X = np.zeros((2 * batch_size, image_size, image_size), dtype='uint8')
        ... fill in X ...
        if part == 'train':
            X = self.augmentor.augment_batch(X)
        else:
            X = X / 255.0

Wouldn't X -> 0's if dividing by 255.0?

Python 2.7.10

1. Maybe a python 3 thing? Or a 'force you to read the code, idiot' sort of thing? :-)

python download_data.py File "download_data.py", line 28 def extract() -> None: ^ SyntaxError: invalid syntax

Deleted the '-> None' pattern after ().

2. urllib problems - Python 3 req't?

File "download_data.py", line 2, in import urllib.request ImportError: No module named request (tensorflow) priot arc-pytorch% pip install urllib Collecting urllib Downloading urllib-1.21.1.tar.gz (226kB) ... Successfully installed urllib-1.21.1 (tensorflow) priot arc-pytorch% !py python download_data.py Traceback (most recent call last): File "download_data.py", line 2, in import urllib.request ImportError: No module named request

Hi Sanyam

Let me begin by thanking you for taking your time implementing this!

I've been playing around porting your code to Tensorflow when I noticed something. The delta_caps variable in the method _get_filterbanks wants delta in the range [-1, 1] (as in zoom out, zoom in) but then in the method you take the absolute value of it.

Is there any reason for doing it like this?

Hi, thanks for the repo, it's great!

I was curious if this repo includes the 21-way Contextual ARC, or is this only the Naive ARC approach? I believe the contextual ARC has a bidirectional LSTM that uses the 21 pairwise embeddings, but I'm not sure how to implement that.

Thanks

Hi, thanks for your great implementation on ARC. Is the current version also support 3-channel RGB images as input?

I found that the implementation works fine with gray-scale input images, such as Omniglot dataset, but when I tried with different dataset with RGB images, it seems like it doesn't work.

First issue in scaling up:

Looks like one needs to analyze all the photos to train with, to get preprocess() factors like in this example:

http://blog.outcome.io/pytorch-quick-start-classifying-an-image/

Seems someone would have written a program by now to take a set of images and output the numbers for

normalize = transforms.Normalize(
   mean=[0.485, 0.456, 0.406],
   std=[0.229, 0.224, 0.225]
)
preprocess = transforms.Compose([
   transforms.Scale(256),
   transforms.CenterCrop(224),
   transforms.ToTensor(),
   normalize
])

Here's a stab at it:

import numpy as np
from PIL import Image

pic_dir = '~/images/prun299'
fileList = pic_dir + '/files'

pixCount = 0
RGB = [0.0, 0.0, 0.0]

with open(fileList) as fp:
    for line in fp:
        file = pic_dir + "/" + line.rstrip()
        try:
            im = Image.open(file)
        except Exception, e:
            print "None: %s %s" % (file, str(e))
            continue

        for x in range(im.width):
            for y in range(im.height):
                pix = im.getpixel((x, y))
                RGB[0] += pix[0]
                RGB[1] += pix[1]
                RGB[2] += pix[2]
        pixCount += im.width * im.height
        im.close()

RGB[0] /= pixCount
RGB[1] /= pixCount
RGB[2] /= pixCount

DEV = [0.0, 0.0, 0.0]

print('pass 2')

with open(fileList) as fp:
    for line in fp:
        #print('line ' + line)
        file = pic_dir + "/" + line.rstrip()
        try:
            im = Image.open(file)
        except:
            continue

        #print('file ' + file)
        for x in range(im.width):
            for y in range(im.height):
                pix = im.getpixel((x, y))
                d = RGB[0] - pix[0]
                DEV[0] += d * d
                d = RGB[1] - pix[1]
                DEV[1] += d * d
                d = RGB[2] - pix[2]
                DEV[2] += d * d
         im.close()

DEV[0] /= pixCount
DEV[1] /= pixCount
DEV[2] /= pixCount
DEV = np.sqrt(DEV)

RGB[0] /= 255
RGB[1] /= 255
RGB[2] /= 255

DEV[0] /= 255
DEV[1] /= 255
DEV[2] /= 255

print('mean=[' + str(RGB[0]) + ', ' + str(RGB[1]) + ', ' + str(RGB[2]) + '],')
print('std=[' + str(DEV[0]) + ', ' + str(DEV[1]) + ', ' + str(DEV[2]) + ']')

#  6764 files:
# mean=[0.3876046197, 0.3751385941, 0.3667266388],
# std=[0.2649736267, 0.2584158245, 0.2701408752]

Resulting in this initial loader, keras version works, this one untested.

from torchvision import models, transforms
from PIL import Image

pair_dir = '~/pb'
pic_dir = '~/images/prun299'
image_size = 299

normalize = transforms.Normalize(
 mean=[0.3876046197, 0.3751385941, 0.3667266388],
 std=[0.2649736267, 0.2584158245, 0.2701408752]
)
preprocess = transforms.Compose([
   transforms.Scale(256),
   transforms.CenterCrop(image_size),
   transforms.ToTensor(),
   normalize
])

file_map = {}

def load_preproc():
    print('Loading pics')
    scan_file(pair_dir + '/test.neg')
    scan_file(pair_dir + '/test.pos')
    scan_file(pair_dir + '/train.pos')
    scan_file(pair_dir + '/train.neg')

def scan_file(fname):
    print('Scan file: ' + fname)
    ct = 0
    ct2 = 0
    with open(fname) as fp:
        for line in fp:
            fname1, fname2 = line.split()
            if (type(file_map.get(fname1, None)) is NoneType):
                ct += 1
                img_pil = Image.open(pic_dir + '/' + fname1)
                img_tensor = preprocess(img_pil)
                img_tensor.unsqueeze_(0)
                file_map[fname1] = img_tensor
            else:
                ct2 += 1

            if (type(file_map.get(fname2, None)) is NoneType):
                ct += 1
                img_pil = Image.open(pic_dir + '/' + fname2)
                img_tensor = preprocess(img_pil)
                img_tensor.unsqueeze_(0)
                file_map[fname2] = img_tensor
            else:
                ct2 += 1

    print('    loaded: ' + str(ct) + ' already loaded: ' + str(ct2))

Here's how the keras file-load-preproc portion looks:

from keras.preprocessing import image
from keras.applications.inception_v3 import preprocess_input

                im1 = image.load_img(pic_dir + '/' + fname1, target_size=input_dim)
                x = image.img_to_array(im1)
                x = np.expand_dims(x, axis=0)
                x = preprocess_input(x)[0]
                file_map[fname1] = x

After making the same 2.7 os.makedirs() change to viz.py as in #2,

% python viz.py --load 0.677756249905 --same /Users/priot/anaconda/lib/python2.7/site-packages/matplotlib/font_manager.py:273: UserWarning: Matplotlib is building the font cache using fc-list. This may take a moment. warnings.warn('Matplotlib is building the font cache using fc-list. This may take a moment.') %

And no obvious action.

ls -l saved_models/6_8_128_cpu/0.677756249905 -rw-r--r-- 1 priot staff 433348 Aug 29 19:21 saved_models/6_8_128_cpu/0.677756249905

OSX Darwin/Macbook Pro

Lots of similar changes as in download issue #1 I closed with fix, plus this pattern:

-- train.py

< def get_pct_accuracy(pred: Variable, target) :

def get_pct_accuracy(pred, target) :