WARNING:tensorflow: The following Variables were used a Lambda layer's call (tf.linalg.matmul_1), but are not present in its tracked objects: <tf.Variable 'dense_1/kernel:0' shape=(64, 1) dtype=float32> It is possible that this is intended behavior, but it is more likely an omission. This is a strong indication that this layer should be formulated as a subclassed Layer rather than a Lambda layer.

AttributeError Traceback (most recent call last) in () 31 32 # 4.Define Model,train,predict and evaluate ---> 33 model = DeepFM(linear_feature_columns, dnn_feature_columns, task='regression') 34 model.compile("adam", "mse", metrics=['mse'], ) 35

4 frames /usr/local/lib/python3.7/dist-packages/keras/engine/functional_utils.py in is_input_keras_tensor(tensor) 46 if not node_module.is_keras_tensor(tensor): 47 raise ValueError(_KERAS_TENSOR_TYPE_CHECK_ERROR_MSG.format(tensor)) ---> 48 return tensor.node.is_input 49 50

AttributeError: 'KerasTensor' object has no attribute 'node' 是不是tensorflow版本的问题？

Traceback (most recent call last): File "E:/testings/DeepCTR-master/examples/run_classification_criteo.py", line 44, in model = DeepFM(linear_feature_columns, dnn_feature_columns, task='binary') File "E:\testings\DeepCTR-master\deepctr\models\deepfm.py", line 64, in DeepFM model = tf.keras.models.Model(inputs=inputs_list, outputs=output) File "C:\Users\Lenovo\anaconda3\envs\python37\lib\site-packages\tensorflow\python\training\tracking\base.py", line 629, in _method_wrapper result = method(self, *args, **kwargs) File "C:\Users\Lenovo\anaconda3\envs\python37\lib\site-packages\keras\engine\functional.py", line 144, in init for t in tf.nest.flatten(inputs)]): File "C:\Users\Lenovo\anaconda3\envs\python37\lib\site-packages\keras\engine\functional.py", line 144, in for t in tf.nest.flatten(inputs)]): File "C:\Users\Lenovo\anaconda3\envs\python37\lib\site-packages\keras\engine\functional_utils.py", line 48, in is_input_keras_tensor return tensor.node.is_input AttributeError: 'KerasTensor' object has no attribute 'node'

运行 https://github.com/shenweichen/DeepCTR/blob/master/examples/run_din.py报错 ： ..../site-packages/deepctr/layers/sequence.py:198 call * outputs._uses_learning_phase = attention_score._uses_learning_phase AttributeError: 'Tensor' object has no attribute '_uses_learning_phase' 请问如何解决呢？ Operating environment(运行环境):

• python version 3.6
• tensorflow version 1.4.0
• deepctr version 0.5.2

运行官网的例子时，报错信息为： tensorflow.python.framework.errors_impl.InvalidArgumentError: indices[0,0] = 104 is not in [0, 14) [[{{node sparse_emb_18-C14/embedding_lookup}} = ResourceGather[Tindices=DT_INT32, _class=["loc:@training/Adam/gradients/sparse_emb_18-C14/embedding_lookup_grad/Reshape"], dtype=DT_FLOAT, validate_indices=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](sparse_emb_18-C14/embeddings, linear_emb_18-C14/Cast)]]

系统版本： tensorflow:1.11.0 keras:2.2.4 deepctr:0.2.2

New Feature:

Modify the Hash layer to support the lookup feature.

Now there are two hash techniques supported in the Hash layer:

1. Lookup Table: when setup vocabulary_path, it can looks up input keys in a table and output the corresponding values. Missed keys are always return the default value, eg. 0.
2. Bucket Hash: when vocabulary_path is not set, Hash will hash the input keys to [0,num_buckets). Parameter mask_zero can set True, which will set the hash value 0 when the input keys are 0 or 0.0, and other value will be hash in range [1,num_buckets).

Initializing Hash with vocabulary_path CSV file which need follow the convention：the first column as keys and second column as values which are seperated by comma.

The following is example snippet:

* `1,emerson`
* `2,lake`
* `3,palmer`

>>> hash = Hash(
...   num_buckets=3+1,
...   vocabulary_path=filename,
...   default_value=0)
>>> hash(tf.constant('lake')).numpy()
2
>>> hash(tf.constant('lakeemerson')).numpy()
0

• delete the Lambda sublayer in LocalActivationUnit Layer class

• add vocabulary_path in the SparseFeat to support the csv HashTable functionality

• update docs and add examples in doc

• Remove trailing whitespace

Describe the bug(问题描述) When set the embedding size to "auto", the Concatenate layer can't merge all input Embedding with different size at axis=2

def concat_fun(inputs, axis=-1): if len(inputs) == 1: return inputs[0] else: return Concatenate(axis=axis)(inputs)

To Reproduce(复现步骤) Steps to reproduce the behavior:

1. Go to '...'
2. Click on '....'
3. Scroll down to '....'
4. ValueError: A Concatenate layer requires inputs with matching shapes except for the concat axis. Got inputs shapes: [(None, 1, 36), (None, 1, 30), (None, 1, 6), (None, 1, 12), (None, 1, 12), (None, 1, 30), (None, 1, 12)]

Operating environment(运行环境):

• python version [e.g. 3.4, 3.6]
• tensorflow version [e.g. 1.4.0, 1.12.0]
• deepctr version [e.g. 0.2.3,]

Additional context Add any other context about the problem here.

Describe the question(问题描述) 在使用deepfm模型进行推理时，单次推理达到300ms，这么高的延迟，不知道是我的操作原因，还是框架本身的问题，在给的例子中进行测试，也得到了相同的结论，如果有解决办法请告知一下，非常感谢！

Additional context Add any other context about the problem here.

Operating environment(运行环境):

• python version [e.g. 3.6]
• tensorflow version [e.g. 2.1.0,]
• deepctr version [e.g. 0.7.4,]

Describe the bug(问题描述) 运行run_dien.py时，报错ValueError: The name "seq_length" is used in 2 times in the model. All layer names should be unique.

To Reproduce(复现步骤) Steps to reproduce the behavior:

1. 运行examples/run_dien.py
2. See error

Operating environment(运行环境):

• python version [3.7.4]
• tensorflow version [2.0.0]
• deepctr version [0.7.4]

Additional context Add any other context about the problem here.

Describe the question(问题描述) 同样的数据，跑了不同的模型，在DeepFM模型上一切正常。 而使用NFFM模型的时候一直梯度爆炸，显示为Nan，请问如何处理这个问题，可以使用梯度阶段吗，该怎么使用呢？

Additional context Add any other context about the problem here.

Operating environment(运行环境):

• python version 3.6
• tensorflow version [e.g. 1.3.0,]
• deepctr version [e.g. 0.4,]

train_df=pd.read_parquet("parquet_train_20201219_110000",engine='pyarrow') test_df=pd.read_parquet("parquet_test_20201220_110000",engine='pyarrow') df = pd.concat([train_df,test_df],axis=0)

train_size=len(train_df) test_size=len(test_df)

target = ['label'] dense_features = ["c1","c2","c3","c4","c5"] sparse_features = [x for x in df.columns if x not in dense_features+target]

for feat in sparse_features: lbe = LabelEncoder() df[feat] = lbe.fit_transform(df[feat]) mms = MinMaxScaler(feature_range=(0, 1))

df[sparse_features] = df[sparse_features].fillna('-1', ) df[dense_features] = mms.fit_transform(df[dense_features])

dnn_feature_columns = [] linear_feature_columns = []

for i, feat in enumerate(sparse_features): dnn_feature_columns.append(tf.feature_column.embedding_column( tf.feature_column.categorical_column_with_identity(feat, df[feat].nunique()), 4)) linear_feature_columns.append(tf.feature_column.categorical_column_with_identity(feat, df[feat].nunique())) for feat in dense_features: dnn_feature_columns.append(tf.feature_column.numeric_column(feat)) linear_feature_columns.append(tf.feature_column.numeric_column(feat))

train = df[0:train_size] test=df[train_size:]

train_model_input = input_fn_pandas(train, sparse_features + dense_features, 'label', shuffle=True) test_model_input = input_fn_pandas(test, sparse_features + dense_features, None, shuffle=False)

model = DeepFMEstimator(linear_feature_columns, dnn_feature_columns, task='binary')

model.train(train_model_input) pred_ans_iter = model.predict(test_model_input) pred_ans = list(map(lambda x: x['pred'], pred_ans_iter)) print("test AUC", round(roc_auc_score(test[target].values, pred_ans), 4))

还有其他的设置吗，设置多gpu跑，也不太快。GPU 利用率20%。

Describe the question(问题描述) 既然DNN中的bn_layers和dropout_layers已经传入了training状态参数来区分是在训练还是在预测阶段，手动设置_uses_learning_phase的作用是什么？ 我的tf版本2.10.0，应该是执行outputs._uses_learning_phase = training is not None https://github.com/shenweichen/DeepCTR/blob/e8f4d818f9b46608bc95bb60ef0bb0633606b2f2/deepctr/layers/sequence.py#L266-L288

在求attention_score的时候，不是已经把training状态传给DNN里的dropout和batchnorm层了吗？ https://github.com/shenweichen/DeepCTR/blob/e8f4d818f9b46608bc95bb60ef0bb0633606b2f2/deepctr/layers/sequence.py#L266

https://github.com/shenweichen/DeepCTR/blob/e8f4d818f9b46608bc95bb60ef0bb0633606b2f2/deepctr/layers/core.py#L104 https://github.com/shenweichen/DeepCTR/blob/e8f4d818f9b46608bc95bb60ef0bb0633606b2f2/deepctr/layers/core.py#L198 https://github.com/shenweichen/DeepCTR/blob/e8f4d818f9b46608bc95bb60ef0bb0633606b2f2/deepctr/layers/core.py#L205

为什么还需要对_uses_learning_phase手动设置？ https://github.com/shenweichen/DeepCTR/blob/e8f4d818f9b46608bc95bb60ef0bb0633606b2f2/deepctr/layers/sequence.py#L283-L286

这里手动设置_uses_learning_phase是否发挥实际作用？去掉会怎么样？对于outputs这个tf.Tensor来说，好像是没有_uses_learning_phase这个类属性，这么写好像是临时新建个了_uses_learning_phase属性，然后赋值成xxx

outputs._uses_learning_phase = xxx

求大佬指点

Additional context Add any other context about the problem here.

Operating environment(运行环境):

• python version 3.9.12
• tensorflow version 2.10.0
• deepctr version 0.9.3

In deepctr tensorflow package, the output for Linear if only sparse features are presented would be the reduce_sum(sparse_input, axis=-1, keep_dims=True), but if there are both sparse and dense features, the output would be reduce_sum(sparse_input, axis=-1, keep_dims=False), what's the rationale for that? Thanks

您好，仓库内容很全面，非常受益， 可否引荐下本人的笔记，把我对自动驾驶的理解分享给大家，希望大家和我一起不断完善相关内容，谢谢您！

Hello, the content of the repository is very comprehensive and very beneficial. Could you introduce my notes and share my understanding of autopilot with others? I hope you can continue to improve the relevant content with me, thank you!

Autopilot-Updating-Notes

Bumps tensorflow from 2.6.2 to 2.9.3.

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

I'm trying to use DeepFM to predict scores for the world cup, which has 2 outputs the [left score, right score]. For the y values, the model takes in a (35245, 2) shape, and runs, but only gives one value for the output. Basically I'm asking how to set the amount of nodes in the output layer to 2 instead of 1.

Y_train looks like this:

   home_score  away_score
         0.0         1.0
         1.0         1.0
         0.0         1.0
         1.0         2.0

The model is:

 model = DeepFM(linear_feature_columns,dnn_feature_columns,task='regression')
 model.compile("adam", "mean_squared_error",
               metrics=['mean_squared_error'], )
history = model.fit(train_model_input, Y_train.values,
                    batch_size=256, epochs=10, verbose=2, validation_split=0.2, )
pred_ans = model.predict(test_model_input, batch_size=256)

Using google colab