I have trained my model using faster-rcnn on my computer. As you know , using script you can only test 1 image. But I want to test all images in my test folder. I have to write a code (using loops) which enables me to do that. Is there anyone can help me about this problem. Thanks in advance. Sincerely.
Hello,
Here you can find a function that I implemented for testing
Faster R-CNN on a set of images:
def get_folder_results(detector, image_dir, device):
' The detector represents your Faster R-CNN model,
image_dir represents the folderpath containing the images,
device : the device used to train (CPU, GPU ...) '
for image in os.listdir(image_dir):
image_path = os.path.join(image_dir, image)
input_images = [T.ToTensor()(Image.open(image_path)).to(device)]
prediction = detector(images)
print(prediction)
After executing this function you will get a prediction per image where each
prediction represents the coordinates of the bounding boxes and the
corresponding class).
Related
I want to use pre-train Net, such as VGG, ResNet. While in Keras, there must be specified the formate in (w,h,3) in input_shape. If I want to specify the channel to 1, is there have more tricks?
conv_vgg = keras.application.VGG16(input_shape=(224,224,3))
I want to specify 3 to 1:
conv_vgg = keras.application.VGG16(input_shape=(224,224,1))
Thanks in advance!
Pre-trained networks as trained in imagenet or other image data sets. This means that is trained with RGB images that's why using a pretrained network requires three channels.
If you want to use pre-trained networks for a single channel image you could repeat your channel three times and proceed. (Repeat-copy two more times your 1-channel image, from (224,224,1) shape to (224,224,3) shape (3-channels image).
In an old version of my code, I used to do a hardcopy() with a given resolution, ie:
frame = hardcopy(figHandle, ['-d' renderer], ['-r' num2str(round(pixelsperinch))]);
For reference, hardcopy saves a figure window to file.
Then I would typically perform:
ZZ = rgb2gray(frame) < 255/2;
se = strel('disk',diskSize);
ZZ2 = imdilate(ZZ,se); %perform dilation.
Surface = bwarea(ZZ2); %get estimated surface (in pixels)
This worked until I switched to Matlab 2017, in which the hardcopy() function is deprecated and we are left with the print() function instead.
I am unable to extract the data from figure handler at a specific resolution using print. I've tried many things, including:
frame = print(figHandle, '-opengl', strcat('-r',num2str(round(pixelsperinch))));
But it doesn't work. How can I overcome this?
EDIT
I don't want to 'save' nor create a figure file, my aim is to extract the data from the figure in order to mesure a surface after a dilation process. I just want to keep this information and since 'im processing a LOT of different trajectories (total is approx. 1e7 trajectories), i don't want to save each file to disk (this is costly, time execution speaking). I'm running this code on a remote server (without a graphic card).
The issue I'm struggling with is: "One or more output arguments not assigned during call to "varargout"."
getframe() does not allow for setting a specific resolution (it uses current resolution instead as far as I know)
EDIT2
Ok, figured out how to do, you need to pass the '-RGBImage' argument like this:
frame = print(figHandle, ['-' renderer], ['-r' num2str(round(pixelsperinch))], '-RGBImage');
it also accept custom resolution and renderer as specified in the documentation.
I think you must specify formattype too (-dtiff in my case). I've tried this in Matlab 2016b with no problem:
print(figHandle,'-dtiff', '-opengl', '-r600', 'nameofmyfig');
EDIT:
If you need the CData just find the handle of the corresponding axes and get its CData
f = findobj('Tag','mytag')
Then depending on your matlab version use:
mycdata = get(f,'CData');
or directly
mycdta = f.CData;
EDIT 2:
You can set the tag of your image programatically and then do what I said previously:
a = imshow('peppers.png');
set(a,'Tag','mytag');
I am trying to debug a custom loss function and I would like to visualize the images generated during the intermediate computation step in the objective function. A tf_summary_image or a simple imshow would be perfect, but the summary it is not working without calling a sess.run() with a proper feed_dict. For simplicity, let's say I have:
def custom_objective(y_pred, y_true):
diff = y_pred - y_true
#Here I would need something to save and/or show the diff image
square = K.square(diff)
#Here I would need something to save and/or show the square image
mean = K.mean(square, axis=-1)
return mean
Any suggestions?
I'm looking at implementing a Caffe CNN which accepts two input images and a label (later perhaps other data) and was wondering if anyone was aware of the correct syntax in the prototxt file for doing this? Is it simply an IMAGE_DATA layer with additional tops? Or should I use separate IMAGE_DATA layers for each?
Thanks,
James
Edit: I have been using the HDF5_DATA layer lately for this and it is definitely the way to go.
HDF5 is a key value store, where each key is a string, and each value is a multi-dimensional array. Thus, to use the HDF5_DATA layer, just add a new key for each top you want to use, and set the value for that key to store the image you want to use. Writing these HDF5 files from python is easy:
import h5py
import numpy as np
filelist = []
for i in range(100):
image1 = get_some_image(i)
image2 = get_another_image(i)
filename = '/tmp/my_hdf5%d.h5' % i
with hypy.File(filename, 'w') as f:
f['data1'] = np.transpose(image1, (2, 0, 1))
f['data2'] = np.transpose(image2, (2, 0, 1))
filelist.append(filename)
with open('/tmp/filelist.txt', 'w') as f:
for filename in filelist:
f.write(filename + '\n')
Then simply set the source of the HDF5_DATA param to be '/tmp/filelist.txt', and set the tops to be "data1" and "data2".
I'm leaving the original response below:
====================================================
There are two good ways of doing this. The easiest is probably to use two separate IMAGE_DATA layers, one with the first image and label, and a second with the second image. Caffe retrieves images from LMDB or LEVELDB, which are key value stores, and assuming you create your two databases with corresponding images having the same integer id key, Caffe will in fact load the images correctly, and you can proceed to construct your net with the data/labels of both layers.
The problem with this approach is that having two data layers is not really very satisfying, and it doesn't scale very well if you want to do more advanced things like having non-integer labels for things like bounding boxes, etc. If you're prepared to make a time investment in this, you can do a better job by modifying the tools/convert_imageset.cpp file to stack images or other data across channels. For example you could create a datum with 6 channels - the first 3 for your first image's RGB, and the second 3 for your second image's RGB. After reading this in using the IMAGE_DATA layer, you can split the stream into two images using a SLICE layer with a slice_point at index 3 along the slice_dim = 1 dimension. If further down the road, you decide that you want to load even more complex assortments of data, you'll understand the encoding scheme and can write your own decoding layer based off of src/caffe/layers/data_layer.cpp to gain full control of the pipeline.
You may also consider using HDF5_DATA layer with multiple "top"s
I am trying to save an image using opencv cvSaveImage function. The problem is that I am performing a DCT on the image and then changing the coefficients that are obtained after performing the DCT, after that I am performing an inverse DCT to get back the pixel values. But this time I get the pixel values in Decimals(e.g. 254.34576). So when I save this using cvSaveImage function it discards all the values after decimals(e.g. saving 254.34576 as 254) and saves the image. Due to this my result gets affected. Please Help
"The function cvSaveImage saves the image to the specified file. The image format is chosen depending on the filename extension, see cvLoadImage. Only 8-bit single-channel or 3-channel (with 'BGR' channel order) images can be saved using this function. If the format, depth or channel order is different, use cvCvtScale and cvCvtColor to convert it before saving, or use universal cvSave to save the image to XML or YAML format."
I'd suggest investigating the cvSave function.
HOWEVER, a much easier way is to just write your own save/load functions, this would be very easy:
f = fopen("image.dat","wb");
fprintf(f,"%d%d",width,height);
for (y=0 to height)
for (x=0 to width)
fprintf(f,"%f",pixelAt(x,y));
And a corresponding mirror function for reading.
P.S. Early morning and I can't remember for the life of me if fprintf works with binary files. But you get the idea. You could use fwrite() instead.