2020-11-09 Keras 深度学习，糖尿病数据

import numpy as np

from keras import Sequential
from keras.layers import Dense

seed=7
np.random.seed(seed)

dataset = np.loadtxt("H:\BaiduNetdiskDownload\pima-indians-diabetes .csv",delimiter=",")
#split into input (X) and output (Y) variables
X=dataset[:,0:8]
Y=dataset[:,8]
#creat a model
model = Sequential()
model.add(Dense(12,input_dim=8,kernel_initializer='uniform',activation='relu'))
model.add(Dense(8,kernel_initializer='uniform',activation='relu'))
model.add(Dense(1,kernel_initializer='uniform',activation='sigmoid'))

#compile model

# model.add(Dense(output dim =500))
# model.add(Activation('sigmoid'))
#
# model.add(Dense(output dim =10))
# model.add(Activation('softmax'))

model.compile(loss='binary_crossentropy',optimizer='adam',metrics=['accuracy']) # fit the model
model.fit(X,Y,batch_size=100,epochs=20)  #mini_batch

#evaluate the model
scores = model.evaluate(X,Y)
print("%s: %.2f%%" % (model.metrics_names[1],scores[1]*100))

C:\Users\Administrator\PycharmProjects\pythonProject\venv\Scripts\python.exe C:/Users/Administrator/Desktop/光学系统/leastSquareMutil.py
2020-11-09 04:56:20.387000: W tensorflow/stream_executor/platform/default/dso_loader.cc:59] Could not load dynamic library 'cudart64_101.dll'; dlerror: cudart64_101.dll not found
2020-11-09 04:56:20.387000: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
2020-11-09 04:56:28.372000: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library nvcuda.dll
2020-11-09 04:56:28.556000: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1716] Found device 0 with properties: 
pciBusID: 0000:01:00.0 name: GeForce GTX 950M computeCapability: 5.0
coreClock: 0.928GHz coreCount: 5 deviceMemorySize: 2.00GiB deviceMemoryBandwidth: 74.65GiB/s
2020-11-09 04:56:28.558000: W tensorflow/stream_executor/platform/default/dso_loader.cc:59] Could not load dynamic library 'cudart64_101.dll'; dlerror: cudart64_101.dll not found
2020-11-09 04:56:28.560000: W tensorflow/stream_executor/platform/default/dso_loader.cc:59] Could not load dynamic library 'cublas64_10.dll'; dlerror: cublas64_10.dll not found
2020-11-09 04:56:28.560000: W tensorflow/stream_executor/platform/default/dso_loader.cc:59] Could not load dynamic library 'cufft64_10.dll'; dlerror: cufft64_10.dll not found
2020-11-09 04:56:28.560000: W tensorflow/stream_executor/platform/default/dso_loader.cc:59] Could not load dynamic library 'curand64_10.dll'; dlerror: curand64_10.dll not found
2020-11-09 04:56:28.561000: W tensorflow/stream_executor/platform/default/dso_loader.cc:59] Could not load dynamic library 'cusolver64_10.dll'; dlerror: cusolver64_10.dll not found
2020-11-09 04:56:28.563000: W tensorflow/stream_executor/platform/default/dso_loader.cc:59] Could not load dynamic library 'cusparse64_10.dll'; dlerror: cusparse64_10.dll not found
2020-11-09 04:56:28.565000: W tensorflow/stream_executor/platform/default/dso_loader.cc:59] Could not load dynamic library 'cudnn64_7.dll'; dlerror: cudnn64_7.dll not found
2020-11-09 04:56:28.566000: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1753] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform.
Skipping registering GPU devices...
2020-11-09 04:56:28.576000: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)to use the following CPU instructions in performance-critical operations:  AVX2
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2020-11-09 04:56:28.636000: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x1768ae20 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2020-11-09 04:56:28.636000: I tensorflow/compiler/xla/service/service.cc:176]   StreamExecutor device (0): Host, Default Version
2020-11-09 04:56:28.637000: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1257] Device interconnect StreamExecutor with strength 1 edge matrix:
2020-11-09 04:56:28.637000: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1263]      
Epoch 1/20
8/8 [==============================] - 0s 875us/step - loss: 0.6921 - accuracy: 0.6510
Epoch 2/20
8/8 [==============================] - 0s 750us/step - loss: 0.6898 - accuracy: 0.6510
Epoch 3/20
8/8 [==============================] - 0s 750us/step - loss: 0.6868 - accuracy: 0.6510
Epoch 4/20
8/8 [==============================] - 0s 750us/step - loss: 0.6827 - accuracy: 0.6510
Epoch 5/20
8/8 [==============================] - 0s 875us/step - loss: 0.6760 - accuracy: 0.6510
Epoch 6/20
8/8 [==============================] - 0s 625us/step - loss: 0.6712 - accuracy: 0.6510
Epoch 7/20
8/8 [==============================] - 0s 1ms/step - loss: 0.6676 - accuracy: 0.6510
Epoch 8/20
8/8 [==============================] - 0s 1000us/step - loss: 0.6654 - accuracy: 0.6510
Epoch 9/20
8/8 [==============================] - 0s 2ms/step - loss: 0.6627 - accuracy: 0.6510
Epoch 10/20
8/8 [==============================] - 0s 1ms/step - loss: 0.6604 - accuracy: 0.6510
Epoch 11/20
8/8 [==============================] - 0s 3ms/step - loss: 0.6582 - accuracy: 0.6510
Epoch 12/20
8/8 [==============================] - 0s 2ms/step - loss: 0.6563 - accuracy: 0.6510
Epoch 13/20
8/8 [==============================] - 0s 2ms/step - loss: 0.6540 - accuracy: 0.6510
Epoch 14/20
8/8 [==============================] - 0s 2ms/step - loss: 0.6506 - accuracy: 0.6510
Epoch 15/20
8/8 [==============================] - 0s 875us/step - loss: 0.6474 - accuracy: 0.6510
Epoch 16/20
8/8 [==============================] - 0s 1000us/step - loss: 0.6444 - accuracy: 0.6510
Epoch 17/20
8/8 [==============================] - 0s 750us/step - loss: 0.6408 - accuracy: 0.6510
Epoch 18/20
8/8 [==============================] - 0s 1000us/step - loss: 0.6398 - accuracy: 0.6510
Epoch 19/20
8/8 [==============================] - 0s 625us/step - loss: 0.6357 - accuracy: 0.6510
Epoch 20/20
8/8 [==============================] - 0s 875us/step - loss: 0.6326 - accuracy: 0.6510
24/24 [==============================] - 0s 792us/step - loss: 0.6297 - accuracy: 0.6510
accuracy: 65.10%

Process finished with exit code 0