I have this model:
class Image(models.Model):
title = models.CharField(max_length=200)
image = models.ImageField(upload_to='img/')
signature = models.TextField(null = True)
The signature is a numpy monodimensional vector encoded in json. In order to make my query, I have to decode each object signature into a nparray, and make a dot product between each object's signature and a given vector, then annotate as a float (named "score") field beside each raw. Lastly I have to order from max to min.
I tried this in view.py
def image_sorted(request):
query_signature = extract_feat(settings.MEDIA_ROOT + "/cache" + "/003_ant_image_0003.jpg") # a NParray object
image_list = Image.objects.annotate(score=np.dot(
JSONVectConverter.json_to_vect(F('signature')), query_signature.T
).astype(float)).order_by('score') #JSONVectConverter is a class of mine
return render(request, 'images/sorted.html', {'image_sorted': image_list})
of course it doesn't work. I think "F()" operator is out of scope...
If you're wondering, I'm writing an image retrieval webapp for my university thesis.
Thank you.
EDIT: I found this that is quite the same problem (He use postgres instead of MySQL)
EDIT2: I just remember now what is the last solution I've adopted! First I pull out every vector from the DB and mantain it in RAM, then I make some simple computes to find the K-Nearest Neighbors. Then, I retrieve from the DB the respective image using its index (primary key). So I decouple this task from Django ORM. Here's the code (from the Rest API)
def query_over_db(query_signature, page):
query_signature = np.array(query_signature)
t0 = time.time()
descriptor_matrix = cache.get('descriptor_matrix')
id_vector = cache.get('id_vector')
if not descriptor_matrix:
id_vector = []
descriptor_matrix = []
images_dict = Image.objects.all().values('id', 'signature')
for image in images_dict:
s = image['signature']
descriptor = np.array(s)
descriptor_matrix.append(descriptor)
id_vector.append(image['id'])
cache.set('id_vector', id_vector)
cache.set('descriptor_matrix', descriptor_matrix)
t1 = time.time()
print("time to pull out the descriptors : " + str(t1 - t0))
t1 = time.time()
#result = np.abs(np.dot(descriptor_matrix, query_signature.T))
#result = np.sum((descriptor_matrix - query_signature)**2, axis=1)
result = ne.evaluate('sum((descriptor_matrix - query_signature)**2, axis=1)')
t2 = time.time()
print("time to calculate similarity: " + str(t2 - t1))
perm = np.argsort(result)[(page - 1) * 30:page * 30]
print(perm.shape)
print(len(id_vector))
perm_id = np.array(id_vector)[perm]
print(len(perm_id))
print("printing sort")
print(np.sort(result)[0])
t4 = time.time()
print("time to order the result: " + str(t4 - t2))
qs = Image.objects.defer('signature').filter(id__in=perm_id.tolist())
qs_new = []
for i in range(len(perm_id)):
qs_new.append(qs.get(id=perm_id[i]))
t3 = time.time()
print("time to get the results from the DB : " + str(t3 - t2))
print("total time : " + str(t3 - t0))
print(result[perm])
return qs_new
I didn't come close to trying something this complex, however I've solved a similar issue here: Combining Django F, Value and a dict to annotate a queryset
I haven't tried this but you could give it a go:
from django.db.models import Case, When, FloatField
query_signature = extract_feat(settings.MEDIA_ROOT + "/cache" + "/003_ant_image_0003.jpg") # a NParray object
value_dict = {}
for image in Image.objects.all():
value_dict[image.signature] = np.dot(
JSONVectConverter.json_to_vect(image.signature),
query_signature.T
).astype(float)
whens = [
When(signature=k, then=v) for k, v in value_dict.items()
]
qs = Image.objects.all().annotate(
score=Case(
*whens,
default=0,
output_field=FloatField()
)
).order_by('score')
Hope it helps