def recognizeImage():
gpu_available = torch.cuda.is_available()
base64string = request.get_json(force=True)['base64']
image = get_image(base64string)
if image.shape[1:] != (3, 32, 32):
return jsonify(error="only RGB image 32x32 accepted",
message="failure!")
model = get_model()
# breakpoint()
# get sample outputs
# breakpoint()
output_tensor = model(image.cuda())
output_tensor = Softmax(dim=1)(output_tensor)
prob_pred_tensor, pred_tensor = torch.max(output_tensor, 1)
output = np.squeeze(
output_tensor.detach().numpy()) if not gpu_available else np.squeeze(
output_tensor.cpu().detach().numpy())
prob_pred = np.squeeze(prob_pred_tensor.detach().numpy()
) if not gpu_available else np.squeeze(
prob_pred_tensor.cpu().detach().numpy())
pred = np.squeeze(
pred_tensor.detach().numpy()) if not gpu_available else np.squeeze(
pred_tensor.cpu().detach().numpy())
classes = [
'airplane', 'automobile', 'bird', 'cat', 'deer', 'dog', 'frog',
'horse', 'ship', 'truck'
]
pred_dict = {
'predicted_class': str(classes[pred]),
'prob_predicted_class': str(prob_pred)
}
for i, prob in enumerate(output):
pred_dict[classes[i]] = str(prob)
return jsonify(prediction=pred_dict, message="success!")
def recognizeImage():
try:
base64string = request.get_json(force=True)['base64']
except:
return jsonify(error="payload does not have base64",
message='failure!')
try:
image = get_image(base64string)
except:
return jsonify(error='improper base64 encoding', message="failure!")
if image.shape[1:] != (3, 32, 32):
return jsonify(error="only RGB image 32x32 accepted",
message="failure!")
model = get_model()
output_tensor = model(image)
output_tensor = Softmax(dim=1)(output_tensor)
prob_pred_tensor, pred_tensor = torch.max(output_tensor, 1)
output = np.squeeze(output_tensor.detach().numpy())
prob_pred = np.squeeze(prob_pred_tensor.detach().numpy())
pred = np.squeeze(pred_tensor.detach().numpy())
classes = [
'airplane', 'automobile', 'bird', 'cat', 'deer', 'dog', 'frog',
'horse', 'ship', 'truck'
]
pred_dict = {
'predicted_class': str(classes[pred]),
'prob_predicted_class': str(prob_pred)
}
for i, prob in enumerate(output):
pred_dict[classes[i]] = str(prob)
return jsonify(prediction=pred_dict, message="success!")
def recognizeImage(uploadfile,localfile):
if (localfile and uploadfile) or (not(localfile) and not(uploadfile)):
return {'error' : 'either upload an image OR give path to local DFS file', 'message' : 'failure!'}
elif uploadfile and not(localfile):
imagefile = uploadfile
elif localfile and not(uploadfile):
imagefile = localfile
# gpu_available = torch.cuda.is_available()
image = get_image(imagefile)
if image.shape[1:] != (3,32,32):
return {'error' : "only RGB image 32x32 accepted", 'message' : "failure!" }
model = get_model()
output_tensor = model(image)
output_tensor = Softmax(dim=1)(output_tensor)
prob_pred_tensor, pred_tensor = torch.max(output_tensor, 1)
output = np.squeeze(output_tensor.detach().numpy())
prob_pred = np.squeeze(prob_pred_tensor.detach().numpy())
pred = np.squeeze(pred_tensor.detach().numpy())
classes = ['airplane', 'automobile', 'bird', 'cat', 'deer','dog', 'frog', 'horse', 'ship', 'truck']
pred_dict = {'predicted_class' : str(classes[pred]),
'prob_predicted_class' : str(prob_pred)}
for i,prob in enumerate(output):
pred_dict[classes[i]] = str(prob)
return {'prediction' : pred_dict, 'message' : "success!" }