keras 5 predict if housing price is above median price 2

 

predict house value from unknown dataset with the trained model. (above average = 1, below average = 0)

#house.py

#train on GPU

pysical_devices = tf.config.experimental.list_physical_devices('GPU')

#print("Num GPUs Available: ", len(pysical_devices))

tf.config.experimental.set_memory_growth(pysical_devices[0], True)

#load model

model = load_model('models/house.h5')

#create test samples that are different from data samples

test_samples = [

    [10000, 6, 5, 0, 1, 0, 2, 5, 0, 500],

    [12000, 7, 5, 1, 1, 1, 3, 7, 0, 600],

    [11000, 7, 5, 0, 1, 1, 3, 6, 0, 550],

    [11000, 6, 5, 0, 1, 1, 3, 6, 0, 550],

]

test_samples = np.array(test_samples)

scaler = MinMaxScaler(feature_range=(0, 1))

scaled_test_samples = scaler.fit_transform(test_samples)

print(scaled_test_samples)

#prediction

predictions = model.predict(x=scaled_test_samples, batch_size=32, verbose=1)

#predicted output index

rounded_predictions = np.argmax(predictions, axis=-1)

print(rounded_predictions)

-------------------------------------

#logs

#scaled input

[[0.  0.  0.  0.  0.  0.  0.  0.  0.  0. ]

 [1.  1.  0.  1.  0.  1.  1.  1.  0.  1. ]

 [0.5 1.  0.  0.  0.  1.  1.  0.5 0.  0.5]

 [0.5 0.  0.  0.  0.  1.  1.  0.5 0.  0.5]]

#output

[0 1 1 0]

reference:

https://www.digitalocean.com/community/tutorials/how-to-build-a-deep-learning-model-to-predict-employee-retention-using-keras-and-tensorflow

http://chuanshuoge2.blogspot.com/2020/12/keras-4-predict-if-housing-price-is_31.html

keras 4 predict if housing price is above median price 1

goal is to predict if house value is above or below average based on 10 types of measurements

#house.py

import tensorflow as tf

from tensorflow import keras

from tensorflow.keras.models import Sequential

from tensorflow.keras.layers import Activation, Dense, Dropout

from tensorflow.keras.optimizers import Adam

from tensorflow.keras.metrics import categorical_crossentropy

from tensorflow.keras import regularizers

import numpy as np

from random import randint

from sklearn.utils import shuffle

from sklearn.preprocessing import MinMaxScaler

from sklearn.metrics import confusion_matrix

import itertools

import matplotlib.pyplot as plt

from tensorflow.keras.models import load_model

import pandas as pd

from sklearn.model_selection import train_test_split

df = pd.read_csv('data/housepricedata.csv')

#print(df.head())

dataset = df.values

#print(dataset)

samples = dataset[0:1000, 0:10]

labels = dataset[0:1000, 10]

samples, labels = shuffle(samples, labels)

#scale input between 0, 1

scaler = MinMaxScaler(feature_range=(0, 1))

scaled_train_samples = scaler.fit_transform(samples)

#split dataset 70% training, 30% testing

train_samples, test_samples, train_labels, test_labels = train_test_split(scaled_train_samples, labels, test_size=0.3)

print(train_samples.shape, train_labels.shape, test_labels.shape, test_labels.shape)

#train on GPU

pysical_devices = tf.config.experimental.list_physical_devices('GPU')

#print("Num GPUs Available: ", len(pysical_devices))

tf.config.experimental.set_memory_growth(pysical_devices[0], True)

#create model

model = Sequential([

    Dense(units=32, input_shape=(10,), activation='relu'),

    Dense(units=32, activation='relu'),

    Dense(units=32, activation='relu'),

    Dense(units=2, activation='softmax')

])

model.summary()

#training & validation

model.compile(optimizer=Adam(learning_rate=0.0001), loss='sparse_categorical_crossentropy', metrics=['accuracy'])

model.fit(x=train_samples, y=train_labels, validation_split=0.1, batch_size=32, epochs=200, shuffle=True, verbose=2)

#save model

#model.save('models/house.h5')

#prediction

predictions = model.predict(x=test_samples, batch_size=32, verbose=1)

#predicted output index

rounded_predictions = np.argmax(predictions, axis=-1)

#visualize prediction accuracy - confusion matrix

cm = confusion_matrix(y_true=test_labels, y_pred=rounded_predictions)

def plot_confusion_matrix(cm, classes,

                        normalize=False,

                        title='Confusion matrix',

                        cmap=plt.cm.Blues):

    """

    This function prints and plots the confusion matrix.

    Normalization can be applied by setting `normalize=True`.

    """

    plt.imshow(cm, interpolation='nearest', cmap=cmap)

    plt.title(title)

    plt.colorbar()

    tick_marks = np.arange(len(classes))

    plt.xticks(tick_marks, classes, rotation=45)

    plt.yticks(tick_marks, classes)

    if normalize:

        cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]

        print("Normalized confusion matrix")

    else:

        print('Confusion matrix, without normalization')

    print(cm)

    thresh = cm.max() / 2.

    for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):

        plt.text(j, i, cm[i, j],

            horizontalalignment="center",

            color="white" if cm[i, j] > thresh else "black")

    plt.tight_layout()

    plt.ylabel('True label')

    plt.xlabel('Predicted label')

    plt.show()

cm_plot_labels = ['below avg', 'above_avg']

plot_confusion_matrix(cm=cm, classes=cm_plot_labels, title='Confusion Matrix')

----------------------------------------

#logs

Model: "sequential"

_________________________________________________________________

Layer (type)                 Output Shape              Param #

=================================================================

dense (Dense)                (None, 32)                352

_________________________________________________________________

dense_1 (Dense)              (None, 32)                1056

_________________________________________________________________

dense_2 (Dense)              (None, 32)                1056

_________________________________________________________________

dense_3 (Dense)              (None, 2)                 66

=================================================================

Total params: 2,530

Trainable params: 2,530

Non-trainable params: 0

_________________________________________________________________

2020-12-31 16:26:55.838065: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:116] None of the MLIR optimization passes are enabled (register

ed 2)

Epoch 1/200

2020-12-31 16:26:56.160440: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cublas64_11.dll

2020-12-31 16:26:56.347504: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cublasLt64_11.dll

20/20 - 1s - loss: 0.6870 - accuracy: 0.5032 - val_loss: 0.6569 - val_accuracy: 0.5857

Epoch 2/200

20/20 - 0s - loss: 0.6803 - accuracy: 0.5032 - val_loss: 0.6507 - val_accuracy: 0.5857

Epoch 3/200

20/20 - 0s - loss: 0.6741 - accuracy: 0.5032 - val_loss: 0.6449 - val_accuracy: 0.5857

Epoch 4/200

20/20 - 0s - loss: 0.6686 - accuracy: 0.5032 - val_loss: 0.6394 - val_accuracy: 0.5857

Epoch 5/200

20/20 - 0s - loss: 0.6636 - accuracy: 0.5032 - val_loss: 0.6352 - val_accuracy: 0.5857

...

Epoch 198/200

20/20 - 0s - loss: 0.2478 - accuracy: 0.9048 - val_loss: 0.2351 - val_accuracy: 0.8857

Epoch 199/200

20/20 - 0s - loss: 0.2472 - accuracy: 0.9048 - val_loss: 0.2351 - val_accuracy: 0.8857

Epoch 200/200

20/20 - 0s - loss: 0.2467 - accuracy: 0.9048 - val_loss: 0.2313 - val_accuracy: 0.9000

10/10 [==============================] - 0s 665us/step

Confusion matrix, without normalization

[[143  13]

 [ 17 127]]

reference:

https://www.freecodecamp.org/news/how-to-build-your-first-neural-network-to-predict-house-prices-with-keras-f8db83049159/

http://chuanshuoge2.blogspot.com/2020/12/keras-2-build-test-simple-sequential.html

Marvel's Avengers

加拿大要求持3天内阴性检测报告登机

 加拿大要求所有乘客在返回前拿到阴性检测报告！

由于近段时间以来，加拿大新增确诊病例不断攀升，导致政府不得不采取更多措施抑制疫情恶化。

就在今天（12月30日），加拿大政府间事务部长Dominic LeBlanc突然宣布了一条与华人息息相关的新规：要求所有乘客在抵达加拿大之前拿到COVID-19阴性检测报告！并且原有的14天入境隔离的规定仍然保留。

“除非绝对必要，否则我们强烈建议您不要出国旅行。”

据报道，加拿大的旅行限制将很快通知航空公司实施新规，要求乘客在登机前3天内进行新冠病毒检测，并且需持有阴性检测报告才能登机。

keras 3 save/load model

//main.py

from tensorflow.keras.models import load_model

"""

#create model

model = Sequential([

    Dense(units=16, input_shape=(1,), activation='relu'),

    Dense(units=32, activation='relu'),

    Dense(units=2, activation='softmax')

])

model.summary()

#training & validation

model.compile(optimizer=Adam(learning_rate=0.0001), loss='sparse_categorical_crossentropy', metrics=['accuracy'])

model.fit(x=scaled_train_samples, y=train_lables, validation_split=0.1, batch_size=10, epochs=30, shuffle=True, verbose=2)

#save model

model.save('models/model1.h5')

"""

#load model

model = load_model('models/model1.h5')

model.summary()

print( model.get_weights())

print(model.optimizer) 

------------------------------

#logs

Model: "sequential"

_________________________________________________________________

Layer (type)                 Output Shape              Param #

=================================================================

dense (Dense)                (None, 16)                32

_________________________________________________________________

dense_1 (Dense)              (None, 32)                544

_________________________________________________________________

dense_2 (Dense)              (None, 2)                 66

=================================================================

Total params: 642

Trainable params: 642

Non-trainable params: 0

_________________________________________________________________

[array([[ 0.26625147, -0.30418316, -0.13632423, -0.4079098 , -0.08543348,

         0.5374129 ,  0.4584436 , -0.28098437, -0.52589685, -0.4887119 ,

         0.01660078, -0.10933313, -0.04969841, -0.10267085,  0.7305957 ,

         0.38774747]], dtype=float32), array([-0.09283859,  0.        ,  0.        ,  0.        ,  0.        ,

       -0.09529305, -0.13439798,  0.        ,  0.        ,  0.        ,

        0.20418786,  0.        ,  0.        ,  0.        , -0.13027988,

       -0.1161219 ], dtype=float32), array([[ 0.26004615, -0.31933463,  0.21335247,  0.06417851, -0.12653175,

        -0.40698838, -0.2899054 , -0.3321916 , -0.51734823,  0.2656369 ,

         0.25500387, -0.23773687,  0.09429104, -0.5213961 ,  0.5374189 ,

         0.47588807,  0.15414259, -0.26182094, -0.06989337,  0.16001046,

         0.05894524,  0.5102477 ,  0.10094702, -0.20431465, -0.03044271,

        -0.25523925, -0.40259373,  0.07096949, -0.3661572 ,  0.40184933,

        -0.20758483,  0.01585205],

       [ 0.2500454 , -0.31888163,  0.12653747, -0.34026104,  0.207423  ,

         0.22553   , -0.21539871,  0.10445303, -0.30555665, -0.28052825,

         0.0283457 ,  0.21818611,  0.24136344, -0.13501498,  0.01192671,

        -0.10412639,  0.2694293 , -0.22594748, -0.06913146, -0.30933705,

         0.00475213, -0.09345153,  0.20352694, -0.163133  ,  0.13384211,

        -0.19982849, -0.28636962, -0.31544378,  0.1858199 ,  0.1552572 ,

         0.01639351,  0.2738203 ],

     ...

       [ 0.50497067, -0.30627   ],

       [ 0.3936801 , -0.17796172],

       [-0.65509355,  0.02540744],

       [-0.10199237, -0.04108612],

       [ 0.7816102 , -0.721409  ]], dtype=float32), array([ 0.09544881, -0.09544882], dtype=float32)]

<tensorflow.python.keras.optimizer_v2.adam.Adam object at 0x00000145A451F8E0>

loaded model prediction on test data set is still accurate

reference:

http://chuanshuoge2.blogspot.com/2020/12/keras-2-build-test-simple-sequential.html

想实现财富自由吗？

keras 2 build & test simple sequential model

#pycharm

import tensorflow as tf

from tensorflow import keras

from tensorflow.keras.models import Sequential

from tensorflow.keras.layers import Activation, Dense

from tensorflow.keras.optimizers import Adam

from tensorflow.keras.metrics import categorical_crossentropy

import numpy as np

from random import randint

from sklearn.utils import shuffle

from sklearn.preprocessing import MinMaxScaler

from sklearn.metrics import confusion_matrix

import itertools

import matplotlib.pyplot as plt

#create training dataset

train_lables = []

train_samples = []

for i in range(50):

    random_younger = randint(13, 64)

    train_samples.append(random_younger)

    train_lables.append(1)

    random_older = randint(65, 100)

    train_samples.append(random_older)

    train_lables.append(0)

for i in range(1000):

    random_younger = randint(13, 64)

    train_samples.append(random_younger)

    train_lables.append(0)

    random_older = randint(65, 100)

    train_samples.append(random_older)

    train_lables.append(1)

"""

for i in train_samples:

    print(i)

for i in train_lables:

    print(i)

"""

train_lables = np.array(train_lables)

train_samples = np.array(train_samples)

train_lables, train_samples = shuffle(train_lables,train_samples)

#scale input between 0, 1

scaler = MinMaxScaler(feature_range=(0, 1))

scaled_train_samples = scaler.fit_transform(train_samples.reshape(-1, 1))

"""

for i in scaled_train_samples:

    print(i)

"""

#train on GPU

pysical_devices = tf.config.experimental.list_physical_devices('GPU')

#print("Num GPUs Available: ", len(pysical_devices))

tf.config.experimental.set_memory_growth(pysical_devices[0], True)

#create model

model = Sequential([

    Dense(units=16, input_shape=(1,), activation='relu'),

    Dense(units=32, activation='relu'),

    Dense(units=2, activation='softmax')

])

model.summary()

#training & validation

model.compile(optimizer=Adam(learning_rate=0.0001), loss='sparse_categorical_crossentropy', metrics=['accuracy'])

model.fit(x=scaled_train_samples, y=train_lables, validation_split=0.1, batch_size=10, epochs=30, shuffle=True, verbose=2)

#create test set

test_labels = []

test_samples = []

for i in range(10):

    random_younger = randint(13, 64)

    test_samples.append(random_younger)

    test_labels.append(1)

    random_older = randint(65, 100)

    test_samples.append(random_older)

    test_labels.append(0)

for i in range(200):

    random_younger = randint(13, 64)

    test_samples.append(random_younger)

    test_labels.append(0)

    random_older = randint(65, 100)

    test_samples.append(random_older)

    test_labels.append(1)

test_labels = np.array(test_labels)

test_samples = np.array(test_samples)

test_labels, test_samples = shuffle(test_labels,test_samples)

scaled_test_samples = scaler.fit_transform(test_samples.reshape(-1, 1))

#prediction - [category1 probability, category 2 probability,...]

predictions = model.predict(x=scaled_test_samples, batch_size=10, verbose=0)

"""

for i in predictions:

    print(i)

"""

#predicted output index

rounded_predictions = np.argmax(predictions, axis=-1)

"""

for i in rounded_predictions:

    print(i)

"""

#visualize prediction accuracy - confusion matrix

cm = confusion_matrix(y_true=test_labels, y_pred=rounded_predictions)

def plot_confusion_matrix(cm, classes,

                        normalize=False,

                        title='Confusion matrix',

                        cmap=plt.cm.Blues):

    """

    This function prints and plots the confusion matrix.

    Normalization can be applied by setting `normalize=True`.

    """

    plt.imshow(cm, interpolation='nearest', cmap=cmap)

    plt.title(title)

    plt.colorbar()

    tick_marks = np.arange(len(classes))

    plt.xticks(tick_marks, classes, rotation=45)

    plt.yticks(tick_marks, classes)

    if normalize:

        cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]

        print("Normalized confusion matrix")

    else:

        print('Confusion matrix, without normalization')

    print(cm)

    thresh = cm.max() / 2.

    for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):

        plt.text(j, i, cm[i, j],

            horizontalalignment="center",

            color="white" if cm[i, j] > thresh else "black")

    plt.tight_layout()

    plt.ylabel('True label')

    plt.xlabel('Predicted label')

    plt.show()

cm_plot_labels = ['category_1', 'category 2']

plot_confusion_matrix(cm=cm, classes=cm_plot_labels, title='Confusion Matrix')

----------------------------

#logs

2020-12-29 13:41:17.573502: I tensorflow/compiler/jit/xla_gpu_device.cc:99] Not creating XLA devices, tf_xla_enable_xla_devices not set

Model: "sequential"

_________________________________________________________________

Layer (type)                 Output Shape              Param #

=================================================================

dense (Dense)                (None, 16)                32

_________________________________________________________________

dense_1 (Dense)              (None, 32)                544

_________________________________________________________________

dense_2 (Dense)              (None, 2)                 66

=================================================================

Total params: 642

Trainable params: 642

Non-trainable params: 0

_________________________________________________________________

2020-12-29 13:41:17.627830: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:116] None of the MLIR optimization passes are enabled (register

ed 2)

Epoch 1/30

2020-12-29 13:41:17.887594: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cublas64_11.dll

2020-12-29 13:41:18.077645: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cublasLt64_11.dll

189/189 - 1s - loss: 0.7641 - accuracy: 0.4254 - val_loss: 0.7218 - val_accuracy: 0.3952

Epoch 2/30

189/189 - 0s - loss: 0.7031 - accuracy: 0.3413 - val_loss: 0.6832 - val_accuracy: 0.4762

Epoch 3/30

189/189 - 0s - loss: 0.6598 - accuracy: 0.5667 - val_loss: 0.6546 - val_accuracy: 0.5762

Epoch 4/30

189/189 - 0s - loss: 0.6252 - accuracy: 0.6730 - val_loss: 0.6264 - val_accuracy: 0.6619

Epoch 5/30

189/189 - 0s - loss: 0.5920 - accuracy: 0.7275 - val_loss: 0.5984 - val_accuracy: 0.6952

Epoch 6/30

189/189 - 0s - loss: 0.5594 - accuracy: 0.7677 - val_loss: 0.5698 - val_accuracy: 0.7381

Epoch 7/30

189/189 - 0s - loss: 0.5285 - accuracy: 0.7884 - val_loss: 0.5427 - val_accuracy: 0.7619

Epoch 8/30

189/189 - 0s - loss: 0.4994 - accuracy: 0.8233 - val_loss: 0.5167 - val_accuracy: 0.7857

Epoch 9/30

189/189 - 0s - loss: 0.4716 - accuracy: 0.8381 - val_loss: 0.4915 - val_accuracy: 0.8238

Epoch 10/30

189/189 - 0s - loss: 0.4457 - accuracy: 0.8571 - val_loss: 0.4676 - val_accuracy: 0.8476

Epoch 11/30

189/189 - 0s - loss: 0.4219 - accuracy: 0.8714 - val_loss: 0.4461 - val_accuracy: 0.8571

Epoch 12/30

189/189 - 0s - loss: 0.4002 - accuracy: 0.8847 - val_loss: 0.4262 - val_accuracy: 0.8619

Epoch 13/30

189/189 - 0s - loss: 0.3807 - accuracy: 0.8873 - val_loss: 0.4085 - val_accuracy: 0.9000

Epoch 14/30

189/189 - 0s - loss: 0.3633 - accuracy: 0.9000 - val_loss: 0.3931 - val_accuracy: 0.9000

Epoch 15/30

189/189 - 0s - loss: 0.3481 - accuracy: 0.9011 - val_loss: 0.3795 - val_accuracy: 0.9000

Epoch 16/30

189/189 - 0s - loss: 0.3353 - accuracy: 0.9063 - val_loss: 0.3675 - val_accuracy: 0.9095

Epoch 17/30

189/189 - 0s - loss: 0.3235 - accuracy: 0.9116 - val_loss: 0.3567 - val_accuracy: 0.9143

Epoch 18/30

189/189 - 0s - loss: 0.3137 - accuracy: 0.9148 - val_loss: 0.3475 - val_accuracy: 0.9143

Epoch 19/30

189/189 - 0s - loss: 0.3051 - accuracy: 0.9180 - val_loss: 0.3396 - val_accuracy: 0.9238

Epoch 20/30

189/189 - 0s - loss: 0.2981 - accuracy: 0.9243 - val_loss: 0.3328 - val_accuracy: 0.9238

Epoch 21/30

189/189 - 0s - loss: 0.2918 - accuracy: 0.9265 - val_loss: 0.3270 - val_accuracy: 0.9238

Epoch 22/30

189/189 - 0s - loss: 0.2866 - accuracy: 0.9296 - val_loss: 0.3223 - val_accuracy: 0.9238

Epoch 23/30

189/189 - 0s - loss: 0.2822 - accuracy: 0.9323 - val_loss: 0.3175 - val_accuracy: 0.9381

Epoch 24/30

189/189 - 0s - loss: 0.2782 - accuracy: 0.9339 - val_loss: 0.3136 - val_accuracy: 0.9381

Epoch 25/30

189/189 - 0s - loss: 0.2748 - accuracy: 0.9323 - val_loss: 0.3102 - val_accuracy: 0.9381

Epoch 26/30

189/189 - 0s - loss: 0.2717 - accuracy: 0.9392 - val_loss: 0.3070 - val_accuracy: 0.9381

Epoch 27/30

189/189 - 0s - loss: 0.2691 - accuracy: 0.9370 - val_loss: 0.3042 - val_accuracy: 0.9381

Epoch 28/30

189/189 - 0s - loss: 0.2669 - accuracy: 0.9381 - val_loss: 0.3017 - val_accuracy: 0.9381

Epoch 29/30

189/189 - 0s - loss: 0.2647 - accuracy: 0.9370 - val_loss: 0.2993 - val_accuracy: 0.9381

Epoch 30/30

189/189 - 0s - loss: 0.2632 - accuracy: 0.9407 - val_loss: 0.2971 - val_accuracy: 0.9381

Confusion matrix, without normalization

[[195  15]

 [ 10 200]]

reference:

https://www.youtube.com/watch?v=qFJeN9V1ZsI&feature=youtu.be

apk downloader

https://apkcombo.com/en-ca/apk-downloader/

use dd to wipe drive

DD can be used to overwrite a disk. Doesn't matter it has protected partition or not. Replace the X for the disk to be wiped. Dd overwrites the disk with zero and allows us to format the device. 

//ubuntu terminal

//list disk

sudo lsblk

//wipe disk

sudo dd if=/dev/urandom of=/dev/sdX bs=4k

//watch dd progress

//open another terminal

sudo watch -n5 'sudo kill -USR1 $(pgrep ^dd)'

reference:

https://linuxhint.com/completely_wipe_hard_drive_ubuntu/

http://chuanshuoge2.blogspot.com/2020/12/use-dd-to-clone-drive.html

use dd to clone drive

//ubuntu terminal

//list disk

sudo lsblk

//clone disk

sudo dd if = /dev/sda of = /dev/sdb

“if” represents inputfile, and “of” represents output file. So the exact copy of /dev/sda will be available in /dev/sdb.

//watch dd progress

//open another terminal

sudo watch -n5 'sudo kill -USR1 $(pgrep ^dd)'

reference:

list disk

https://linuxhint.com/list_disks_ubuntu/

dd

https://www.geeksforgeeks.org/dd-command-linux/#:~:text=dd%20is%20a%20command%2Dline,system%20just%20like%20normal%20files.

monitor dd

https://askubuntu.com/questions/215505/how-do-you-monitor-the-progress-of-dd

What’s the difference between SATA, PCIe and NVMe?

NVMe, AHCI and IDE are transfer protocols (languages). They run on top of transfer interfaces such as PCIe or SATA (spoken, written).

SATA is the market incumbent and dominant interface for connecting an SSD to the PC. It employs the command protocol AHCI (it also supports IDE) which was built with slower spinning disks in mind rather than flash memory. SATA transfer rates begin at 150 MB/s and max out at 600 MB/s for third generation technology. For most consumers this is adequate.

PCIe (Peripheral Component Interconnect Express ) supersedes SATA as the latest high bandwidth interface that connects hardware: CPUs, GPUs, SSDs, sound cards, network cards, and other PCIe cards. Entry level PCIe 3.0 SSD speeds are two to three times faster than the older generation of SATA 3.0 SSDs mainly due to the number of channels contained by each to transfer data (roughly 10 for SATA and 25 for PCIe). However, depending on usage, real world benchmarks may not reflect this massive gain due to bottlenecks elsewhere in the PC. Here is a comparison between the two market leading NVMe and SATA SSDs: Samsung 970 Pro vs 860 Pro.

NVMe is the latest high performance and optimized protocol which supersedes AHCI and compliments PCIe technology. It offers an optimised command and completion path for use with NVMe based storage. It was developed by a consortium of manufacturers specifically for SSDs to overcome the speed bottleneck imposed by the older SATA connection. It is akin to a more efficient language between storage device and PC: one message needs to be sent for a 4GB transfer instead of two, NVMe can handle 65,000 queues of data each with 65,000 commands, instead of one queue that with the capacity for 32 commands, and it only has seven major commands (read, write, flush etc). As well as delivering better throughput NVMe offers reduced latency. NVMe will be the protocol of choice for the next generation of storage technologies such as 3D XPoint.

PCIe 4.0 refers to the fourth generation of PCIe interface which has double the bandwidth (64GB/s for a x16 slot) compared to PCIe 3.0 (32GB/s for a x16 slot), which is the usual improvement between PCIe generations. PCIe devices are forward and backward compatible, therefore a PCIe 3.0 SSD will still work on a PCIe 4.0 motherboard and conversely a PCIe 4.0 SSD would work on a PCIe 3.0 motherboard (following a software update), with performance limited by the weaker component. PCIe 4.0 devices such as AMD’s X570 motherboard chipset are coming to market in 2019.

PCIe 5.0 devices are expected to be available in 2020 and will have double of bandwidth of PCIe 4.0 (132GB/s for a x16 slot) as well as other technical enhancements. However, given that 16 lanes of PCIe 3.0 is currently sufficient for the majority of users, demand for PCIe 5.0 in the near future will mostly be driven by super users and data centres, and will co-exist alongside PCIe 4.0 devices.

reference:

https://www.userbenchmark.com/Faq/What-s-the-difference-between-SATA-PCIe-and-NVMe/105

keras 1 run tensorflow on gpu

//tensorflow supports 64 bit python version 3.5 - 3.8

//download python 3.8.7

https://www.python.org/downloads/release/python-387/

//install visual studio 2017 community

//install c++ reditributable

https://support.microsoft.com/en-us/help/2977003/the-latest-supported-visual-c-downloads

//install tensorflow

pip install --upgrade pip

pip install tensorflow

https://www.tensorflow.org/install

//cuda supported nvidia gpu

https://www.nvidia.com/en-us/geforce/technologies/cuda/supported-gpus/

//download gpu driver

https://www.nvidia.com/download/index.aspx?lang=en-us

//numpy fails to pass sanity check

pip uninstall numpy

pip install numpy==1.19.3

https://stackoverflow.com/questions/64729944/runtimeerror-the-current-numpy-installation-fails-to-pass-a-sanity-check-due-to

//tf-nightly-gpu looking for cusolver64_10.dll on a Cuda 11.1.1

revert to install cuda 11.1.0, maybe also install cuda 10.1

https://github.com/tensorflow/tensorflow/issues/44567

//install cuda toolkit 11.1.0

https://developer.nvidia.com/cuda-11.1.0-download-archive

//install cuda tookit 10.1 -maybe needed

https://developer.nvidia.com/cuda-10.1-download-archive-base

//install cudnn for cuda 11.0

https://developer.nvidia.com/rdp/cudnn-download

//5. restart windows

https://docs.nvidia.com/deeplearning/cudnn/install-guide/index.html

//main.py

import tensorflow as tf

#tf.version.VERSION

print("Num GPUs Available: ", len(tf.config.experimental.list_physical_devices('GPU')))

//pycharm terminal

(venv) C:\Users\bob\keras>python main.py

2020-12-27 10:21:57.210710: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cudart64_110.dll

2020-12-27 10:23:45.222471: I tensorflow/compiler/jit/xla_cpu_device.cc:41] Not creating XLA devices, tf_xla_enable_xla_devices not set

2020-12-27 10:23:45.375593: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library nvcuda.dll

2020-12-27 10:23:46.401095: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1720] Found device 0 with properties:

pciBusID: 0000:01:00.0 name: GeForce GTX 1060 3GB computeCapability: 6.1

coreClock: 1.7085GHz coreCount: 9 deviceMemorySize: 3.00GiB deviceMemoryBandwidth: 178.99GiB/s

2020-12-27 10:23:46.401228: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cudart64_110.dll

2020-12-27 10:23:50.660090: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cublas64_11.dll

2020-12-27 10:23:50.660490: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cublasLt64_11.dll

2020-12-27 10:23:52.598990: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cufft64_10.dll

2020-12-27 10:23:52.797069: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library curand64_10.dll

2020-12-27 10:23:54.320794: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cusolver64_10.dll

2020-12-27 10:23:54.931670: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cusparse64_11.dll

2020-12-27 10:23:55.064642: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cudnn64_8.dll

2020-12-27 10:23:55.064844: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1862] Adding visible gpu devices: 0

Num GPUs Available:  1

reference:

https://deeplizard.com/learn/video/IubEtS2JAiY

offline registry view

reference:

https://www.nirsoft.net/utils/offline_registry_view.html

lansing trip

expense

nov 16 - driving, dollarama

nov 25 - hard drive, phone

nov 26 - fuel x2, taxi, hotel 

nov 28 - pilot meal

nov 29 - hotel, fuel, pilot meal, taxi

nov 30 - tools, fuel x 2, fedex, pilot meal, hotel

dec 1 - hotel

dec 3 - hotel

dec 4 - hotel, car rental, uber

dec 5 - hotel

dec 6 - phone, hotel, uber x 4, fuel

dec 7 - hotel

dec 9 - hotel

dec 10 - hotel

dec 11 - fedex, hotel

dec 12 - rental car, gas

dec 13 - hotel

dec 15 - hotel

dec 17 - hotel, phone

dec 18 - hotel

dec 19 - hotel, dollar tree, car rental

dec 21 - hotel

dec 23 - hotel, dollar tree

dec 24 - hotel, gas, rental car, fuel

dec 25 - luggage, uber

timesheet

nov 16 - bundle - 8h

nov 26 - ferry to kalamazoo - 12h

nov27 - survey - 12h

nov28 - survey - 12h

nov29 - ferry to flint, survey - 12h

nov30 - fix bad frame - 8h

dec1 - weather down - 8h

dec2 - survey - 10h

dec3 - survey port huron - 10h

dec4 - weather down - 8h

dec5 - weather down - 8h

dec6 - ferry to morristown - 8h

dec7 - waiting for atc approval - 8h

dec8 - waiting for atc approval - 8h

dec9 - weather - 8h

dec10 - survey - 10h

dec 11 - weather - 8h

dec12 - weather -8h

dec13 - survey - 10h

dec14 - weather - 8h

dec 15 - survey - 10h

dec 16 - aircraft maintenance - 8h

dec 17 - aircraft maintenance - 8h

dec 18 - aircraft maintenance - 8h

dec 19 - aircraft maintenance - 8h

dec 20 - aircraft maintenance - 8h

dec 21 - weather - 8h

dec 22 - weather - 8h

dec 23 - survey - 8h

dec 24 - survey - 8h

dec 25 - fly back -8h

NZXT Gaming PC Build | INTEL i9-10850K | RTX 3080

Total cost of building this PC was $2400 Parts list: (Amazon & Newegg affiliate) NZXT H510 Elite Case https://amzn.to/384Abtb Newegg https://bit.ly/38AhEFF NZXT N7 Z490 Motherboard https://amzn.to/36FEbPO https://www.nzxt.com/products/n7-z490... NZXT C850W Power Supply https://amzn.to/36d8qfN Newegg https://bit.ly/3eTnRgI NZXT Kraken Z63 Liquid Cooler https://amzn.to/329PSMa Newegg https://bit.ly/36q5RXL INTEL i9-10850K CPU https://amzn.to/2TJCCcu Newegg https://bit.ly/3ljAmES Corsair Dominator Platinum RGB 16GB (2x8GB) DDR4 3200 Newegg https://bit.ly/3lpXRMu Corsair Dominator Platinum RGB 32GB (4x8GB) DDR4 3200 https://amzn.to/3fWw98r Nvidia Geforce RTX 3080 1TB WD BLACK SN750 NVMe https://amzn.to/3mS0qaJ Newegg https://bit.ly/2GROPZF 500GB WD BLACK SN750 NVMe https://amzn.to/2HXX3zP Newegg https://bit.ly/32zh07y Antec PSU Extension Cable https://amzn.to/3jOTby3 NZXT AER RGB 2 120mm https://www.nzxt.com/products/aer-rgb-2 NZXT AER RGB 2 120mm https://amzn.to/2GAVrLS NZXT AER RGB 2 140mm https://amzn.to/2TP5X5m Newegg https://bit.ly/3nh7hup

redis tutorial

TensorFlow.js - client side neural networks

YYC boarder testing

Steps to follow upon arrival at YYC: 

1. You must fill in the ArriveCAN app form with your quarantine plan and contact info up to 48 hours in advance as of Nov. 21.  
2. Complete your customs declaration with the CanBorder eDeclaration app. 
3. Complete the International Border Testing Pilot Program questionnaire (this can be done up to five days in advance of arriving).
   

Visit the Government of Alberta’s website for more information on the program.  

Batch Size in a Neural Network

需求侧改革

MobileNet Image Classification

Neural Network Optimization Algorithm

VGG16 Neural Network Visualization

Max Pooling in Convolutional Neural Networks

Convolutional Neural Networks

重卡倒车

Keras Tutorial

Software Engineer vs YouTuber

Keras vs Tensorflow vs PyTorch

roman booteen coins

速度与激情全9部

TensorFlow Beginner Full Course Edureka

斗罗大陆 第134集 小舞献祭

google lens detect car model

新材料储能电池

What If You Had to Spend a Year at Home

Deep Learning Full Course Edureka

玻色采样是什么

Neural Networks from Scratch - layers, forward pass, activation function

人脸识别 -> 卫星遥控 -> 狙击 -> 自爆

World's Biggest Things

九章量子计算机

Concurrency in Go

Sub-1% Mortgage Rates Come to Canada, Courtesy of HSBC

 

A High Ratio Mortgage is a personal mortgage with a down payment of less than 20% of the purchase price. Applications are subject to credit approval. Rate displayed includes a 0.35%  or 0.25% discount off our Special Offer rate and is only available for high ratio residential mortgages.

斗罗大陆 第133集

BBC's Great Canadian Railway Journeys

Wired vs Wireless Security Cameras

golden rule: use wired camera where you can, and consider wireless otherwise.

i9-10900k vs. i7-10700k

 Intel’s Comet Lake flagship, the i9-10900K, is the fastest gaming and desktop CPU currently available.The 10900K also requires a new (Z490) LGA1200 motherboard

19,677 User Benchmarks

Best Bench: 108% Base clock 3.7 GHz, turbo 5.3 GHz (avg)
Worst Bench: 96% Base clock 3.7 GHz, turbo 0.8 GHz (avg)

SPEED RANK: 2nd / 1276

45,594 User Benchmarks

Best Bench: 106% Base clock 3.8 GHz, turbo 5.15 GHz (avg)
Worst Bench: 91% Base clock 3.8 GHz, turbo 0.8 GHz (avg)

SPEED RANK: 7th / 1276

Age Newest		7 Months			7 Months
TDP Thermal Design Power (TDP)		125 Watts			125 Watts
Cores CPU Processing Cores		10 cores	Higher core count. +25%		8 cores
Threads CPU Processing Threads		20 threads	Higher thread count. +25%		16 threads
Lithography Manufacturing process		14 nm			14 nm
Base Clock Base Clock Speed		3.7 GHz			3.8 GHz	+3%
Turbo Clock Turbo Clock Speed		5.3 GHz	+4%		5.1 GHz
64-Core OC Multi Core Mixed Speed		2126 Pts	Faster OC 64-core speed. +28%		1666 Pts
64-Core Avg. Multi Core Mixed Speed		1996 Pts	Faster 64-core speed. +30%		1541 Pts

reference:

https://cpu.userbenchmark.com/Compare/Intel-Core-i9-10900K-vs-Intel-Core-i7-10700K/4071vs4070