How to resize image regions for CNN?

Question

I am using AlexNet for object recognition. I have trained my model using images with size (277,277). Then have used Selective search algorithm to extract regions from image and feeding those regions to network for testing/prediction. How ever when I resize image regions(from SelectiveSearch), it gives error.

Code For resizing Training Images:

try:
 img_array = cv2.imread(os.path.join(path,img))
 new_array = cv2.resize(img_array, (IMG_SIZE, IMG_SIZE))
 gray_img = cv2.cvtColor(new_array, cv2.COLOR_BGR2GRAY)
 training_data.append([gray_img, class_num])

except Exception as e:
 pass

code for resizing selected image regions:

img_lbl, regions = selectivesearch.selective_search(img, scale=500, sigma=0.4, min_size=10)
for r in regions:
 x, y, w, h = r['rect']
 segment = img[y:y + h, x:x + w]
 gray_img = cv2.resize(segment, (277, 277))
 gray_img = cv2.cvtColor(gray_img, cv2.COLOR_BGR2GRAY)
 gray_img = np.array(gray_img).reshape(-1, 277, 277, 1)
 gray_img = gray_img / 255.0
 prediction = model.predict(gray_img)

it gives error on last line i.e:

prediction = model.predict(gray_img)

and error is:

Error: Error when checking input: expected conv2d_1_input to have shape (227, 227, 1) but got array with shape (277, 277, 1)

When both shapes are same then why it is giving this error.

can you show the neural_network you created with all the layers and stuff? — Parthik B., Jul 19 '19 at 10:36
I am sorry i forgot to update. I have solved this issue. I my self don't know what was the issue but when I rewrite the code it was working fine. — Umama Khalid, Jul 20 '19 at 11:05

Karaszka · Answer 1 · 2019-07-19T10:18:22.243

1

Your model is expecting a tensor as an input, but you are trying to evaluate on a numpy array. Instead use placeholder of a given shape and then feed your array into this placeholder in a session.

# define a placeholder for input 
image = tf.placeholder(dtype=tf.float32, name="image", shape=[277,277,1])
prediction = model.predict(image)

# evaluate each of your resized images in a session
with tf.Session() as sess:
    for r in regions:
        x, y, w, h = r['rect']
        # rest of your code from the loop here 
        gray_img = gray_img /255.
        p = sess.run(prediction, feed_dict={image: gray_img})
        print(p) # to print the prediction of your model for this image

Maybe you should take a look at this question: What's the difference between tf.placeholder and tf.Variable?

edited Jul 19 '19 at 10:18

answered Jul 18 '19 at 15:50

Karaszka

306
3
12

Should I remove that resize and reshape lines of code and place these lines? or I should place these lines after resizing and reshaping image. – Umama Khalid Jul 18 '19 at 16:07
Now it is giving me this error: Error: cannot reshape array of size 6900 into shape (277,277,1) – Umama Khalid Jul 18 '19 at 16:12
Your code is incomplete, so I can't tell you exactly why are you getting this error. Generally you want to define your model with a placeholder as an input and then you want to map a value (resized image) to this placeholder. – Karaszka Jul 19 '19 at 10:08
Sure @UmamaKhalid! Consider upvoting my answer if you used the code I posted. – Karaszka Jul 31 '19 at 12:53

How to resize image regions for CNN?

1 Answers1