肥猫零零七

@panjf2000 could use this method? ```go for j := 0; j < batchCount; j++ { bj:=j routinePoll.Submit(func() { genBucketBatch(bj) }) } ```

@smallnest 如果在支持 C++ 那就更完美了

c++ 在深度学习在线推理领域非常火,但是和其他生态结合跨语言的微服务就比较弱了

curl -O https://storage.googleapis.com/criteo-cail-datasets/day_1.gz file=day_1.gz dist=/path/ dist_file=day_1.tsv gzip -d -v -c ${file} >> "${dist}/${dist_file}"

@c21 At first, it was due to the scheme problem. Adding the scheme was enough. However, when there is abnormal data in the data, ray will report an error and...

FREQUENCY_THRESHOLD = 3 INT_FEATURE_COUNT = 13 CAT_FEATURE_COUNT = 26 DAYS = 24 DEFAULT_LABEL_NAME = "label" DEFAULT_INT_NAMES: List[str] = [f"int_{idx}" for idx in range(INT_FEATURE_COUNT)] DEFAULT_CAT_NAMES: List[str] = [f"cat_{idx}" for idx in...

Also ask if we can complete the TensorFlow model packaging through C ++ API

how to package a model for TensorFlow2.0 ,it does't have a session and static graph `create_keras_neuropod( neuropod_path, model_name, sess, model, node_name_mapping = None, input_spec = None, output_spec = None, input_tensor_device...

@VivekPanyam Algorithm engineer after training complete model, the model will be stored in a particular file system, is not responsible for, a model based on neuropod packaging, if using neuropod...

@VivekPanyam @vkuzmin-uber V How do you do reasoning with TensorFlow 2.0 based on Neuropod, using the Create Keras Neuropod encapsulation model