Image Recognition Using Keras-ResNet50¶
About this project¶
We're going to use a pretrained model included in Keras to do image recognition. Keras comes with several image recognition models including
- VGG (Visual Geometry Group at the University of Oxford)
- ResNet50 (MS research)
- Inception-v3 (Google)
- Xception (Keras)
We'll use the ResNet50 in this project. This paper describes ResNets. Check out this link for details on the model and ResNets in general.
We have a few images to pick from to see how well the image classifier performs
Import and set up model¶
In [1]:
import numpy as np
# from tensorflow.keras import backend
from keras.preprocessing import image
from tensorflow.keras.applications import resnet50 # <model
#Image visualization
%pylab inline
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
Using TensorFlow backend.
Populating the interactive namespace from numpy and matplotlib
In [2]:
#Now we load the imported model
model =resnet50.ResNet50() #Create a new instance of the model
Details of the model layers¶
After we load the model we can use summary() to look at the model's layers and data flow structure.
In [18]:
model.summary()
Model: "resnet50"
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_1 (InputLayer) [(None, 224, 224, 3) 0
__________________________________________________________________________________________________
conv1_pad (ZeroPadding2D) (None, 230, 230, 3) 0 input_1[0][0]
__________________________________________________________________________________________________
conv1 (Conv2D) (None, 112, 112, 64) 9472 conv1_pad[0][0]
__________________________________________________________________________________________________
bn_conv1 (BatchNormalizationV1) (None, 112, 112, 64) 256 conv1[0][0]
__________________________________________________________________________________________________
activation (Activation) (None, 112, 112, 64) 0 bn_conv1[0][0]
__________________________________________________________________________________________________
pool1_pad (ZeroPadding2D) (None, 114, 114, 64) 0 activation[0][0]
__________________________________________________________________________________________________
max_pooling2d (MaxPooling2D) (None, 56, 56, 64) 0 pool1_pad[0][0]
__________________________________________________________________________________________________
res2a_branch2a (Conv2D) (None, 56, 56, 64) 4160 max_pooling2d[0][0]
__________________________________________________________________________________________________
bn2a_branch2a (BatchNormalizati (None, 56, 56, 64) 256 res2a_branch2a[0][0]
__________________________________________________________________________________________________
activation_1 (Activation) (None, 56, 56, 64) 0 bn2a_branch2a[0][0]
__________________________________________________________________________________________________
res2a_branch2b (Conv2D) (None, 56, 56, 64) 36928 activation_1[0][0]
__________________________________________________________________________________________________
bn2a_branch2b (BatchNormalizati (None, 56, 56, 64) 256 res2a_branch2b[0][0]
__________________________________________________________________________________________________
activation_2 (Activation) (None, 56, 56, 64) 0 bn2a_branch2b[0][0]
__________________________________________________________________________________________________
res2a_branch2c (Conv2D) (None, 56, 56, 256) 16640 activation_2[0][0]
__________________________________________________________________________________________________
res2a_branch1 (Conv2D) (None, 56, 56, 256) 16640 max_pooling2d[0][0]
__________________________________________________________________________________________________
bn2a_branch2c (BatchNormalizati (None, 56, 56, 256) 1024 res2a_branch2c[0][0]
__________________________________________________________________________________________________
bn2a_branch1 (BatchNormalizatio (None, 56, 56, 256) 1024 res2a_branch1[0][0]
__________________________________________________________________________________________________
add (Add) (None, 56, 56, 256) 0 bn2a_branch2c[0][0]
bn2a_branch1[0][0]
__________________________________________________________________________________________________
activation_3 (Activation) (None, 56, 56, 256) 0 add[0][0]
__________________________________________________________________________________________________
res2b_branch2a (Conv2D) (None, 56, 56, 64) 16448 activation_3[0][0]
__________________________________________________________________________________________________
bn2b_branch2a (BatchNormalizati (None, 56, 56, 64) 256 res2b_branch2a[0][0]
__________________________________________________________________________________________________
activation_4 (Activation) (None, 56, 56, 64) 0 bn2b_branch2a[0][0]
__________________________________________________________________________________________________
res2b_branch2b (Conv2D) (None, 56, 56, 64) 36928 activation_4[0][0]
__________________________________________________________________________________________________
bn2b_branch2b (BatchNormalizati (None, 56, 56, 64) 256 res2b_branch2b[0][0]
__________________________________________________________________________________________________
activation_5 (Activation) (None, 56, 56, 64) 0 bn2b_branch2b[0][0]
__________________________________________________________________________________________________
res2b_branch2c (Conv2D) (None, 56, 56, 256) 16640 activation_5[0][0]
__________________________________________________________________________________________________
bn2b_branch2c (BatchNormalizati (None, 56, 56, 256) 1024 res2b_branch2c[0][0]
__________________________________________________________________________________________________
add_1 (Add) (None, 56, 56, 256) 0 bn2b_branch2c[0][0]
activation_3[0][0]
__________________________________________________________________________________________________
activation_6 (Activation) (None, 56, 56, 256) 0 add_1[0][0]
__________________________________________________________________________________________________
res2c_branch2a (Conv2D) (None, 56, 56, 64) 16448 activation_6[0][0]
__________________________________________________________________________________________________
bn2c_branch2a (BatchNormalizati (None, 56, 56, 64) 256 res2c_branch2a[0][0]
__________________________________________________________________________________________________
activation_7 (Activation) (None, 56, 56, 64) 0 bn2c_branch2a[0][0]
__________________________________________________________________________________________________
res2c_branch2b (Conv2D) (None, 56, 56, 64) 36928 activation_7[0][0]
__________________________________________________________________________________________________
bn2c_branch2b (BatchNormalizati (None, 56, 56, 64) 256 res2c_branch2b[0][0]
__________________________________________________________________________________________________
activation_8 (Activation) (None, 56, 56, 64) 0 bn2c_branch2b[0][0]
__________________________________________________________________________________________________
res2c_branch2c (Conv2D) (None, 56, 56, 256) 16640 activation_8[0][0]
__________________________________________________________________________________________________
bn2c_branch2c (BatchNormalizati (None, 56, 56, 256) 1024 res2c_branch2c[0][0]
__________________________________________________________________________________________________
add_2 (Add) (None, 56, 56, 256) 0 bn2c_branch2c[0][0]
activation_6[0][0]
__________________________________________________________________________________________________
activation_9 (Activation) (None, 56, 56, 256) 0 add_2[0][0]
__________________________________________________________________________________________________
res3a_branch2a (Conv2D) (None, 28, 28, 128) 32896 activation_9[0][0]
__________________________________________________________________________________________________
bn3a_branch2a (BatchNormalizati (None, 28, 28, 128) 512 res3a_branch2a[0][0]
__________________________________________________________________________________________________
activation_10 (Activation) (None, 28, 28, 128) 0 bn3a_branch2a[0][0]
__________________________________________________________________________________________________
res3a_branch2b (Conv2D) (None, 28, 28, 128) 147584 activation_10[0][0]
__________________________________________________________________________________________________
bn3a_branch2b (BatchNormalizati (None, 28, 28, 128) 512 res3a_branch2b[0][0]
__________________________________________________________________________________________________
activation_11 (Activation) (None, 28, 28, 128) 0 bn3a_branch2b[0][0]
__________________________________________________________________________________________________
res3a_branch2c (Conv2D) (None, 28, 28, 512) 66048 activation_11[0][0]
__________________________________________________________________________________________________
res3a_branch1 (Conv2D) (None, 28, 28, 512) 131584 activation_9[0][0]
__________________________________________________________________________________________________
bn3a_branch2c (BatchNormalizati (None, 28, 28, 512) 2048 res3a_branch2c[0][0]
__________________________________________________________________________________________________
bn3a_branch1 (BatchNormalizatio (None, 28, 28, 512) 2048 res3a_branch1[0][0]
__________________________________________________________________________________________________
add_3 (Add) (None, 28, 28, 512) 0 bn3a_branch2c[0][0]
bn3a_branch1[0][0]
__________________________________________________________________________________________________
activation_12 (Activation) (None, 28, 28, 512) 0 add_3[0][0]
__________________________________________________________________________________________________
res3b_branch2a (Conv2D) (None, 28, 28, 128) 65664 activation_12[0][0]
__________________________________________________________________________________________________
bn3b_branch2a (BatchNormalizati (None, 28, 28, 128) 512 res3b_branch2a[0][0]
__________________________________________________________________________________________________
activation_13 (Activation) (None, 28, 28, 128) 0 bn3b_branch2a[0][0]
__________________________________________________________________________________________________
res3b_branch2b (Conv2D) (None, 28, 28, 128) 147584 activation_13[0][0]
__________________________________________________________________________________________________
bn3b_branch2b (BatchNormalizati (None, 28, 28, 128) 512 res3b_branch2b[0][0]
__________________________________________________________________________________________________
activation_14 (Activation) (None, 28, 28, 128) 0 bn3b_branch2b[0][0]
__________________________________________________________________________________________________
res3b_branch2c (Conv2D) (None, 28, 28, 512) 66048 activation_14[0][0]
__________________________________________________________________________________________________
bn3b_branch2c (BatchNormalizati (None, 28, 28, 512) 2048 res3b_branch2c[0][0]
__________________________________________________________________________________________________
add_4 (Add) (None, 28, 28, 512) 0 bn3b_branch2c[0][0]
activation_12[0][0]
__________________________________________________________________________________________________
activation_15 (Activation) (None, 28, 28, 512) 0 add_4[0][0]
__________________________________________________________________________________________________
res3c_branch2a (Conv2D) (None, 28, 28, 128) 65664 activation_15[0][0]
__________________________________________________________________________________________________
bn3c_branch2a (BatchNormalizati (None, 28, 28, 128) 512 res3c_branch2a[0][0]
__________________________________________________________________________________________________
activation_16 (Activation) (None, 28, 28, 128) 0 bn3c_branch2a[0][0]
__________________________________________________________________________________________________
res3c_branch2b (Conv2D) (None, 28, 28, 128) 147584 activation_16[0][0]
__________________________________________________________________________________________________
bn3c_branch2b (BatchNormalizati (None, 28, 28, 128) 512 res3c_branch2b[0][0]
__________________________________________________________________________________________________
activation_17 (Activation) (None, 28, 28, 128) 0 bn3c_branch2b[0][0]
__________________________________________________________________________________________________
res3c_branch2c (Conv2D) (None, 28, 28, 512) 66048 activation_17[0][0]
__________________________________________________________________________________________________
bn3c_branch2c (BatchNormalizati (None, 28, 28, 512) 2048 res3c_branch2c[0][0]
__________________________________________________________________________________________________
add_5 (Add) (None, 28, 28, 512) 0 bn3c_branch2c[0][0]
activation_15[0][0]
__________________________________________________________________________________________________
activation_18 (Activation) (None, 28, 28, 512) 0 add_5[0][0]
__________________________________________________________________________________________________
res3d_branch2a (Conv2D) (None, 28, 28, 128) 65664 activation_18[0][0]
__________________________________________________________________________________________________
bn3d_branch2a (BatchNormalizati (None, 28, 28, 128) 512 res3d_branch2a[0][0]
__________________________________________________________________________________________________
activation_19 (Activation) (None, 28, 28, 128) 0 bn3d_branch2a[0][0]
__________________________________________________________________________________________________
res3d_branch2b (Conv2D) (None, 28, 28, 128) 147584 activation_19[0][0]
__________________________________________________________________________________________________
bn3d_branch2b (BatchNormalizati (None, 28, 28, 128) 512 res3d_branch2b[0][0]
__________________________________________________________________________________________________
activation_20 (Activation) (None, 28, 28, 128) 0 bn3d_branch2b[0][0]
__________________________________________________________________________________________________
res3d_branch2c (Conv2D) (None, 28, 28, 512) 66048 activation_20[0][0]
__________________________________________________________________________________________________
bn3d_branch2c (BatchNormalizati (None, 28, 28, 512) 2048 res3d_branch2c[0][0]
__________________________________________________________________________________________________
add_6 (Add) (None, 28, 28, 512) 0 bn3d_branch2c[0][0]
activation_18[0][0]
__________________________________________________________________________________________________
activation_21 (Activation) (None, 28, 28, 512) 0 add_6[0][0]
__________________________________________________________________________________________________
res4a_branch2a (Conv2D) (None, 14, 14, 256) 131328 activation_21[0][0]
__________________________________________________________________________________________________
bn4a_branch2a (BatchNormalizati (None, 14, 14, 256) 1024 res4a_branch2a[0][0]
__________________________________________________________________________________________________
activation_22 (Activation) (None, 14, 14, 256) 0 bn4a_branch2a[0][0]
__________________________________________________________________________________________________
res4a_branch2b (Conv2D) (None, 14, 14, 256) 590080 activation_22[0][0]
__________________________________________________________________________________________________
bn4a_branch2b (BatchNormalizati (None, 14, 14, 256) 1024 res4a_branch2b[0][0]
__________________________________________________________________________________________________
activation_23 (Activation) (None, 14, 14, 256) 0 bn4a_branch2b[0][0]
__________________________________________________________________________________________________
res4a_branch2c (Conv2D) (None, 14, 14, 1024) 263168 activation_23[0][0]
__________________________________________________________________________________________________
res4a_branch1 (Conv2D) (None, 14, 14, 1024) 525312 activation_21[0][0]
__________________________________________________________________________________________________
bn4a_branch2c (BatchNormalizati (None, 14, 14, 1024) 4096 res4a_branch2c[0][0]
__________________________________________________________________________________________________
bn4a_branch1 (BatchNormalizatio (None, 14, 14, 1024) 4096 res4a_branch1[0][0]
__________________________________________________________________________________________________
add_7 (Add) (None, 14, 14, 1024) 0 bn4a_branch2c[0][0]
bn4a_branch1[0][0]
__________________________________________________________________________________________________
activation_24 (Activation) (None, 14, 14, 1024) 0 add_7[0][0]
__________________________________________________________________________________________________
res4b_branch2a (Conv2D) (None, 14, 14, 256) 262400 activation_24[0][0]
__________________________________________________________________________________________________
bn4b_branch2a (BatchNormalizati (None, 14, 14, 256) 1024 res4b_branch2a[0][0]
__________________________________________________________________________________________________
activation_25 (Activation) (None, 14, 14, 256) 0 bn4b_branch2a[0][0]
__________________________________________________________________________________________________
res4b_branch2b (Conv2D) (None, 14, 14, 256) 590080 activation_25[0][0]
__________________________________________________________________________________________________
bn4b_branch2b (BatchNormalizati (None, 14, 14, 256) 1024 res4b_branch2b[0][0]
__________________________________________________________________________________________________
activation_26 (Activation) (None, 14, 14, 256) 0 bn4b_branch2b[0][0]
__________________________________________________________________________________________________
res4b_branch2c (Conv2D) (None, 14, 14, 1024) 263168 activation_26[0][0]
__________________________________________________________________________________________________
bn4b_branch2c (BatchNormalizati (None, 14, 14, 1024) 4096 res4b_branch2c[0][0]
__________________________________________________________________________________________________
add_8 (Add) (None, 14, 14, 1024) 0 bn4b_branch2c[0][0]
activation_24[0][0]
__________________________________________________________________________________________________
activation_27 (Activation) (None, 14, 14, 1024) 0 add_8[0][0]
__________________________________________________________________________________________________
res4c_branch2a (Conv2D) (None, 14, 14, 256) 262400 activation_27[0][0]
__________________________________________________________________________________________________
bn4c_branch2a (BatchNormalizati (None, 14, 14, 256) 1024 res4c_branch2a[0][0]
__________________________________________________________________________________________________
activation_28 (Activation) (None, 14, 14, 256) 0 bn4c_branch2a[0][0]
__________________________________________________________________________________________________
res4c_branch2b (Conv2D) (None, 14, 14, 256) 590080 activation_28[0][0]
__________________________________________________________________________________________________
bn4c_branch2b (BatchNormalizati (None, 14, 14, 256) 1024 res4c_branch2b[0][0]
__________________________________________________________________________________________________
activation_29 (Activation) (None, 14, 14, 256) 0 bn4c_branch2b[0][0]
__________________________________________________________________________________________________
res4c_branch2c (Conv2D) (None, 14, 14, 1024) 263168 activation_29[0][0]
__________________________________________________________________________________________________
bn4c_branch2c (BatchNormalizati (None, 14, 14, 1024) 4096 res4c_branch2c[0][0]
__________________________________________________________________________________________________
add_9 (Add) (None, 14, 14, 1024) 0 bn4c_branch2c[0][0]
activation_27[0][0]
__________________________________________________________________________________________________
activation_30 (Activation) (None, 14, 14, 1024) 0 add_9[0][0]
__________________________________________________________________________________________________
res4d_branch2a (Conv2D) (None, 14, 14, 256) 262400 activation_30[0][0]
__________________________________________________________________________________________________
bn4d_branch2a (BatchNormalizati (None, 14, 14, 256) 1024 res4d_branch2a[0][0]
__________________________________________________________________________________________________
activation_31 (Activation) (None, 14, 14, 256) 0 bn4d_branch2a[0][0]
__________________________________________________________________________________________________
res4d_branch2b (Conv2D) (None, 14, 14, 256) 590080 activation_31[0][0]
__________________________________________________________________________________________________
bn4d_branch2b (BatchNormalizati (None, 14, 14, 256) 1024 res4d_branch2b[0][0]
__________________________________________________________________________________________________
activation_32 (Activation) (None, 14, 14, 256) 0 bn4d_branch2b[0][0]
__________________________________________________________________________________________________
res4d_branch2c (Conv2D) (None, 14, 14, 1024) 263168 activation_32[0][0]
__________________________________________________________________________________________________
bn4d_branch2c (BatchNormalizati (None, 14, 14, 1024) 4096 res4d_branch2c[0][0]
__________________________________________________________________________________________________
add_10 (Add) (None, 14, 14, 1024) 0 bn4d_branch2c[0][0]
activation_30[0][0]
__________________________________________________________________________________________________
activation_33 (Activation) (None, 14, 14, 1024) 0 add_10[0][0]
__________________________________________________________________________________________________
res4e_branch2a (Conv2D) (None, 14, 14, 256) 262400 activation_33[0][0]
__________________________________________________________________________________________________
bn4e_branch2a (BatchNormalizati (None, 14, 14, 256) 1024 res4e_branch2a[0][0]
__________________________________________________________________________________________________
activation_34 (Activation) (None, 14, 14, 256) 0 bn4e_branch2a[0][0]
__________________________________________________________________________________________________
res4e_branch2b (Conv2D) (None, 14, 14, 256) 590080 activation_34[0][0]
__________________________________________________________________________________________________
bn4e_branch2b (BatchNormalizati (None, 14, 14, 256) 1024 res4e_branch2b[0][0]
__________________________________________________________________________________________________
activation_35 (Activation) (None, 14, 14, 256) 0 bn4e_branch2b[0][0]
__________________________________________________________________________________________________
res4e_branch2c (Conv2D) (None, 14, 14, 1024) 263168 activation_35[0][0]
__________________________________________________________________________________________________
bn4e_branch2c (BatchNormalizati (None, 14, 14, 1024) 4096 res4e_branch2c[0][0]
__________________________________________________________________________________________________
add_11 (Add) (None, 14, 14, 1024) 0 bn4e_branch2c[0][0]
activation_33[0][0]
__________________________________________________________________________________________________
activation_36 (Activation) (None, 14, 14, 1024) 0 add_11[0][0]
__________________________________________________________________________________________________
res4f_branch2a (Conv2D) (None, 14, 14, 256) 262400 activation_36[0][0]
__________________________________________________________________________________________________
bn4f_branch2a (BatchNormalizati (None, 14, 14, 256) 1024 res4f_branch2a[0][0]
__________________________________________________________________________________________________
activation_37 (Activation) (None, 14, 14, 256) 0 bn4f_branch2a[0][0]
__________________________________________________________________________________________________
res4f_branch2b (Conv2D) (None, 14, 14, 256) 590080 activation_37[0][0]
__________________________________________________________________________________________________
bn4f_branch2b (BatchNormalizati (None, 14, 14, 256) 1024 res4f_branch2b[0][0]
__________________________________________________________________________________________________
activation_38 (Activation) (None, 14, 14, 256) 0 bn4f_branch2b[0][0]
__________________________________________________________________________________________________
res4f_branch2c (Conv2D) (None, 14, 14, 1024) 263168 activation_38[0][0]
__________________________________________________________________________________________________
bn4f_branch2c (BatchNormalizati (None, 14, 14, 1024) 4096 res4f_branch2c[0][0]
__________________________________________________________________________________________________
add_12 (Add) (None, 14, 14, 1024) 0 bn4f_branch2c[0][0]
activation_36[0][0]
__________________________________________________________________________________________________
activation_39 (Activation) (None, 14, 14, 1024) 0 add_12[0][0]
__________________________________________________________________________________________________
res5a_branch2a (Conv2D) (None, 7, 7, 512) 524800 activation_39[0][0]
__________________________________________________________________________________________________
bn5a_branch2a (BatchNormalizati (None, 7, 7, 512) 2048 res5a_branch2a[0][0]
__________________________________________________________________________________________________
activation_40 (Activation) (None, 7, 7, 512) 0 bn5a_branch2a[0][0]
__________________________________________________________________________________________________
res5a_branch2b (Conv2D) (None, 7, 7, 512) 2359808 activation_40[0][0]
__________________________________________________________________________________________________
bn5a_branch2b (BatchNormalizati (None, 7, 7, 512) 2048 res5a_branch2b[0][0]
__________________________________________________________________________________________________
activation_41 (Activation) (None, 7, 7, 512) 0 bn5a_branch2b[0][0]
__________________________________________________________________________________________________
res5a_branch2c (Conv2D) (None, 7, 7, 2048) 1050624 activation_41[0][0]
__________________________________________________________________________________________________
res5a_branch1 (Conv2D) (None, 7, 7, 2048) 2099200 activation_39[0][0]
__________________________________________________________________________________________________
bn5a_branch2c (BatchNormalizati (None, 7, 7, 2048) 8192 res5a_branch2c[0][0]
__________________________________________________________________________________________________
bn5a_branch1 (BatchNormalizatio (None, 7, 7, 2048) 8192 res5a_branch1[0][0]
__________________________________________________________________________________________________
add_13 (Add) (None, 7, 7, 2048) 0 bn5a_branch2c[0][0]
bn5a_branch1[0][0]
__________________________________________________________________________________________________
activation_42 (Activation) (None, 7, 7, 2048) 0 add_13[0][0]
__________________________________________________________________________________________________
res5b_branch2a (Conv2D) (None, 7, 7, 512) 1049088 activation_42[0][0]
__________________________________________________________________________________________________
bn5b_branch2a (BatchNormalizati (None, 7, 7, 512) 2048 res5b_branch2a[0][0]
__________________________________________________________________________________________________
activation_43 (Activation) (None, 7, 7, 512) 0 bn5b_branch2a[0][0]
__________________________________________________________________________________________________
res5b_branch2b (Conv2D) (None, 7, 7, 512) 2359808 activation_43[0][0]
__________________________________________________________________________________________________
bn5b_branch2b (BatchNormalizati (None, 7, 7, 512) 2048 res5b_branch2b[0][0]
__________________________________________________________________________________________________
activation_44 (Activation) (None, 7, 7, 512) 0 bn5b_branch2b[0][0]
__________________________________________________________________________________________________
res5b_branch2c (Conv2D) (None, 7, 7, 2048) 1050624 activation_44[0][0]
__________________________________________________________________________________________________
bn5b_branch2c (BatchNormalizati (None, 7, 7, 2048) 8192 res5b_branch2c[0][0]
__________________________________________________________________________________________________
add_14 (Add) (None, 7, 7, 2048) 0 bn5b_branch2c[0][0]
activation_42[0][0]
__________________________________________________________________________________________________
activation_45 (Activation) (None, 7, 7, 2048) 0 add_14[0][0]
__________________________________________________________________________________________________
res5c_branch2a (Conv2D) (None, 7, 7, 512) 1049088 activation_45[0][0]
__________________________________________________________________________________________________
bn5c_branch2a (BatchNormalizati (None, 7, 7, 512) 2048 res5c_branch2a[0][0]
__________________________________________________________________________________________________
activation_46 (Activation) (None, 7, 7, 512) 0 bn5c_branch2a[0][0]
__________________________________________________________________________________________________
res5c_branch2b (Conv2D) (None, 7, 7, 512) 2359808 activation_46[0][0]
__________________________________________________________________________________________________
bn5c_branch2b (BatchNormalizati (None, 7, 7, 512) 2048 res5c_branch2b[0][0]
__________________________________________________________________________________________________
activation_47 (Activation) (None, 7, 7, 512) 0 bn5c_branch2b[0][0]
__________________________________________________________________________________________________
res5c_branch2c (Conv2D) (None, 7, 7, 2048) 1050624 activation_47[0][0]
__________________________________________________________________________________________________
bn5c_branch2c (BatchNormalizati (None, 7, 7, 2048) 8192 res5c_branch2c[0][0]
__________________________________________________________________________________________________
add_15 (Add) (None, 7, 7, 2048) 0 bn5c_branch2c[0][0]
activation_45[0][0]
__________________________________________________________________________________________________
activation_48 (Activation) (None, 7, 7, 2048) 0 add_15[0][0]
__________________________________________________________________________________________________
avg_pool (GlobalAveragePooling2 (None, 2048) 0 activation_48[0][0]
__________________________________________________________________________________________________
fc1000 (Dense) (None, 1000) 2049000 avg_pool[0][0]
==================================================================================================
Total params: 25,636,712
Trainable params: 25,583,592
Non-trainable params: 53,120
__________________________________________________________________________________________________
Load image to predict¶
Downsample the image¶
In [15]:
#Load in the sample image we want to predict
imgloc='shark.jpg'
img =image.load_img(imgloc) #Load in the image
print(shape(img))#Size of image
#Look at loaded image
plt.figure()
plt.imshow(img)
plt.title('Original')
plt.show() # display it
#Because the image is too big we need to downsample it in order to
#pass it to Keras. Keras needs imagesize to be matched to
#the number of input nodes in the model in this case 224x224 pxls
imgName = imgloc#'bay.jpg'
#Re- Load in the sample image we want to predict
img =image.load_img(imgName, target_size=(224,224)) #Load in the image and resize
print(shape(img))#Size of image
#Look at loaded image
plt.figure()
plt.imshow(img)
plt.title('Downsampled')
plt.show() # display it
(351, 624, 3)
(224, 224, 3)
More Preprocessing steps¶
In [16]:
#Convert image to array (flatten)
x=image.img_to_array(img)
#The neural network is actually expecting (a list) more than 1 image so we will trick it
#Add a 4th dimension to the array
x= np.expand_dims(x,axis=0)
#Normalize data to 0-1 instead of 0-255
x=resnet50.preprocess_input(x)
Run neural network and make prediction¶
In [17]:
#Now we run the normalized data through the network and predict
predictions =model.predict(x)
#We will get back a predictions object with 1000 element array.
#Each element reps a probability that the input matches each of the 1000 objects
#that the network was trained on.
#Here we use a function to tell us the names of the objects that
#the network predicted. We only want to top 10 so we ask for ony 10
prediction_classes =resnet50.decode_predictions(predictions, top=10)
#Print out all the predictions
for imagenet_id, name, likelihood in prediction_classes[0]:
print("-{}: {:2f} % likelihood".format(name, likelihood*100))
#Look at loaded image
plt.figure()
plt.imshow(img)
plt.title('Downsampled')
plt.show() # display it
-hammerhead: 65.850562 % likelihood -great_white_shark: 21.884859 % likelihood -tiger_shark: 12.248133 % likelihood -electric_ray: 0.006338 % likelihood -albatross: 0.002689 % likelihood -sturgeon: 0.002292 % likelihood -stingray: 0.001961 % likelihood -killer_whale: 0.001225 % likelihood -grey_whale: 0.000721 % likelihood -loggerhead: 0.000335 % likelihood
Put it all into a function!¶
In [31]:
def imgClasser(locc):
imgName = locc
#Re- Load in the sample image we want to predict
img =image.load_img(imgName, target_size=(224,224)) #Load in the image and resize
#Convert image to array (flatten)
x=image.img_to_array(img)
#The neural network is actually expecting (a list) more than 1 image so we will trick it
#Add a 4th dimension to the array
x= np.expand_dims(x,axis=0)
#Normalize data to 0-1 instead of 0-255
x=resnet50.preprocess_input(x)
#Now we run the normalized data through the network and predict
predictions =model.predict(x)
#We will get back a predictions object with 1000 element array.
#Each element reps a probability that the input matches each of the 1000 objects
#that the network was trained on.
#Here we use a function to tell us the names of the objects that
#the network predicted. We only want to top 10 so we ask for ony 10
prediction_classes =resnet50.decode_predictions(predictions, top=10)
#Print out all the predictions
for imagenet_id, name, likelihood in prediction_classes[0]:
print("-{}: {:2f} % likelihood".format(name, likelihood*100))
#Look at loaded image
plt.figure()
plt.imshow(img)
plt.title('Downsampled')
plt.show() # display it
Classify Image¶
Finally, we use the model to identify an object in a new image. We pass the image to the model and print the top 10 most likely objects that the model thinks it is.
In [30]:
imgClasser('burger.jpg')
-cheeseburger: 99.906200 % likelihood -bagel: 0.070201 % likelihood -hotdog: 0.012809 % likelihood -bakery: 0.003466 % likelihood -plate: 0.002827 % likelihood -French_loaf: 0.002641 % likelihood -chocolate_sauce: 0.000375 % likelihood -ice_cream: 0.000308 % likelihood -guacamole: 0.000269 % likelihood -meat_loaf: 0.000222 % likelihood
We see that the model is able to successfully identify the image as containing a cheeseburger with a 99.9% liklihood!