Prediction on a Single Image NOT Included in the Validation Set about ssd_keras HOT 13 CLOSED

1. Load the image.
2. Expand the first dimension since model.predict() requires 4-D input: imgs = np.array([img])
3. Call model.predict(imgs)

from ssd_keras.

Thanks a lot for your kind help ^_^ I followed your suggestion and revised your code as below ("Revised code"). In the end I get an image "grey-colored" with blue boxes (instead of the original image which is NOT grey-colored). Can you help me to correct the revised code below? I really appreciate your kind attention and warm help!

#Revised code:

#Generate a sample
import cv2
import numpy as np

i000=Image.open('...\001.jpg')
i000.load()
i000=np.asarray(i000,dtype="float32")
X=[] # List of Images
X.append(i000)
X=np.asarray(X,dtype="float32")
i=0

#Make a prediction
y_pred = model.predict(X)
...
(The same code with [97]-[99] in train_ssd300.ipynb)

from ssd_keras.

As of the latest commit it is now also possible to use BatchGenerator to serve batches of images only (no labels).

You can do this either by passing the constructor a text file that contains the names (just the base names, not the full file paths) of the images you would like to generate:

generator = BatchGenerator(filenames='list_of_your_image_names.txt',
                           filenames_type='text',
                           images_path='path_to_directory/that_contains_the_images')

Or you could just pass a Python list that contains the full file paths of the images you would like to generate:

generator = BatchGenerator(filenames=python_list_of_your_image_paths)

Then call generator.generate() with the desired options (it must be train=False). Note that the generator returns two lists in this case, the batch of images, and a list of the names of the images in the batch.

from ssd_keras.

Thanks a lot for your kind help ^_^ I followed your suggestion and revised your code as below ("Revised code"). Then, I get an error message "AttributeError: 'numpy.ndarray' object has no attribute 'read' ". Can you help me to correct the revised code below? I really appreciate your kind attention and warm help!

#Revised code:
#Generate a sample
import cv2
import numpy as np

i000=Image.open('...\001.jpg')
i000.load()
i000=np.asarray(i000,dtype="float32")
l000=[] # List of Images
l000.append(i000)
g000 = BatchGenerator(filenames=l000)
g001 = g000.generate(batch_size=1,...,diagnostics=False)
X, filenames = next(g001) # <= I get an error message here
i = 0

#Make a prediction
y_pred = model.predict(X)
...
(The same code with [97]-[99] in train_ssd300.ipynb)

from ssd_keras.

As described in my post above, the list you pass to the constructor must contain the paths to the images, not the images themselves, i.e. your list should be

l000.append('...\001.jpg')

The batch generator loads the images for you, you only give it the paths where to find those images.

from ssd_keras.

Thanks a lot for your kind help ^_^ I am following your suggestion and two values of the predicted boxes are infinite with the error message below (The loss is 317 at this point and I continue to retrain the model). Is it because of huge loss or other problem(s)? I really appreciate your continued support!

#Error message:
Predicted boxes:
[[ 1.00e+00 1.00e+00 -inf inf 3.18e+09 3.18e+09]]
...\Anaconda3\lib\site-packages\spyder\utils\ipython\start_kernel.py:400: RuntimeWarning: overflow encountered in exp
...\Anaconda3\lib\site-packages\spyder\utils\ipython\start_kernel.py:65: RuntimeWarning: invalid value encountered in multiply
spy_cfg.InteractiveShell.xmode = 'Plain'
...\Anaconda3\lib\site-packages\spyder\utils\ipython\start_kernel.py:66: RuntimeWarning: invalid value encountered in multiply
...\Anaconda3\lib\site-packages\spyder\utils\ipython\start_kernel.py:229: RuntimeWarning: invalid value encountered in less_equal

from ssd_keras.

I got the error like " expected input_1 to have 4 dimensions, but got array with shape (687, 1087, 3)" while passing a image into model.predict([image]).
images = cv2.imread('./examples/pred_01.png')
image = np.array(images)
#Y_pred = model.predict([images])
#Y_pred = model.predict([image])
I have tried both the ways but I got the same error as mentioned the above.
I am waiting for your valuable suggestions.

from ssd_keras.

@TanmoyDL apparently the input to model.predict() needs to be an array, so the way to do it is

image = cv2.imread('./examples/pred_01.png')
y_pred = model.predict(np.array([image]))

@ecophy if the loss is 317 then something is likely very wrong and there is no point trying to make any predictions with such a model, but with the provided information I can't tell anything more specific since I know nothing about how you trained the model, on what data, etc.

from ssd_keras.

@pierluigiferrari Thanks for your kind help. It is working fine.
Now, I will test it on the video data by passing the video frames into model.predict (). I hope it should work.

from ssd_keras.

Thanks a lot for your kind help ^_^ I rebuilt the data, retrained the model then the prediction worked well :) Please, have a nice day!

from ssd_keras.

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.

from ssd_keras.

@pierluigiferrari Thanks for your kind help. It is working fine.
Now, I will test it on the video data by passing the video frames into model.predict (). I hope it should work.

Did you test on video data?

from ssd_keras.

@SahadevPoudel did you manage to detect on a video?
if so are you willing to share your code?
i got stuck and tried for several days now and would appreciate any help or hint from you :)

from ssd_keras.