I’m attempting to do the Digits Kaggle challenge as a first data set and I think I have created the ImageClassifier correctly but I’m getting an error when I come to run the learning rate finder.
The training data set is given as a csv file where each row in the csv has a label as the first column specifying what the number is and then the next 783 columns are a pixel grayscale value of an image of the handwritten digit. The images are 28 x 28 but given as a single row.
Given that I don’t have a folder of images, I am trying to use the ImageClassifierData.from_arrays. I have created 4 ndarrays: train_vals, train_Y, valid_vals and valid_Y, where train_vals is (33600, 28, 28), train_Y is (33600,), valid_vals is (8400, 28, 28) and valid_Y is (8400,).
I can create Python Images from the 28 x 28 arrays using Image.fromarray(img_data.astype(np.uint8)) where img_data is the (28, 28) ndarray and can see each of the handwritten digits.
I have defined a function to get the data:
def get_data(sz, bs): tfms = tfms_from_model(arch, sz, aug_tfms=transforms_basic, max_zoom=1.1) return ImageClassifierData.from_arrays(PATH, trn=(train_imgs, train_Y), val=(valid_imgs, valid_Y), bs=bs, tfms=tfms)
I’m using resnet34 with sz=28 and bs=64 and I’m creating the learn object as:
learn = ConvLearner.pretrained(arch, data)
However, when I run
learn.lr_find() I get the following error:
~/fastai/courses/dl1/fastai/transforms.py in transform(self, x, y) 223 224 def transform(self, x, y=None): --> 225 x = self.do_transform(x,False) 226 return (x, self.do_transform(y,True)) if y is not None else x 227 ~/fastai/courses/dl1/fastai/transforms.py in do_transform(self, x, is_y) 383 def do_transform(self, x, is_y): 384 if is_y: return scale_min(x, self.store.new_sz_y, cv2.INTER_NEAREST) --> 385 else : return scale_min(x, self.store.new_sz, cv2.INTER_AREA ) 386 387 ~/fastai/courses/dl1/fastai/transforms.py in scale_min(im, targ, interpolation) 13 ratio = targ/min(r,c) 14 sz = (scale_to(c, ratio, targ), scale_to(r, ratio, targ)) ---> 15 return cv2.resize(im, sz, interpolation=interpolation) 16 17 def zoom_cv(x,z): error: /io/opencv/modules/imgproc/src/imgwarp.cpp:3361: error: (-215) func != 0 in function resize
I saw in another post that it might be because the resize is expecting Images so I tried converting my 28 x 28 ndarrays to Images, which forced me to change my train_vals into a list of Images but the ImageClassifierData.from_arrays won’t take a list as the dataset.
I’m very new to this so I’m not quite sure which direction to go from here.
I realized one of my problems was that resnet is expecting RGB images and the digits only have the one grayscale channel, so I was able to add an extra axis (42000, 28, 28, 1) and then broadcast_to (42000, 28, 28, 3) to turn the images into 3 channels (albeit duplicating the monochrome channel 3X). I can now run the lr_find() successfully so long as I don’t use data_augmentation or zooming, which is a bit of a bummer. I would love to know a way to get aug working with ndarray images.
After doing a fit with differential learning rates [lr/9, lr/3, lr] I managed to get it to 0.993. Its not bad but not in the the top 50 but its without any augmentation so I wonder how the results would be with data augmentation and TTA.