): sample[x] = [0] samples.append(sample) - + if __name__ == "__main__": """ main """ @@ -89,8 +142,10 @@ if __name__ == "__main__": sys.exit(-1) ret = data_reader(sys.argv[4], samples, labels) - + print(len(samples)) correct = 0 + wrong_label_1_count = 0 + result_list = [] for i in range(0, len(samples) - BATCH_SIZE, BATCH_SIZE): api.clear() batch = samples[i:i + BATCH_SIZE] @@ -110,6 +165,7 @@ if __name__ == "__main__": idx = 0 for x in predictions: + result_list.append(x["prob1"]) if x["prob0"] >= x["prob1"]: pred = 0 else: @@ -118,9 +174,14 @@ if __name__ == "__main__": if labels[i + idx] == pred: correct += 1 else: - print("id=%d predict incorrect: pred=%d label=%d (%f %f)" % - (i + idx, pred, labels[i + idx], x["prob0"], x["prob1"])) - + #if labels[i + idx] == 1: + # wrong_label_1_count += 1 + # print("error label=1 count", wrong_label_1_count) + #print("id=%d predict incorrect: pred=%d label=%d (%f %f)" % + # (i + idx, pred, labels[i + idx], x["prob0"], x["prob1"])) + pass idx = idx + 1 + - print("Acc=%f" % (float(correct) / len(samples))) + #print("Acc=%f" % (float(correct) / len(samples))) + print("auc = ", auc(labels, result_list) )