jhabarsingh / docmed Goto Github PK

script.py:29: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray
  return np.array(data)
Traceback (most recent call last):
  File "script.py", line 109, in <module>
    pickle.dump(model, binary_file)
TypeError: can't pickle weakref objects
(env)

@csrf_exempt
def covid_xray_prediction(request, *args, **kwargs):
	"""
	Covid Detectoin From Xray Report
	"""
	if request.method == 'POST' and request.FILES['file']:
		image = request.FILES['file']
		nparr = numpy.fromstring(image, numpy.uint8)
		img = cv2.imdecode(nparr, cv2.IMREAD_COLOR)
		hasCovid = classify_xray(img)
		print(hasCovid)
		if hasCovid == 'noncovid':
			return render(request, "machine_learning/covid_xray_prediction.html", {
				'data': 'true'
			})
		image = Image.open(image).convert('RGB')
		data = predict_from_xray(image)
		return redirect("main:covid_xray_result", data)
	return render(request, "machine_learning/covid_xray_prediction.html", {
		'data': 'false'
	})

a bytes-like object is required, not 'InMemoryUploadedFile'

        1. Code Explanation (Brief)
        2. Input Format 
        3. Output Format
        4. What Model is Used?
        5. What all models were used?
        6. Why your choose the above Models?