kl8_anylysis

1. 选10中奖率太低，建议改成中奖率最高的选4、选5，如果追求稍微高点的奖金可以选7
2. matplotlib 聚类图和原项目numpy版本冲突，建议删除这个代码即可
3. 选号方法，只要热号(近10-20期出现较多的号码)、跳号、邻号、斜连号等
   不知是否可以建立个qq群以便更好的讨论细节

看到大佬最近都在更新统计学的部分，就是KL8_AYALYSIS这几个，请问最近更新的有什么用呢？

OS：win7_x64
python : 3.8.17

(py38) D:\Lottery\predict_Lottery_ticket-main>
(py38) D:\Lottery\predict_Lottery_ticket-main>python get_data.py --name ssq
Traceback (most recent call last):
File "get_data.py", line 7, in
from common import get_data_run
File "D:\Lottery\predict_Lottery_ticket-main\common.py", line 13, in
import tensorflow as tf
ModuleNotFoundError: No module named 'tensorflow'

(py38) D:\Lottery\predict_Lottery_ticket-main>pip3 show tensorflow
WARNING: Package(s) not found: tensorflow

Traceback (most recent call last):
File "E:\predict_Lottery_ticket-main\run_predict.py", line 52, in
_data, title = predict_run(args.name)
File "E:\predict_Lottery_ticket-main\common.py", line 422, in predict_run
predict_features = try_error(name, data, windows_size)
File "E:\predict_Lottery_ticket-main\common.py", line 320, in try_error
if len(predict_features) != windows_size:
TypeError: object of type 'NoneType' has no len()Traceback (most recent call last):
File "E:\predict_Lottery_ticket-main\run_predict.py", line 52, in
_data, title = predict_run(args.name)
File "E:\predict_Lottery_ticket-main\common.py", line 422, in predict_run
predict_features = try_error(name, data, windows_size)
File "E:\predict_Lottery_ticket-main\common.py", line 320, in try_error
if len(predict_features) != windows_size:
TypeError: object of type 'NoneType' has no len()

File "C:\Users\71539\AppData\Roaming\Python\Python310\site-packages\tensorflow\python\training\saver.py", line 1599, in _import_meta_graph_with_return_elements
meta_graph_def = meta_graph.read_meta_graph_file(meta_graph_or_file)
File "C:\Users\71539\AppData\Roaming\Python\Python310\site-packages\tensorflow\python\framework\meta_graph.py", line 611, in read_meta_graph_file
raise IOError(f"File does not exist. Received: {filename}.")
OSError: File does not exist. Received: T:\全系列彩票预测\predict_Lottery_ticket-main\predict_Lottery_ticket-main/model//ssq/3/red_ball_model/red_ball_model.ckpt.meta.
(base) PS T:\全系列彩票预测\predict_Lottery_ticket-main\predict_Lottery_ticket-main> python run_predict.py --name ssq kl8
2024-04-05 22:27:23.339476: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable TF_ENABLE_ONEDNN_OPTS=0.
WARNING:tensorflow:From C:\Users\71539\AppData\Roaming\Python\Python310\site-packages\keras\src\losses.py:2976: The name tf.losses.sparse_softmax_cross_entropy is deprecated. Please use tf.compat.v1.losses.sparse_softmax_cross_entropy instead.

WARNING:tensorflow:From T:\全系列彩票预测\predict_Lottery_ticket-main\predict_Lottery_ticket-main\common.py:219: The name tf.disable_eager_execution is deprecated. Please use tf.compat.v1.disable_eager_execution instead.

2024-04-05 22:27:28.448749: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: SSE SSE2 SSE3 SSE4.1 SSE4.2 AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
usage: run_predict.py [-h] [--name NAME] [--windows_size WINDOWS_SIZE] [--cq CQ]
run_predict.py: error: unrecognized arguments: kl8
(base) PS T:\全系列彩票预测\predict_Lottery_ticket-main\predict_Lottery_ticket-main>

基于历史数据的分析似乎arima模型比lstm更好，功能和大佬之前的analysis文件类似。

具体报错信息如下，较多，烦请大佬看看是什么原因导致的：
2023-11-21 11:56:07.314324: W tensorflow/c/c_api.cc:304] Operation '{name:'embedding/embeddings/Assign' id:17 op device:{requested: '', assigned: ''} def:{{{node embedding/embeddings/Assign}} = AssignVariableOp[_has_manual_control_dependencies=true, dtype=DT_FLOAT, validate_shape=false](embedding/embeddings, embedding/embeddings/Initializer/stateless_random_uniform)}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session.
2023-11-21 11:56:07.317735: W tensorflow/c/c_api.cc:304] Operation '{name:'strided_slice/stack_1' id:23 op device:{requested: '', assigned: ''} def:{{{node strided_slice/stack_1}} = Const_has_manual_control_dependencies=true, dtype=DT_INT32, value=Tensor<type: int32 shape: [4] values: 0 0 1...>}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session.
2023-11-21 11:56:07.318914: W tensorflow/c/c_api.cc:304] Operation '{name:'strided_slice/stack_2' id:24 op device:{requested: '', assigned: ''} def:{{{node strided_slice/stack_2}} = Const_has_manual_control_dependencies=true, dtype=DT_INT32, value=Tensor<type: int32 shape: [4] values: 1 1 1...>}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session.
2023-11-21 11:56:07.373457: W tensorflow/c/c_api.cc:304] Operation '{name:'lstm/lstm_cell/bias/Assign' id:75 op device:{requested: '', assigned: ''} def:{{{node lstm/lstm_cell/bias/Assign}} = AssignVariableOp[_has_manual_control_dependencies=true, dtype=DT_FLOAT, validate_shape=false](lstm/lstm_cell/bias, lstm/lstm_cell/bias/Initializer/concat)}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session.
2023-11-21 11:56:07.386801: W tensorflow/c/c_api.cc:304] Operation '{name:'strided_slice_1/stack_1' id:287 op device:{requested: '', assigned: ''} def:{{{node strided_slice_1/stack_1}} = Const_has_manual_control_dependencies=true, dtype=DT_INT32, value=Tensor<type: int32 shape: [4] values: 0 0 2...>}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session.
2023-11-21 11:56:07.394237: W tensorflow/c/c_api.cc:304] Operation '{name:'strided_slice_1/stack_2' id:288 op device:{requested: '', assigned: ''} def:{{{node strided_slice_1/stack_2}} = Const_has_manual_control_dependencies=true, dtype=DT_INT32, value=Tensor<type: int32 shape: [4] values: 1 1 1...>}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session.
2023-11-21 11:56:07.461841: W tensorflow/c/c_api.cc:304] Operation '{name:'lstm_1/lstm_cell/kernel/Assign' id:309 op device:{requested: '', assigned: ''} def:{{{node lstm_1/lstm_cell/kernel/Assign}} = AssignVariableOp[_has_manual_control_dependencies=true, dtype=DT_FLOAT, validate_shape=false](lstm_1/lstm_cell/kernel, lstm_1/lstm_cell/kernel/Initializer/stateless_random_uniform)}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session.
2023-11-21 11:56:07.481893: W tensorflow/c/c_api.cc:304] Operation '{name:'strided_slice_2/stack_1' id:553 op device:{requested: '', assigned: ''} def:{{{node strided_slice_2/stack_1}} = Const_has_manual_control_dependencies=true, dtype=DT_INT32, value=Tensor<type: int32 shape: [4] values: 0 0 3...>}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session.
2023-11-21 11:56:07.495515: W tensorflow/c/c_api.cc:304] Operation '{name:'strided_slice_2/stack_2' id:554 op device:{requested: '', assigned: ''} def:{{{node strided_slice_2/stack_2}} = Const_has_manual_control_dependencies=true, dtype=DT_INT32, value=Tensor<type: int32 shape: [4] values: 1 1 1...>}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session.
2023-11-21 11:56:07.577133: W tensorflow/c/c_api.cc:304] Operation '{name:'lstm_2/lstm_cell/recurrent_kernel/Assign' id:598 op device:{requested: '', assigned: ''} def:{{{node lstm_2/lstm_cell/recurrent_kernel/Assign}} = AssignVariableOp[_has_manual_control_dependencies=true, dtype=DT_FLOAT, validate_shape=false](lstm_2/lstm_cell/recurrent_kernel, lstm_2/lstm_cell/recurrent_kernel/Initializer/mul_1)}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session.
2023-11-21 11:56:07.604845: W tensorflow/c/c_api.cc:304] Operation '{name:'strided_slice_3/stack_1' id:819 op device:{requested: '', assigned: ''} def:{{{node strided_slice_3/stack_1}} = Const_has_manual_control_dependencies=true, dtype=DT_INT32, value=Tensor<type: int32 shape: [4] values: 0 0 4...>}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session.
2023-11-21 11:56:07.625097: W tensorflow/c/c_api.cc:304] Operation '{name:'strided_slice_3/stack_2' id:820 op device:{requested: '', assigned: ''} def:{{{node strided_slice_3/stack_2}} = Const_has_manual_control_dependencies=true, dtype=DT_INT32, value=Tensor<type: int32 shape: [4] values: 1 1 1...>}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session.
2023-11-21 11:56:07.718605: W tensorflow/c/c_api.cc:304] Operation '{name:'lstm_3/lstm_cell/bias/Assign' id:873 op device:{requested: '', assigned: ''} def:{{{node lstm_3/lstm_cell/bias/Assign}} = AssignVariableOp[_has_manual_control_dependencies=true, dtype=DT_FLOAT, validate_shape=false](lstm_3/lstm_cell/bias, lstm_3/lstm_cell/bias/Initializer/concat)}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session.
2023-11-21 11:56:07.754472: W tensorflow/c/c_api.cc:304] Operation '{name:'strided_slice_4/stack_1' id:1085 op device:{requested: '', assigned: ''} def:{{{node strided_slice_4/stack_1}} = Const_has_manual_control_dependencies=true, dtype=DT_INT32, value=Tensor<type: int32 shape: [4] values: 0 0 5...>}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session.
2023-11-21 11:56:07.781493: W tensorflow/c/c_api.cc:304] Operation '{name:'strided_slice_4/stack_2' id:1086 op device:{requested: '', assigned: ''} def:{{{node strided_slice_4/stack_2}} = Const_has_manual_control_dependencies=true, dtype=DT_INT32, value=Tensor<type: int32 shape: [4] values: 1 1 1...>}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session.
2023-11-21 11:56:07.890400: W tensorflow/c/c_api.cc:304] Operation '{name:'lstm_4/lstm_cell/kernel/Assign' id:1107 op device:{requested: '', assigned: ''} def:{{{node lstm_4/lstm_cell/kernel/Assign}} = AssignVariableOp[_has_manual_control_dependencies=true, dtype=DT_FLOAT, validate_shape=false](lstm_4/lstm_cell/kernel, lstm_4/lstm_cell/kernel/Initializer/stateless_random_uniform)}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session.
2023-11-21 11:56:07.935544: W tensorflow/c/c_api.cc:304] Operation '{name:'strided_slice_5/stack_1' id:1351 op device:{requested: '', assigned: ''} def:{{{node strided_slice_5/stack_1}} = Const_has_manual_control_dependencies=true, dtype=DT_INT32, value=Tensor<type: int32 shape: [4] values: 0 0 6...>}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session.
2023-11-21 11:56:07.967973: W tensorflow/c/c_api.cc:304] Operation '{name:'strided_slice_5/stack_2' id:1352 op device:{requested: '', assigned: ''} def:{{{node strided_slice_5/stack_2}} = Const_has_manual_control_dependencies=true, dtype=DT_INT32, value=Tensor<type: int32 shape: [4] values: 1 1 1...>}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session.
2023-11-21 11:56:08.085564: W tensorflow/c/c_api.cc:304] Operation '{name:'lstm_5/lstm_cell/bias/Assign' id:1405 op device:{requested: '', assigned: ''} def:{{{node lstm_5/lstm_cell/bias/Assign}} = AssignVariableOp[_has_manual_control_dependencies=true, dtype=DT_FLOAT, validate_shape=false](lstm_5/lstm_cell/bias, lstm_5/lstm_cell/bias/Initializer/concat)}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session.
2023-11-21 11:56:08.390042: W tensorflow/c/c_api.cc:304] Operation '{name:'dense/kernel/Assign' id:1886 op device:{requested: '', assigned: ''} def:{{{node dense/kernel/Assign}} = AssignVariableOp[_has_manual_control_dependencies=true, dtype=DT_FLOAT, validate_shape=false](dense/kernel, dense/kernel/Initializer/stateless_random_uniform)}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session.
2023-11-21 11:56:08.481486: W tensorflow/c/c_api.cc:304] Operation '{name:'Slice_2/size' id:2228 op device:{requested: '', assigned: ''} def:{{{node Slice_2/size}} = Const_has_manual_control_dependencies=true, dtype=DT_INT32, value=Tensor<type: int32 shape: [3] values: -1 -1 -1>}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session.
2023-11-21 11:56:08.586300: W tensorflow/c/c_api.cc:304] Operation '{name:'Slice_1/begin' id:2223 op device:{requested: '', assigned: ''} def:{{{node Slice_1/begin}} = Const_has_manual_control_dependencies=true, dtype=DT_INT32, value=Tensor<type: int32 shape: [3] values: 0 0 0>}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session.
2023-11-21 11:56:08.663866: W tensorflow/c/c_api.cc:304] Operation '{name:'Slice_1/size' id:2224 op device:{requested: '', assigned: ''} def:{{{node Slice_1/size}} = Const_has_manual_control_dependencies=true, dtype=DT_INT32, value=Tensor<type: int32 shape: [3] values: -1 1 -1>}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session.
2023-11-21 11:56:08.741485: W tensorflow/c/c_api.cc:304] Operation '{name:'SequenceMask/Range' id:2241 op device:{requested: '', assigned: ''} def:{{{node SequenceMask/Range}} = Range[Tidx=DT_INT32, _has_manual_control_dependencies=true](SequenceMask/Const, strided_slice_8, SequenceMask/Const_1)}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session.
2023-11-21 11:56:08.818814: W tensorflow/c/c_api.cc:304] Operation '{name:'SequenceMask/ExpandDims/dim' id:2242 op device:{requested: '', assigned: ''} def:{{{node SequenceMask/ExpandDims/dim}} = Const_has_manual_control_dependencies=true, dtype=DT_INT32, value=Tensor<type: int32 shape: [] values: -1>}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session.
2023-11-21 11:56:08.894904: W tensorflow/c/c_api.cc:304] Operation '{name:'Const_1' id:2230 op device:{requested: '', assigned: ''} def:{{{node Const_1}} = Const_has_manual_control_dependencies=true, dtype=DT_INT32, value=Tensor<type: int32 shape: [] values: 0>}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session.
2023-11-21 11:56:08.972938: W tensorflow/c/c_api.cc:304] Operation '{name:'sub_1/y' id:2231 op device:{requested: '', assigned: ''} def:{{{node sub_1/y}} = Const_has_manual_control_dependencies=true, dtype=DT_INT32, value=Tensor<type: int32 shape: [] values: 1>}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session.
2023-11-21 11:56:09.630670: W tensorflow/c/c_api.cc:304] Operation '{name:'Variable/Assign' id:1913 op device:{requested: '', assigned: ''} def:{{{node Variable/Assign}} = AssignVariableOp[_has_manual_control_dependencies=true, dtype=DT_FLOAT, validate_shape=false](Variable, stateless_random_uniform)}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session.

现在训练中遇到的问题：

1. 当设置BatchSize大于1后无法预测，需要设置BatchSize为1重新训练，想问问各位大佬这样重新训练后对模型的预测结果是否会有影响
2. 当设置BatchSize大于1，比如512,1024后，多次训练会导致loss值为Nan的错误。
   望哪位大佬帮忙解答下。

但是选7返奖率的数学期望也能达到57%左右....60%是否依然表示和随机选数其实是一样呢

red_sequence_len应该是6
其他参数不知道有什么作用 能否解释下参数意义？

This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: SSE SSE2 SSE3 SSE4.1 SSE4.2 AVX AVX2 AVX_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
Traceback (most recent call last):
File "D:\Files\python object\predict_Lottery_ticket-main2\run_train_model.py", line 17, in
from modeling import LstmWithCRFModel, SignalLstmModel, tf
File "D:\Files\python object\predict_Lottery_ticket-main2\modeling.py", line 8, in
from tensorflow_addons.text.crf import crf_decode, crf_log_likelihood
ModuleNotFoundError: No module named 'tensorflow_addons'

KL8_ANALYSIS和LSTM模型应该不是一回事吧？一个是自主寻找数字规律并随即生成符合规律的数，另一个是让模型自己找规律。看到大佬最近都在更新KL8_ANALYSIS，难道说是模型无法发现诸如奇偶性、冷热号这些规律吗？

正在创建【七星彩】数据集...
2023-06-01 13:58:48.902 | INFO | common:get_data_run:23 - 【七星彩】最新一期期号：23061
2023-06-01 13:58:48.903 | INFO | common:get_data_run:24 - 正在获取【七星彩】数据。。。
2023-06-01 13:58:49.603 | INFO | common:get_data_run:32 - 【七星彩】数据准备就绪，共2892期, 下一步可训练模型...
2023-06-01 13:58:49.605 | INFO | main:action:359 - 正在创建【七星彩】数据集...
2023-06-01 13:58:49.609 | INFO | main:create_train_data:65 - 训练数据已加载!
2023-06-01 13:58:49.610 | INFO | main:create_train_data:68 - 训练集数据维度: (2892, 7)
2023-06-01 13:58:49.614 | INFO | main:action:364 - 开始训练【七星彩】红球模型...
2023-06-01 13:58:49.615 | INFO | main:train_red_ball_model:99 - 特征数据维度: (2888, 3, 7)
2023-06-01 13:58:49.615 | INFO | main:train_red_ball_model:100 - 标签数据维度: (2888, 7)
2023-06-01 13:58:49.637597: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:354] MLIR V1 optimization pass is not enabled
2023-06-01 13:58:52.521392: W tensorflow/core/common_runtime/forward_type_inference.cc:332] Type inference failed. This indicates an invalid graph that escaped type checking. Error message: INVALID_ARGUMENT: expected compatible input types, but input 1:
type_id: TFT_OPTIONAL
args {
type_id: TFT_PRODUCT
args {
type_id: TFT_TENSOR
args {
type_id: TFT_INT32
}
}
}
is neither a subtype nor a supertype of the combined inputs preceding it:
type_id: TFT_OPTIONAL
args {
type_id: TFT_PRODUCT
args {
type_id: TFT_TENSOR
args {
type_id: TFT_FLOAT
}
}
}

    while inferring type of node 'cond_1/output/_1862'

2023-06-01 13:58:55.961582: W tensorflow/c/c_api.cc:349] Operation '{name:'lstm_6/while' id:1828 op device:{requested: '', assigned: ''} def:{{{node lstm_6/while}} = While[T=[DT_INT32, DT_INT32, DT_INT32, DT_VARIANT, DT_FLOAT, 13037780287242672343, DT_VARIANT, DT_VARIANT, DT_VARIANT, DT_VARIANT, DT_VARIANT], _lower_using_switch_merge=true, _num_original_outputs=45, _read_only_resource_inputs=[8, 9, 10], _stateful_parallelism=false, body=lstm_6_while_body_2931[], cond=lstm_6_while_cond_2930[], output_shapes=[[], [], [], [], [1,10], 8875109386904515972, [], [], [], [], []], parallel_iterations=32](lstm_6/while/loop_counter, lstm_6/while/maximum_iterations, lstm_6/time, lstm_6/TensorArrayV2_1, lstm_6/zeros, lstm_6/zeros_1, lstm_6/strided_slice_1, lstm_6/TensorArrayUnstack/TensorListFromTensor, lstm_6/lstm_cell_6/kernel, lstm_6/lstm_cell_6/recurrent_kernel, lstm_6/lstm_cell_6/bias, lstm_6/while/EmptyTensorList, lstm_6/while/EmptyTensorList_1, lstm_6/while/EmptyTensorList_2, lstm_6/while/EmptyTensorList_3, lstm_6/while/EmptyTensorList_4, lstm_6/while/EmptyTensorList_5, lstm_6/while/EmptyTensorList_6, lstm_6/while/EmptyTensorList_7, lstm_6/while/EmptyTensorList_8, lstm_6/while/EmptyTensorList_9, lstm_6/while/EmptyTensorList_10, lstm_6/while/EmptyTensorList_11, lstm_6/while/EmptyTensorList_12, lstm_6/while/EmptyTensorList_13, lstm_6/while/EmptyTensorList_14, lstm_6/while/EmptyTensorList_15, lstm_6/while/EmptyTensorList_16, lstm_6/while/EmptyTensorList_17, lstm_6/while/EmptyTensorList_18, lstm_6/while/EmptyTensorList_19, lstm_6/while/EmptyTensorList_20, lstm_6/while/EmptyTensorList_21, lstm_6/while/EmptyTensorList_22, lstm_6/while/EmptyTensorList_23, lstm_6/while/EmptyTensorList_24, lstm_6/while/EmptyTensorList_25, lstm_6/while/EmptyTensorList_26, lstm_6/while/EmptyTensorList_27, lstm_6/while/EmptyTensorList_28, lstm_6/while/EmptyTensorList_29, lstm_6/while/EmptyTensorList_30, lstm_6/while/EmptyTensorList_31, lstm_6/while/EmptyTensorList_32, lstm_6/while/EmptyTensorList_33)}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session.
Traceback (most recent call last):
File "C:\Users\eru1030\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\client\session.py", line 1378, in _do_call
return fn(*args)
File "C:\Users\eru1030\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\client\session.py", line 1361, in _run_fn
return self._call_tf_sessionrun(options, feed_dict, fetch_list,
File "C:\Users\eru1030\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\client\session.py", line 1454, in _call_tf_sessionrun
return tf_session.TF_SessionRun_wrapper(self._session, options, feed_dict,
tensorflow.python.framework.errors_impl.InvalidArgumentError: indices[0,0,6] = 13 is not in [0, 10)
[[{{node embedding/embedding_lookup}}]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "run_train_model.py", line 515, in
run(args.name, list_windows_size)
File "run_train_model.py", line 392, in run
action(name)
File "run_train_model.py", line 366, in action
train_red_ball_model(name, x_data=train_data["red"]["x_data"], y_data=train_data["red"]["y_data"])
File "run_train_model.py", line 160, in train_red_ball_model
, loss, pred = sess.run([
File "C:\Users\eru1030\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\client\session.py", line 968, in run
result = self._run(None, fetches, feed_dict, options_ptr,
File "C:\Users\eru1030\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\client\session.py", line 1191, in _run
results = self._do_run(handle, final_targets, final_fetches,
File "C:\Users\eru1030\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\client\session.py", line 1371, in _do_run
return self._do_call(_run_fn, feeds, fetches, targets, options,
File "C:\Users\eru1030\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\client\session.py", line 1397, in _do_call
raise type(e)(node_def, op, message) # pylint: disable=no-value-for-parameter
tensorflow.python.framework.errors_impl.InvalidArgumentError: Graph execution error:

Detected at node 'embedding/embedding_lookup' defined at (most recent call last):
File "run_train_model.py", line 515, in
run(args.name, list_windows_size)
File "run_train_model.py", line 392, in run
action(name)
File "run_train_model.py", line 366, in action
train_red_ball_model(name, x_data=train_data["red"]["x_data"], y_data=train_data["red"]["y_data"])
File "run_train_model.py", line 102, in train_red_ball_model
red_ball_model = LstmWithCRFModel(
File "C:\Users\eru1030\Desktop\predict_Lottery_ticket-main\modeling.py", line 38, in init
embedding = tf.keras.layers.Embedding(words_size, embedding_size)(self._inputs)
File "C:\Users\eru1030\AppData\Roaming\Python\Python38\site-packages\keras\engine\base_layer_v1.py", line 838, in call
outputs = call_fn(cast_inputs, *args, **kwargs)
File "C:\Users\eru1030\AppData\Roaming\Python\Python38\site-packages\keras\layers\core\embedding.py", line 208, in call
out = tf.nn.embedding_lookup(self.embeddings, inputs)
Node: 'embedding/embedding_lookup'
indices[0,0,6] = 13 is not in [0, 10)
[[{{node embedding/embedding_lookup}}]]

Original stack trace for 'embedding/embedding_lookup':
File "run_train_model.py", line 515, in
run(args.name, list_windows_size)
File "run_train_model.py", line 392, in run
action(name)
File "run_train_model.py", line 366, in action
train_red_ball_model(name, x_data=train_data["red"]["x_data"], y_data=train_data["red"]["y_data"])
File "run_train_model.py", line 102, in train_red_ball_model
red_ball_model = LstmWithCRFModel(
File "C:\Users\eru1030\Desktop\predict_Lottery_ticket-main\modeling.py", line 38, in init
embedding = tf.keras.layers.Embedding(words_size, embedding_size)(self._inputs)
File "C:\Users\eru1030\AppData\Roaming\Python\Python38\site-packages\keras\engine\base_layer_v1.py", line 838, in call
outputs = call_fn(cast_inputs, *args, **kwargs)
File "C:\Users\eru1030\AppData\Roaming\Python\Python38\site-packages\keras\layers\core\embedding.py", line 208, in call
out = tf.nn.embedding_lookup(self.embeddings, inputs)
File "C:\Users\eru1030\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\util\traceback_utils.py", line 150, in error_handler
return fn(*args, **kwargs)
File "C:\Users\eru1030\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\util\dispatch.py", line 1176, in op_dispatch_handler
return dispatch_target(*args, **kwargs)
File "C:\Users\eru1030\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\ops\embedding_ops.py", line 402, in embedding_lookup_v2
return embedding_lookup(params, ids, "div", name, max_norm=max_norm)
File "C:\Users\eru1030\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\util\traceback_utils.py", line 150, in error_handler
return fn(*args, **kwargs)
File "C:\Users\eru1030\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\util\dispatch.py", line 1176, in op_dispatch_handler
return dispatch_target(*args, **kwargs)
File "C:\Users\eru1030\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\ops\embedding_ops.py", line 330, in embedding_lookup
return _embedding_lookup_and_transform(
File "C:\Users\eru1030\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\ops\embedding_ops.py", line 144, in _embedding_lookup_and_transform
array_ops.gather(params[0], ids, name=name), ids, max_norm)
File "C:\Users\eru1030\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\util\traceback_utils.py", line 150, in error_handler
return fn(*args, **kwargs)
File "C:\Users\eru1030\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\util\dispatch.py", line 1176, in op_dispatch_handler
return dispatch_target(*args, **kwargs)
File "C:\Users\eru1030\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\util\deprecation.py", line 561, in new_func
return func(*args, **kwargs)
File "C:\Users\eru1030\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\ops\array_ops.py", line 5284, in gather
return params.sparse_read(indices, name=name)
File "C:\Users\eru1030\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\ops\resource_variable_ops.py", line 750, in sparse_read
value = gen_resource_variable_ops.resource_gather(
File "C:\Users\eru1030\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\ops\gen_resource_variable_ops.py", line 620, in resource_gather
_, _, _op, _outputs = _op_def_library._apply_op_helper(
File "C:\Users\eru1030\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\framework\op_def_library.py", line 797, in _apply_op_helper
op = g._create_op_internal(op_type_name, inputs, dtypes=None,
File "C:\Users\eru1030\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\framework\ops.py", line 3800, in _create_op_internal
ret = Operation(

但是预测的总体正确个数却没有比期望高太多，选4期望是中1个，我将最近的100期作为测试集，预测正确的个数差不多109个，略高于期望，但好几次限模拟能实现盈利，因为有时候一期预测中4个就是100，即使后面3期连续不中也是赚的。
想请问大佬那些盈利的训练是否可以表示模型训练较为成功，可以保存其权重、参数等数据作为日后预测用？

如题代码已照葫芦画瓢加了 PK拾 类型的获取数据、训练、预测了

from tensorflow.compat.v1.keras.layers import CuDNNLSTM as LSTM compat标红了
from tensorflow.keras.layers import LSTM keras标红了

如题，抱歉我是小白不太懂
python run_train_model.py --name kl8
python run_predict.py --name kl8
是不是这样就可以了

还有就是我训练了两次，预测号码会有些许不同。请问这个训练是会迭代的还是每次训练都是从头开始的呀

我测了了一个pytorch代码使用了独立显卡。但是这个代码运行的时候独显根本没有启动。

想模拟一些数据 都是要先python run_train_model.py --name ssq --windows_size 3,5,7 --red_epochs 1 --blue_epochs 1 --batch_size 1 #
再python run_predict.py --name ssq --windows_size 3,5,7 吗 感谢大佬

我运行analysis和cash的时候提示是以最新一期公布号码的快乐8来预测，比如今天是263期，已经公布号码了，那么请问在统计数学统计量的时候263期本身有没有算进去？如果算进去的话会不会影响各种统计量？
刚才试了下，感觉比LSTM训练的还准一些......

先说一下安装过程, protobuf版本会报错, 限定在3.20就好了, 还有一个numpy的版本改为1.18.5, 就不会报错, 还少一个Pillow组件.
其他没问题, 程序写的很好, 运行也没问题.
希望作者可以加入7乐彩的彩种, 那个没有重复号码也没有篮球, 相对来说概率会提高不少.
另外不知道作者研究过马尔可夫链, 之前看有马尔可夫链预测彩票的相关论文, 效果据说不错.

请问可以预测ssq复式号码吗？

因为用较大的batch_size训练后无法直接预测，需要用batch_size＝1再训练一次后才能预测，经过很多次我才发现，无论用较大的batch_size加上4000～5000的epochs训练到loss值有多低，因为不能预测而必须再用batch_size＝1再训练一次时会发现loss值又变得很高，也就是说没有保存和继承之前的训练结果，还请作者不厌其烦给予指点，如果保存训练结果并在下次训练时继承之前的成果

大佬，运行不起来。错误日志：
D:\study\ml\predict_Lottery_ticket_pytorch-master>python run_train_model.py --name ssq --windows_size 3,5,7 --red_epochs 1 --blue_epochs 1 --batch_size 1
2023-05-17 10:40:51.928 | INFO | main::135 - 正在创建【双色球】数据集...
2023-05-17 10:40:51.929 | INFO | main:action:95 - 正在创建【双色球】数据集...
2023-05-17 10:40:51.936 | INFO | common:create_train_data:41 - 训练数据已加载!
2023-05-17 10:40:51.952 | INFO | common:create_train_data:72 - 训练集数据维度: (2996, 4, 6, 1)
2023-05-17 10:40:51.955 | INFO | common:create_train_data:41 - 训练数据已加载!
2023-05-17 10:40:52.012 | INFO | common:create_train_data:72 - 训练集数据维度: (2996, 4, 6, 1)
2023-05-17 10:40:52.017 | INFO | main:action:100 - 开始训练【双色球】红球模型...
2023-05-17 10:40:52.021 | INFO | main:train_ball_model:57 - 标签数据维度: (2996, 4, 6, 1)
0%| | 0/1 [00:00<?, ?it/s]Traceback (most recent call last):
File "D:\study\ml\predict_Lottery_ticket_pytorch-master\run_train_model.py", line 177, in
run(args.name, list_windows_size)
File "D:\study\ml\predict_Lottery_ticket_pytorch-master\run_train_model.py", line 124, in run
action(name)
File "D:\study\ml\predict_Lottery_ticket_pytorch-master\run_train_model.py", line 102, in action
train_ball_model(name, dataset=red_data, sub_name="红球")
File "D:\study\ml\predict_Lottery_ticket_pytorch-master\run_train_model.py", line 77, in train_ball_model
y_pred = model(x.float())
File "C:\Python310\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "D:\study\ml\predict_Lottery_ticket_pytorch-master\modeling.py", line 125, in forward
x = x.permute(1, 0, 2) # 将输入序列转置为 (seq_len, batch_size, input_size)
RuntimeError: permute(sparse_coo): number of dimensions in the tensor input does not match the length of the desired ordering of dimensions i.e. input.dim() = 4 is not equal to len(dims) = 3
0%| | 0/1 [00:00<?, ?it/s]

请问一定要用python3.8系统和tensflow2.3版本吗？如果用其他版本有哪些差距吗？主要是我的系统没法装ancode，在notebook上只支持python3.9，tensflow也只有2.13.版本，请问影响大吗？

作者您好，500w数据更新太慢了，经常到很晚才更新前一天的开奖数据，我在csv文件里手动增加训练后会被覆盖，请问能不能手动给本地数据增加最近1期的开奖结果？

应该要如何设置GPU来计算。

大佬好，我想问一下，篮球或者红球训练次数多了以后，每轮训练数量不拉高就会很慢，我吧每轮训的练数量拉高之后，训练完以后是不能直接预测的，我还要吧每轮训的练数量设置成1，这样是不是吧我第一次的覆盖了。我用--predict_pro 1，或者吧蓝红球的训练次数拉低以后再训练，文件都会缩小...

我的指令是这样用的，是否有错。
第一种

1. python run_train_model.py --name ssq --windows_size 3,5,7 --red_epochs 128 --blue_epochs 128 --batch_size 24
2. python run_train_model.py --name ssq --windows_size 3,5,7 --predict_pro 1
   第二种
3. python run_train_model.py --name ssq --windows_size 3,5,7 --red_epochs 128 --blue_epochs 128 --batch_size 24
4. python run_train_model.py --name ssq --windows_size 3,5,7 --red_epochs 128 --blue_epochs 128 --batch_size 24 --predict_pro 1
   上面两种是正确的吗，不知道有没有办法解决这个问题

请问kl8_running是批量生成往期数据吗？我运行了一天，好像它不会自动停止....另外请问kl8_running会自动调用kl8_cash取去验证吗？

1：数据源，现在的数据源登录不上，建议使用17500，这么多年了还是很稳定的
2：预测结果，现在预测结果就是最新的一期，可以把历史预测也打印出来吗？比如说最近50期或者100期的预测结果【整个参数，动态设定】，最好是开奖结果和预测结果一起，这样能明显的看出来之前的预测的准确性
3：预测结果的数量，也整个动态的吧，比如说，每期预测5注号，10注号

未完待续，持续交流

大佬，我发现每次使用getData获取数据样本的时候，500W的3D开奖数据不会把最新一期的放在列表内，我应该如何解决这个问题呢?

大佬，快乐8预测了20个号，但是从这20个号中选几个号的组合也太多了，能否推荐十个号

最近一直在找合适的参数，一开始命中率挺高，不知道如何找到的合适参数在连续几期验证之后严重跑偏，最近试了很多思路，依旧命中率降低，比如单轮次 多size，单size 多轮次等。
我想了想 也查询了下 Tensorflow 有反向传播算法，根据已知的数据逆向推导出相关的参数，然后再去正向预测，不知道这样的想法是否可行。我们可以通过历史数据，用最后一组逆推，依次迭代，至少逆推多次，找出合适的参数，再来验证。
我们每天对3d 排列三进行多参数的实验，但始终没有得到一个好的结果。

1、能不能自定义训练数据，有两点考量：①体彩摇奖机器从2019年12月有换新 ②想用最新一期已开奖号，对比调试合适的参数
2、config配置文件修改pls的轮数和每轮训练量貌似不生效，还是得执行的时候设置参数才行
3、高于1个batch_size训练后还得执行一遍才能预测，对于算力配置低的机器有点体验感差了。（心理作用，感觉用--predict_pro 1 参数会影响预测结果）

跪求增加排列5

您好，大佬，能否将福彩3D的预测也加进去，最近我们找到了一些规律，您有空的时候麻烦帮忙把3d的预测也加进去，我们一同研究，谢谢大佬。

大佬，能不能加入注意力机制