File - Ipynb - JupyterLab

3/6/24, 11:47 PM file
In [2]: import tensorflow as tf

import cv2, os
import matplotlib.pyplot as plt
import numpy as np
import sym_name
2024-03-05 15:37:25.626878: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightl
y 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`.
2024-03-05 15:37:25.877079: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN
factory: Attempting to register factory for plugin cuDNN when one has already been registered
2024-03-05 15:37:25.877144: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT
factory: Attempting to register factory for plugin cuFFT when one has already been registered
2024-03-05 15:37:25.918724: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBL
AS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
2024-03-05 15:37:25.999476: 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: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the
appropriate compiler flags.
2024-03-05 15:37:26.845677: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find T
ensorRT
In [3]: img_array = cv2.imread("training/0/Training_3908.jpg")
In [4]: img_array.shape
Out[4]: (48, 48, 3)
In [5]: plt.imshow(img_array)
Out[5]: <matplotlib.image.AxesImage at 0x7f3201e41c60>
localhost:8888/doc/tree/file.ipynb 1/30
3/6/24, 11:47 PM file
In [6]: dir = "training/"

classes = ['0','1','2','3','4','5','6']
In [7]: for category in classes:

path = os.path.join(dir, category)
for img in os.listdir(path):
img_path = os.path.join(path, img)
img_array = cv2.imread(img_path)
if img_array is not None: # Check if image was read successfully
plt.imshow(cv2.cvtColor(img_array, cv2.COLOR_BGR2RGB)) # Convert BGR to RGB
plt.show()
break
break
3/6/24, 11:47 PM file
In [8]: img_size = 224

new_array = cv2.resize(img_array,(img_size,img_size))
plt.imshow(cv2.cvtColor(new_array,cv2.COLOR_BGR2RGB))
plt.show()
3/6/24, 11:47 PM file
In [9]: new_array.shape
Out[9]: (224, 224, 3)
In [10]: train_data = []
def create_train_data():
for category in classes:
path = os.path.join(dir, category)
class_num = classes.index(category)
for img in os.listdir(path):
try:
img_path = os.path.join(path, img)
img_array = cv2.imread(img_path)
new_array = cv2.resize(img_array,(img_size,img_size))
3/6/24, 11:47 PM file
train_data.append([new_array,class_num])
except Exception as e:
pass
create_train_data()
In [11]: print(len(train_data))
28709
In [12]: import random
random.shuffle(train_data)
In [13]: x = []
y = []
for features,label in train_data:

x.append(features)
y.append(label)
x = np.array(x).reshape(-1, img_size, img_size, 3)
In [14]: x.shape
Out[14]: (28709, 224, 224, 3)
In [15]: # x = x/255.0
In [16]: type(y)
Out[16]: list
In [17]: y[0]
Out[17]: 5
In [18]: y = np.array(y)
y.shape
3/6/24, 11:47 PM file
Out[18]: (28709,)
In [19]: from tensorflow import keras

from tensorflow.keras import layers
In [20]: model = tf.keras.applications.MobileNetV2()
In [21]: model.summary()
3/6/24, 11:47 PM file
Model: "mobilenetv2_1.00_224"
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_1 (InputLayer) [(None, 224, 224, 3)] 0 []
Conv1 (Conv2D) (None, 112, 112, 32) 864 ['input_1[0][0]']
bn_Conv1 (BatchNormalizati (None, 112, 112, 32) 128 ['Conv1[0][0]']

on)
Conv1_relu (ReLU) (None, 112, 112, 32) 0 ['bn_Conv1[0][0]']
expanded_conv_depthwise (D (None, 112, 112, 32) 288 ['Conv1_relu[0][0]']

epthwiseConv2D)
expanded_conv_depthwise_BN (None, 112, 112, 32) 128 ['expanded_conv_depthwise[0][0

(BatchNormalization) ]']
expanded_conv_depthwise_re (None, 112, 112, 32) 0 ['expanded_conv_depthwise_BN[0

lu (ReLU) ][0]']
expanded_conv_project (Con (None, 112, 112, 16) 512 ['expanded_conv_depthwise_relu

v2D) [0][0]']
expanded_conv_project_BN ( (None, 112, 112, 16) 64 ['expanded_conv_project[0][0]'

BatchNormalization) ]
block_1_expand (Conv2D) (None, 112, 112, 96) 1536 ['expanded_conv_project_BN[0][

0]']
block_1_expand_BN (BatchNo (None, 112, 112, 96) 384 ['block_1_expand[0][0]']

rmalization)
block_1_expand_relu (ReLU) (None, 112, 112, 96) 0 ['block_1_expand_BN[0][0]']
block_1_pad (ZeroPadding2D (None, 113, 113, 96) 0 ['block_1_expand_relu[0][0]']

)
block_1_depthwise (Depthwi (None, 56, 56, 96) 864 ['block_1_pad[0][0]']

seConv2D)
3/6/24, 11:47 PM file
block_1_depthwise_BN (Batc (None, 56, 56, 96) 384 ['block_1_depthwise[0][0]']

hNormalization)
block_1_depthwise_relu (Re (None, 56, 56, 96) 0 ['block_1_depthwise_BN[0][0]']

LU)
block_1_project (Conv2D) (None, 56, 56, 24) 2304 ['block_1_depthwise_relu[0][0]

']
block_1_project_BN (BatchN (None, 56, 56, 24) 96 ['block_1_project[0][0]']

ormalization)
block_2_expand (Conv2D) (None, 56, 56, 144) 3456 ['block_1_project_BN[0][0]']

rmalization)
block_2_depthwise (Depthwi (None, 56, 56, 144) 1296 ['block_2_expand_relu[0][0]']

seConv2D)

hNormalization)

LU)

']

ormalization)
block_2_add (Add) (None, 56, 56, 24) 0 ['block_1_project_BN[0][0]',

'block_2_project_BN[0][0]']
block_3_expand (Conv2D) (None, 56, 56, 144) 3456 ['block_2_add[0][0]']
3/6/24, 11:47 PM file
rmalization)

)

seConv2D)

hNormalization)

LU)

']

ormalization)

rmalization)

seConv2D)

hNormalization)

LU)

']
3/6/24, 11:47 PM file

ormalization)


rmalization)

seConv2D)

hNormalization)

LU)

']

ormalization)
block_5_add (Add) (None, 28, 28, 32) 0 ['block_4_add[0][0]',


rmalization)

)
3/6/24, 11:47 PM file

seConv2D)

hNormalization)

LU)

']

ormalization)

rmalization)

seConv2D)

hNormalization)

LU)

']

ormalization)

3/6/24, 11:47 PM file

rmalization)

seConv2D)

hNormalization)

LU)

']

ormalization)


rmalization)

seConv2D)

hNormalization)

LU)
3/6/24, 11:47 PM file
']

ormalization)

block_10_expand_BN (BatchN (None, 14, 14, 384) 1536 ['block_10_expand[0][0]']

ormalization)
block_10_expand_relu (ReLU (None, 14, 14, 384) 0 ['block_10_expand_BN[0][0]']

)
block_10_depthwise (Depthw (None, 14, 14, 384) 3456 ['block_10_expand_relu[0][0]']

iseConv2D)
block_10_depthwise_BN (Bat (None, 14, 14, 384) 1536 ['block_10_depthwise[0][0]']

chNormalization)
block_10_depthwise_relu (R (None, 14, 14, 384) 0 ['block_10_depthwise_BN[0][0]'

eLU) ]
block_10_project (Conv2D) (None, 14, 14, 96) 36864 ['block_10_depthwise_relu[0][0

]']
block_10_project_BN (Batch (None, 14, 14, 96) 384 ['block_10_project[0][0]']

Normalization)

ormalization)

)

iseConv2D)
3/6/24, 11:47 PM file

chNormalization)

eLU) ]

]']

Normalization)


ormalization)

)

iseConv2D)

chNormalization)

eLU) ]

]']

Normalization)

3/6/24, 11:47 PM file

ormalization)

)
block_13_pad (ZeroPadding2 (None, 15, 15, 576) 0 ['block_13_expand_relu[0][0]']

D)
block_13_depthwise (Depthw (None, 7, 7, 576) 5184 ['block_13_pad[0][0]']

iseConv2D)

chNormalization)

eLU) ]

]']

Normalization)

ormalization)

)

iseConv2D)

chNormalization)
3/6/24, 11:47 PM file

eLU) ]

]']

Normalization)


ormalization)

)

iseConv2D)

chNormalization)

eLU) ]

]']

Normalization)

3/6/24, 11:47 PM file
ormalization)

)

iseConv2D)

chNormalization)

eLU) ]

]']

Normalization)
Conv_1 (Conv2D) (None, 7, 7, 1280) 409600 ['block_16_project_BN[0][0]']
Conv_1_bn (BatchNormalizat (None, 7, 7, 1280) 5120 ['Conv_1[0][0]']

ion)
out_relu (ReLU) (None, 7, 7, 1280) 0 ['Conv_1_bn[0][0]']
global_average_pooling2d ( (None, 1280) 0 ['out_relu[0][0]']

GlobalAveragePooling2D)
predictions (Dense) (None, 1000) 1281000 ['global_average_pooling2d[0][

0]']
==================================================================================================
Total params: 3538984 (13.50 MB)
Trainable params: 3504872 (13.37 MB)
Non-trainable params: 34112 (133.25 KB)
__________________________________________________________________________________________________
In [22]: base_input = model.layers[0].input
3/6/24, 11:47 PM file
base_output = model.layers[-2].output
In [23]: base_input
base_output
Out[23]: <KerasTensor: shape=(None, 1280) dtype=float32 (created by layer 'global_average_pooling2d')>
In [24]: final_output = layers.Dense(128)(base_output)

final_output = layers.Activation('relu')(final_output)
final_output = layers.Dense(64)(final_output)
final_output = layers.Activation('relu')(final_output)
final_output = layers.Dense(7,activation='softmax')(final_output)
In [25]: final_output
Out[25]: <KerasTensor: shape=(None, 7) dtype=float32 (created by layer 'dense_2')>
In [26]: new_model = keras.Model(inputs = base_input, outputs= final_output)
In [27]: new_model.summary()
3/6/24, 11:47 PM file
Model: "model"
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_1 (InputLayer) [(None, 224, 224, 3)] 0 []
Conv1 (Conv2D) (None, 112, 112, 32) 864 ['input_1[0][0]']
bn_Conv1 (BatchNormalizati (None, 112, 112, 32) 128 ['Conv1[0][0]']

on)
Conv1_relu (ReLU) (None, 112, 112, 32) 0 ['bn_Conv1[0][0]']
expanded_conv_depthwise (D (None, 112, 112, 32) 288 ['Conv1_relu[0][0]']

epthwiseConv2D)
expanded_conv_depthwise_BN (None, 112, 112, 32) 128 ['expanded_conv_depthwise[0][0

(BatchNormalization) ]']
expanded_conv_depthwise_re (None, 112, 112, 32) 0 ['expanded_conv_depthwise_BN[0

lu (ReLU) ][0]']
expanded_conv_project (Con (None, 112, 112, 16) 512 ['expanded_conv_depthwise_relu

v2D) [0][0]']
expanded_conv_project_BN ( (None, 112, 112, 16) 64 ['expanded_conv_project[0][0]'

BatchNormalization) ]
block_1_expand (Conv2D) (None, 112, 112, 96) 1536 ['expanded_conv_project_BN[0][

0]']

rmalization)

)

seConv2D)
3/6/24, 11:47 PM file

hNormalization)

LU)

']

ormalization)

rmalization)

seConv2D)

hNormalization)

LU)

']

ormalization)

3/6/24, 11:47 PM file
rmalization)

)

seConv2D)

hNormalization)

LU)

']

ormalization)

rmalization)

seConv2D)

hNormalization)

LU)

']
3/6/24, 11:47 PM file

ormalization)


rmalization)

seConv2D)

hNormalization)

LU)

']

ormalization)


rmalization)

)
3/6/24, 11:47 PM file

seConv2D)

hNormalization)

LU)

']

ormalization)

rmalization)

seConv2D)

hNormalization)

LU)

']

ormalization)

3/6/24, 11:47 PM file

rmalization)

seConv2D)

hNormalization)

LU)

']

ormalization)


rmalization)

seConv2D)

hNormalization)

LU)
3/6/24, 11:47 PM file
']

ormalization)


ormalization)

)

iseConv2D)

chNormalization)

eLU) ]

]']

Normalization)

ormalization)

)

iseConv2D)
3/6/24, 11:47 PM file

chNormalization)

eLU) ]

]']

Normalization)


ormalization)

)

iseConv2D)

chNormalization)

eLU) ]

]']

Normalization)

3/6/24, 11:47 PM file

ormalization)

)
block_13_pad (ZeroPadding2 (None, 15, 15, 576) 0 ['block_13_expand_relu[0][0]']

D)
block_13_depthwise (Depthw (None, 7, 7, 576) 5184 ['block_13_pad[0][0]']

iseConv2D)

chNormalization)

eLU) ]

]']

Normalization)

ormalization)

)

iseConv2D)

chNormalization)
3/6/24, 11:47 PM file

eLU) ]

]']

Normalization)


ormalization)

)

iseConv2D)

chNormalization)

eLU) ]

]']

Normalization)

3/6/24, 11:47 PM file
ormalization)

)

iseConv2D)

chNormalization)

eLU) ]

]']

Normalization)
Conv_1 (Conv2D) (None, 7, 7, 1280) 409600 ['block_16_project_BN[0][0]']
Conv_1_bn (BatchNormalizat (None, 7, 7, 1280) 5120 ['Conv_1[0][0]']

ion)
out_relu (ReLU) (None, 7, 7, 1280) 0 ['Conv_1_bn[0][0]']
global_average_pooling2d ( (None, 1280) 0 ['out_relu[0][0]']

GlobalAveragePooling2D)
dense (Dense) (None, 128) 163968 ['global_average_pooling2d[0][

0]']
activation (Activation) (None, 128) 0 ['dense[0][0]']
dense_1 (Dense) (None, 64) 8256 ['activation[0][0]']
activation_1 (Activation) (None, 64) 0 ['dense_1[0][0]']
dense_2 (Dense) (None, 7) 455 ['activation_1[0][0]']
3/6/24, 11:47 PM file
==================================================================================================
Total params: 2430663 (9.27 MB)
Trainable params: 2396551 (9.14 MB)
Non-trainable params: 34112 (133.25 KB)
__________________________________________________________________________________________________
In [28]: new_model.compile(loss="sparse_categorical_crossentropy", optimizer="adam", metrics=["accuracy"])
In [29]: history = new_model.fit(x,y, batch_size = 32, epochs=5, verbose="True")
The Kernel crashed while executing code in the the current cell or a previous cell. Please review the code in the ce
ll(s) to identify a possible cause of the failure. Click <a href='https://aka.ms/vscodeJupyterKernelCrash'>here</a>
for more info. View Jupyter <a href='command:jupyter.viewOutput'>log</a> for further details.

File - Ipynb - JupyterLab

Uploaded by

Copyright:

Available Formats

File - Ipynb - JupyterLab

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

File - Ipynb - JupyterLab

Uploaded by

Copyright:

Available Formats

3/6/24, 11:47 PM file

In [2]: import tensorflow as tf

In [3]: img_array = cv2.imread("training/0/Training_3908.jpg")

Out[4]: (48, 48, 3)

Out[5]: <matplotlib.image.AxesImage at 0x7f3201e41c60>

In [6]: dir = "training/"

In [7]: for category in classes:

In [8]: img_size = 224

Out[9]: (224, 224, 3)

In [12]: import random

for features,label in train_data:

x = np.array(x).reshape(-1, img_size, img_size, 3)

Out[14]: (28709, 224, 224, 3)

In [19]: from tensorflow import keras

In [20]: model = tf.keras.applications.MobileNetV2()

Conv1 (Conv2D) (None, 112, 112, 32) 864 ['input_1[0][0]']

bn_Conv1 (BatchNormalizati (None, 112, 112, 32) 128 ['Conv1[0][0]']

Conv1_relu (ReLU) (None, 112, 112, 32) 0 ['bn_Conv1[0][0]']

expanded_conv_depthwise (D (None, 112, 112, 32) 288 ['Conv1_relu[0][0]']

expanded_conv_depthwise_BN (None, 112, 112, 32) 128 ['expanded_conv_depthwise[0][0

expanded_conv_depthwise_re (None, 112, 112, 32) 0 ['expanded_conv_depthwise_BN[0

expanded_conv_project (Con (None, 112, 112, 16) 512 ['expanded_conv_depthwise_relu

expanded_conv_project_BN ( (None, 112, 112, 16) 64 ['expanded_conv_project[0][0]'

block_1_expand (Conv2D) (None, 112, 112, 96) 1536 ['expanded_conv_project_BN[0][

block_1_expand_BN (BatchNo (None, 112, 112, 96) 384 ['block_1_expand[0][0]']

block_1_expand_relu (ReLU) (None, 112, 112, 96) 0 ['block_1_expand_BN[0][0]']

block_1_pad (ZeroPadding2D (None, 113, 113, 96) 0 ['block_1_expand_relu[0][0]']

block_1_depthwise (Depthwi (None, 56, 56, 96) 864 ['block_1_pad[0][0]']

block_1_depthwise_BN (Batc (None, 56, 56, 96) 384 ['block_1_depthwise[0][0]']

block_1_depthwise_relu (Re (None, 56, 56, 96) 0 ['block_1_depthwise_BN[0][0]']

block_1_project (Conv2D) (None, 56, 56, 24) 2304 ['block_1_depthwise_relu[0][0]

block_1_project_BN (BatchN (None, 56, 56, 24) 96 ['block_1_project[0][0]']

block_2_expand (Conv2D) (None, 56, 56, 144) 3456 ['block_1_project_BN[0][0]']

block_2_expand_BN (BatchNo (None, 56, 56, 144) 576 ['block_2_expand[0][0]']

block_2_expand_relu (ReLU) (None, 56, 56, 144) 0 ['block_2_expand_BN[0][0]']

block_2_depthwise (Depthwi (None, 56, 56, 144) 1296 ['block_2_expand_relu[0][0]']

block_2_depthwise_BN (Batc (None, 56, 56, 144) 576 ['block_2_depthwise[0][0]']

block_2_depthwise_relu (Re (None, 56, 56, 144) 0 ['block_2_depthwise_BN[0][0]']

block_2_project (Conv2D) (None, 56, 56, 24) 3456 ['block_2_depthwise_relu[0][0]

block_2_project_BN (BatchN (None, 56, 56, 24) 96 ['block_2_project[0][0]']

block_2_add (Add) (None, 56, 56, 24) 0 ['block_1_project_BN[0][0]',

block_3_expand (Conv2D) (None, 56, 56, 144) 3456 ['block_2_add[0][0]']

block_3_expand_BN (BatchNo (None, 56, 56, 144) 576 ['block_3_expand[0][0]']

block_3_expand_relu (ReLU) (None, 56, 56, 144) 0 ['block_3_expand_BN[0][0]']

block_3_pad (ZeroPadding2D (None, 57, 57, 144) 0 ['block_3_expand_relu[0][0]']

block_3_depthwise (Depthwi (None, 28, 28, 144) 1296 ['block_3_pad[0][0]']

block_3_depthwise_BN (Batc (None, 28, 28, 144) 576 ['block_3_depthwise[0][0]']

block_3_depthwise_relu (Re (None, 28, 28, 144) 0 ['block_3_depthwise_BN[0][0]']

block_3_project (Conv2D) (None, 28, 28, 32) 4608 ['block_3_depthwise_relu[0][0]

block_3_project_BN (BatchN (None, 28, 28, 32) 128 ['block_3_project[0][0]']

block_4_expand (Conv2D) (None, 28, 28, 192) 6144 ['block_3_project_BN[0][0]']

block_4_expand_BN (BatchNo (None, 28, 28, 192) 768 ['block_4_expand[0][0]']

block_4_expand_relu (ReLU) (None, 28, 28, 192) 0 ['block_4_expand_BN[0][0]']

block_4_depthwise (Depthwi (None, 28, 28, 192) 1728 ['block_4_expand_relu[0][0]']

block_4_depthwise_BN (Batc (None, 28, 28, 192) 768 ['block_4_depthwise[0][0]']

block_4_depthwise_relu (Re (None, 28, 28, 192) 0 ['block_4_depthwise_BN[0][0]']

block_4_project (Conv2D) (None, 28, 28, 32) 6144 ['block_4_depthwise_relu[0][0]

block_4_project_BN (BatchN (None, 28, 28, 32) 128 ['block_4_project[0][0]']

block_4_add (Add) (None, 28, 28, 32) 0 ['block_3_project_BN[0][0]',