if not grabbed: break #frame = cv2.resize(frame, (256,256), interpolation = cv2.INTER_LINEAR) frame = imutils.resize(frame, width= 256) #constructing a blob from our image blob = cv2.dnn.blobFromImage(cv2.resize( frame, (256, 256)), 1/255.0, (256, 256), 0, swapRB=True, crop=False) #Open the model and run forward pass with the given blob with open(model_file, "rb") as f: model_bytes = f.read() ot = OnnxTransformer(model_bytes) start = time.time() pred = ot.fit_transform(blob) end = time.time() # Infer the total number of classes, height and width (numClasses, height, width) = pred.shape[1:4] # Argmax is utilized to find the class label with largest probability for every pixel in the image classMap = np.argmax(pred[0], axis=0) # classes are mapped to their respective colours mask = COLORS[classMap] # resizing the mask and class map to match its dimensions with the input image mask = cv2.resize( mask, (frame.shape[1], frame.shape[0]), interpolation=cv2.INTER_NEAREST) classMap = cv2.resize(
#####################################
# Let's create the OnnxTransformer
# which we apply on that particular image.
with open(model_file, "rb") as f:
model_bytes = f.read()
ot = OnnxTransformer(model_bytes)
img2 = img.resize((224, 224))
X = np.asarray(img2).transpose((2, 0, 1))
X = X[np.newaxis, :, :, :] / 255.0
print(X.shape, X.min(), X.max())
pred = ot.fit_transform(X)[0, :]
print(pred.shape)
#############################
# And the best classes are...
results = nlargest(10, range(pred.shape[0]), pred.take)
print(results)
data = [{
"index": i,
"label": labels.get(str(i), ('?', '?'))[1],
'score': pred[i]
} for i in results]
df = pandas.DataFrame(data)
print(df)