Note

Go to the end to download the full example code

Segmentation tutorial

This example demonstrates image segmentation with an Akida-compatible model as illustrated through person segmentation using the Portrait128 dataset.

Using pre-trained models for quick runtime, this example shows the evolution of model performance for a trained keras floating point model, a keras quantized and Quantization Aware Trained (QAT) model, and an Akida-converted model. Notice that the performance of the original keras floating point model is maintained throughout the model conversion flow.

1. Load the dataset

import os
import numpy as np
from akida_models import fetch_file

# Download validation set from Brainchip data server, it contains 10% of the original dataset
data_path = fetch_file(fname="val.tar.gz",
                       origin="https://data.brainchip.com/dataset-mirror/portrait128/val.tar.gz",
                       cache_subdir=os.path.join("datasets", "portrait128"),
                       extract=True)

data_dir = os.path.join(os.path.dirname(data_path), "val")
x_val = np.load(os.path.join(data_dir, "val_img.npy"))
y_val = np.load(os.path.join(data_dir, "val_msk.npy")).astype('uint8')
batch_size = 32
steps = x_val.shape[0] // 32

# Visualize some data
import matplotlib.pyplot as plt

id = np.random.randint(0, x_val.shape[0])

fig, axs = plt.subplots(3, 3, constrained_layout=True)
for col in range(3):
    axs[0, col].imshow(x_val[id + col] / 255.)
    axs[0, col].axis('off')
    axs[1, col].imshow(1 - y_val[id + col], cmap='Greys')
    axs[1, col].axis('off')
    axs[2, col].imshow(x_val[id + col] / 255. * y_val[id + col])
    axs[2, col].axis('off')

fig.suptitle('Image, mask and masked image', fontsize=10)
plt.show()
Image, mask and masked image
Downloading data from https://data.brainchip.com/dataset-mirror/portrait128/val.tar.gz.

        0/267313385 [..............................] - ETA: 0s
   122880/267313385 [..............................] - ETA: 1:52
   638976/267313385 [..............................] - ETA: 42s 
  1220608/267313385 [..............................] - ETA: 33s
  1802240/267313385 [..............................] - ETA: 29s
  2269184/267313385 [..............................] - ETA: 29s
  2539520/267313385 [..............................] - ETA: 31s
  3104768/267313385 [..............................] - ETA: 30s
  3694592/267313385 [..............................] - ETA: 29s
  4276224/267313385 [..............................] - ETA: 28s
  4882432/267313385 [..............................] - ETA: 27s
  5464064/267313385 [..............................] - ETA: 26s
  6037504/267313385 [..............................] - ETA: 26s
  6627328/267313385 [..............................] - ETA: 25s
  7217152/267313385 [..............................] - ETA: 25s
  7806976/267313385 [..............................] - ETA: 25s
  8396800/267313385 [..............................] - ETA: 25s
  9003008/267313385 [>.............................] - ETA: 24s
  9592832/267313385 [>.............................] - ETA: 24s
 10141696/267313385 [>.............................] - ETA: 24s
 10780672/267313385 [>.............................] - ETA: 24s
 11386880/267313385 [>.............................] - ETA: 23s
 11976704/267313385 [>.............................] - ETA: 23s
 12566528/267313385 [>.............................] - ETA: 23s
 13156352/267313385 [>.............................] - ETA: 23s
 13746176/267313385 [>.............................] - ETA: 23s
 14336000/267313385 [>.............................] - ETA: 23s
 14925824/267313385 [>.............................] - ETA: 23s
 15515648/267313385 [>.............................] - ETA: 23s
 16089088/267313385 [>.............................] - ETA: 22s
 16678912/267313385 [>.............................] - ETA: 22s
 17268736/267313385 [>.............................] - ETA: 22s
 17858560/267313385 [=>............................] - ETA: 22s
 18448384/267313385 [=>............................] - ETA: 22s
 19038208/267313385 [=>............................] - ETA: 22s
 19628032/267313385 [=>............................] - ETA: 22s
 20217856/267313385 [=>............................] - ETA: 22s
 20807680/267313385 [=>............................] - ETA: 22s
 21397504/267313385 [=>............................] - ETA: 22s
 21987328/267313385 [=>............................] - ETA: 21s
 22577152/267313385 [=>............................] - ETA: 21s
 23166976/267313385 [=>............................] - ETA: 21s
 23756800/267313385 [=>............................] - ETA: 21s
 24346624/267313385 [=>............................] - ETA: 21s
 24936448/267313385 [=>............................] - ETA: 21s
 25526272/267313385 [=>............................] - ETA: 21s
 26116096/267313385 [=>............................] - ETA: 21s
 26705920/267313385 [=>............................] - ETA: 21s
 27295744/267313385 [==>...........................] - ETA: 21s
 27885568/267313385 [==>...........................] - ETA: 21s
 28475392/267313385 [==>...........................] - ETA: 21s
 29065216/267313385 [==>...........................] - ETA: 21s
 29655040/267313385 [==>...........................] - ETA: 21s
 30228480/267313385 [==>...........................] - ETA: 22s
 31096832/267313385 [==>...........................] - ETA: 21s
 32079872/267313385 [==>...........................] - ETA: 21s
 33865728/267313385 [==>...........................] - ETA: 20s
 34455552/267313385 [==>...........................] - ETA: 20s
 35045376/267313385 [==>...........................] - ETA: 20s
 35635200/267313385 [==>...........................] - ETA: 20s
 36225024/267313385 [===>..........................] - ETA: 20s
 36814848/267313385 [===>..........................] - ETA: 20s
 37404672/267313385 [===>..........................] - ETA: 20s
 37994496/267313385 [===>..........................] - ETA: 20s
 38584320/267313385 [===>..........................] - ETA: 20s
 39174144/267313385 [===>..........................] - ETA: 20s
 39763968/267313385 [===>..........................] - ETA: 19s
 40353792/267313385 [===>..........................] - ETA: 19s
 40943616/267313385 [===>..........................] - ETA: 19s
 41533440/267313385 [===>..........................] - ETA: 19s
 42090496/267313385 [===>..........................] - ETA: 19s
 42647552/267313385 [===>..........................] - ETA: 19s
 43204608/267313385 [===>..........................] - ETA: 19s
 43761664/267313385 [===>..........................] - ETA: 19s
 44318720/267313385 [===>..........................] - ETA: 19s
 44859392/267313385 [====>.........................] - ETA: 19s
 45416448/267313385 [====>.........................] - ETA: 19s
 45957120/267313385 [====>.........................] - ETA: 19s
 46530560/267313385 [====>.........................] - ETA: 19s
 47087616/267313385 [====>.........................] - ETA: 19s
 47644672/267313385 [====>.........................] - ETA: 19s
 48201728/267313385 [====>.........................] - ETA: 19s
 48791552/267313385 [====>.........................] - ETA: 19s
 49381376/267313385 [====>.........................] - ETA: 19s
 49905664/267313385 [====>.........................] - ETA: 19s
 50085888/267313385 [====>.........................] - ETA: 19s
 51200000/267313385 [====>.........................] - ETA: 19s
 52559872/267313385 [====>.........................] - ETA: 19s
 53018624/267313385 [====>.........................] - ETA: 19s
 53608448/267313385 [=====>........................] - ETA: 19s
 54198272/267313385 [=====>........................] - ETA: 18s
 54788096/267313385 [=====>........................] - ETA: 18s
 55361536/267313385 [=====>........................] - ETA: 18s
 55951360/267313385 [=====>........................] - ETA: 18s
 56541184/267313385 [=====>........................] - ETA: 18s
 57131008/267313385 [=====>........................] - ETA: 18s
 57720832/267313385 [=====>........................] - ETA: 18s
 58310656/267313385 [=====>........................] - ETA: 18s
 58900480/267313385 [=====>........................] - ETA: 18s
 59490304/267313385 [=====>........................] - ETA: 18s
 60080128/267313385 [=====>........................] - ETA: 18s
 60669952/267313385 [=====>........................] - ETA: 18s
 61243392/267313385 [=====>........................] - ETA: 18s
 61833216/267313385 [=====>........................] - ETA: 18s
 62423040/267313385 [======>.......................] - ETA: 18s
 62947328/267313385 [======>.......................] - ETA: 18s
 63291392/267313385 [======>.......................] - ETA: 18s
 63881216/267313385 [======>.......................] - ETA: 18s
 64454656/267313385 [======>.......................] - ETA: 18s
 65044480/267313385 [======>.......................] - ETA: 17s
 65634304/267313385 [======>.......................] - ETA: 17s
 66224128/267313385 [======>.......................] - ETA: 17s
 66584576/267313385 [======>.......................] - ETA: 17s
 67141632/267313385 [======>.......................] - ETA: 17s
 67731456/267313385 [======>.......................] - ETA: 17s
 68321280/267313385 [======>.......................] - ETA: 17s
 68911104/267313385 [======>.......................] - ETA: 17s
 69500928/267313385 [======>.......................] - ETA: 17s
 70041600/267313385 [======>.......................] - ETA: 17s
 70582272/267313385 [======>.......................] - ETA: 17s
 71122944/267313385 [======>.......................] - ETA: 17s
 71663616/267313385 [=======>......................] - ETA: 17s
 72187904/267313385 [=======>......................] - ETA: 17s
 72777728/267313385 [=======>......................] - ETA: 17s
 73367552/267313385 [=======>......................] - ETA: 17s
 73957376/267313385 [=======>......................] - ETA: 17s
 74547200/267313385 [=======>......................] - ETA: 17s
 75120640/267313385 [=======>......................] - ETA: 17s
 75661312/267313385 [=======>......................] - ETA: 17s
 76201984/267313385 [=======>......................] - ETA: 17s
 76742656/267313385 [=======>......................] - ETA: 16s
 77266944/267313385 [=======>......................] - ETA: 16s
 77791232/267313385 [=======>......................] - ETA: 16s
 78381056/267313385 [=======>......................] - ETA: 16s
 78970880/267313385 [=======>......................] - ETA: 16s
 79560704/267313385 [=======>......................] - ETA: 16s
 80150528/267313385 [=======>......................] - ETA: 16s
 80740352/267313385 [========>.....................] - ETA: 16s
 81281024/267313385 [========>.....................] - ETA: 16s
 81821696/267313385 [========>.....................] - ETA: 16s
 82362368/267313385 [========>.....................] - ETA: 16s
 82886656/267313385 [========>.....................] - ETA: 16s
 83410944/267313385 [========>.....................] - ETA: 16s
 83951616/267313385 [========>.....................] - ETA: 16s
 84541440/267313385 [========>.....................] - ETA: 16s
 85131264/267313385 [========>.....................] - ETA: 16s
 85721088/267313385 [========>.....................] - ETA: 16s
 86310912/267313385 [========>.....................] - ETA: 16s
 86900736/267313385 [========>.....................] - ETA: 16s
 87441408/267313385 [========>.....................] - ETA: 16s
 87982080/267313385 [========>.....................] - ETA: 16s
 88522752/267313385 [========>.....................] - ETA: 15s
 89047040/267313385 [========>.....................] - ETA: 15s
 89571328/267313385 [=========>....................] - ETA: 15s
 90095616/267313385 [=========>....................] - ETA: 15s
 90685440/267313385 [=========>....................] - ETA: 15s
 91258880/267313385 [=========>....................] - ETA: 15s
 91848704/267313385 [=========>....................] - ETA: 15s
 92438528/267313385 [=========>....................] - ETA: 15s
 93028352/267313385 [=========>....................] - ETA: 15s
 93585408/267313385 [=========>....................] - ETA: 15s
 94126080/267313385 [=========>....................] - ETA: 15s
 94666752/267313385 [=========>....................] - ETA: 15s
 95191040/267313385 [=========>....................] - ETA: 15s
 95715328/267313385 [=========>....................] - ETA: 15s
 96239616/267313385 [=========>....................] - ETA: 15s
 96813056/267313385 [=========>....................] - ETA: 15s
 97353728/267313385 [=========>....................] - ETA: 15s
 97910784/267313385 [=========>....................] - ETA: 15s
 98467840/267313385 [==========>...................] - ETA: 15s
 99024896/267313385 [==========>...................] - ETA: 15s
 99532800/267313385 [==========>...................] - ETA: 15s
100024320/267313385 [==========>...................] - ETA: 15s
100515840/267313385 [==========>...................] - ETA: 14s
101023744/267313385 [==========>...................] - ETA: 14s
101548032/267313385 [==========>...................] - ETA: 14s
102055936/267313385 [==========>...................] - ETA: 14s
102629376/267313385 [==========>...................] - ETA: 14s
103219200/267313385 [==========>...................] - ETA: 14s
103809024/267313385 [==========>...................] - ETA: 14s
104398848/267313385 [==========>...................] - ETA: 14s
104988672/267313385 [==========>...................] - ETA: 14s
105529344/267313385 [==========>...................] - ETA: 14s
106070016/267313385 [==========>...................] - ETA: 14s
106610688/267313385 [==========>...................] - ETA: 14s
107134976/267313385 [===========>..................] - ETA: 14s
107659264/267313385 [===========>..................] - ETA: 14s
108199936/267313385 [===========>..................] - ETA: 14s
108789760/267313385 [===========>..................] - ETA: 14s
109379584/267313385 [===========>..................] - ETA: 14s
109969408/267313385 [===========>..................] - ETA: 14s
110559232/267313385 [===========>..................] - ETA: 14s
111149056/267313385 [===========>..................] - ETA: 14s
111689728/267313385 [===========>..................] - ETA: 13s
112230400/267313385 [===========>..................] - ETA: 13s
112754688/267313385 [===========>..................] - ETA: 13s
113278976/267313385 [===========>..................] - ETA: 13s
113786880/267313385 [===========>..................] - ETA: 13s
114327552/267313385 [===========>..................] - ETA: 13s
114917376/267313385 [===========>..................] - ETA: 13s
115507200/267313385 [===========>..................] - ETA: 13s
116097024/267313385 [============>.................] - ETA: 13s
116686848/267313385 [============>.................] - ETA: 13s
117260288/267313385 [============>.................] - ETA: 13s
117800960/267313385 [============>.................] - ETA: 13s
118325248/267313385 [============>.................] - ETA: 13s
118849536/267313385 [============>.................] - ETA: 13s
119357440/267313385 [============>.................] - ETA: 13s
119881728/267313385 [============>.................] - ETA: 13s
120471552/267313385 [============>.................] - ETA: 13s
121061376/267313385 [============>.................] - ETA: 13s
121651200/267313385 [============>.................] - ETA: 13s
122241024/267313385 [============>.................] - ETA: 13s
122830848/267313385 [============>.................] - ETA: 13s
123404288/267313385 [============>.................] - ETA: 12s
123994112/267313385 [============>.................] - ETA: 12s
124567552/267313385 [============>.................] - ETA: 12s
125157376/267313385 [=============>................] - ETA: 12s
125747200/267313385 [=============>................] - ETA: 12s
126337024/267313385 [=============>................] - ETA: 12s
126926848/267313385 [=============>................] - ETA: 12s
127516672/267313385 [=============>................] - ETA: 12s
128106496/267313385 [=============>................] - ETA: 12s
128696320/267313385 [=============>................] - ETA: 12s
129269760/267313385 [=============>................] - ETA: 12s
129826816/267313385 [=============>................] - ETA: 12s
130318336/267313385 [=============>................] - ETA: 12s
130809856/267313385 [=============>................] - ETA: 12s
131284992/267313385 [=============>................] - ETA: 12s
131776512/267313385 [=============>................] - ETA: 12s
132268032/267313385 [=============>................] - ETA: 12s
132726784/267313385 [=============>................] - ETA: 12s
133464064/267313385 [=============>................] - ETA: 12s
134037504/267313385 [==============>...............] - ETA: 12s
134627328/267313385 [==============>...............] - ETA: 11s
135200768/267313385 [==============>...............] - ETA: 11s
135790592/267313385 [==============>...............] - ETA: 11s
136380416/267313385 [==============>...............] - ETA: 11s
136970240/267313385 [==============>...............] - ETA: 11s
137543680/267313385 [==============>...............] - ETA: 11s
138117120/267313385 [==============>...............] - ETA: 11s
138674176/267313385 [==============>...............] - ETA: 11s
139247616/267313385 [==============>...............] - ETA: 11s
139821056/267313385 [==============>...............] - ETA: 11s
140394496/267313385 [==============>...............] - ETA: 11s
140967936/267313385 [==============>...............] - ETA: 11s
141541376/267313385 [==============>...............] - ETA: 11s
142114816/267313385 [==============>...............] - ETA: 11s
142688256/267313385 [===============>..............] - ETA: 11s
143261696/267313385 [===============>..............] - ETA: 11s
143835136/267313385 [===============>..............] - ETA: 11s
144408576/267313385 [===============>..............] - ETA: 11s
144998400/267313385 [===============>..............] - ETA: 11s
145571840/267313385 [===============>..............] - ETA: 10s
146145280/267313385 [===============>..............] - ETA: 10s
146718720/267313385 [===============>..............] - ETA: 10s
147275776/267313385 [===============>..............] - ETA: 10s
147849216/267313385 [===============>..............] - ETA: 10s
148439040/267313385 [===============>..............] - ETA: 10s
149028864/267313385 [===============>..............] - ETA: 10s
149618688/267313385 [===============>..............] - ETA: 10s
150208512/267313385 [===============>..............] - ETA: 10s
150781952/267313385 [===============>..............] - ETA: 10s
151388160/267313385 [===============>..............] - ETA: 10s
151961600/267313385 [================>.............] - ETA: 10s
152518656/267313385 [================>.............] - ETA: 10s
153075712/267313385 [================>.............] - ETA: 10s
153632768/267313385 [================>.............] - ETA: 10s
154189824/267313385 [================>.............] - ETA: 10s
154730496/267313385 [================>.............] - ETA: 10s
155238400/267313385 [================>.............] - ETA: 10s
155893760/267313385 [================>.............] - ETA: 10s
156450816/267313385 [================>.............] - ETA: 9s 
157007872/267313385 [================>.............] - ETA: 9s
157564928/267313385 [================>.............] - ETA: 9s
158121984/267313385 [================>.............] - ETA: 9s
158679040/267313385 [================>.............] - ETA: 9s
159268864/267313385 [================>.............] - ETA: 9s
159858688/267313385 [================>.............] - ETA: 9s
160448512/267313385 [=================>............] - ETA: 9s
161038336/267313385 [=================>............] - ETA: 9s
161628160/267313385 [=================>............] - ETA: 9s
162217984/267313385 [=================>............] - ETA: 9s
162807808/267313385 [=================>............] - ETA: 9s
163397632/267313385 [=================>............] - ETA: 9s
163971072/267313385 [=================>............] - ETA: 9s
164511744/267313385 [=================>............] - ETA: 9s
165052416/267313385 [=================>............] - ETA: 9s
165576704/267313385 [=================>............] - ETA: 9s
166100992/267313385 [=================>............] - ETA: 9s
166625280/267313385 [=================>............] - ETA: 9s
167215104/267313385 [=================>............] - ETA: 8s
167804928/267313385 [=================>............] - ETA: 8s
168394752/267313385 [=================>............] - ETA: 8s
168984576/267313385 [=================>............] - ETA: 8s
169574400/267313385 [==================>...........] - ETA: 8s
170164224/267313385 [==================>...........] - ETA: 8s
170754048/267313385 [==================>...........] - ETA: 8s
171343872/267313385 [==================>...........] - ETA: 8s
171933696/267313385 [==================>...........] - ETA: 8s
172523520/267313385 [==================>...........] - ETA: 8s
173113344/267313385 [==================>...........] - ETA: 8s
173703168/267313385 [==================>...........] - ETA: 8s
174292992/267313385 [==================>...........] - ETA: 8s
174882816/267313385 [==================>...........] - ETA: 8s
175472640/267313385 [==================>...........] - ETA: 8s
176029696/267313385 [==================>...........] - ETA: 8s
176619520/267313385 [==================>...........] - ETA: 8s
177209344/267313385 [==================>...........] - ETA: 8s
177799168/267313385 [==================>...........] - ETA: 8s
178388992/267313385 [===================>..........] - ETA: 7s
178978816/267313385 [===================>..........] - ETA: 7s
179568640/267313385 [===================>..........] - ETA: 7s
180158464/267313385 [===================>..........] - ETA: 7s
180748288/267313385 [===================>..........] - ETA: 7s
181338112/267313385 [===================>..........] - ETA: 7s
181927936/267313385 [===================>..........] - ETA: 7s
182517760/267313385 [===================>..........] - ETA: 7s
183107584/267313385 [===================>..........] - ETA: 7s
183697408/267313385 [===================>..........] - ETA: 7s
184287232/267313385 [===================>..........] - ETA: 7s
184860672/267313385 [===================>..........] - ETA: 7s
185466880/267313385 [===================>..........] - ETA: 7s
186056704/267313385 [===================>..........] - ETA: 7s
186646528/267313385 [===================>..........] - ETA: 7s
187236352/267313385 [====================>.........] - ETA: 7s
187826176/267313385 [====================>.........] - ETA: 7s
188416000/267313385 [====================>.........] - ETA: 7s
189005824/267313385 [====================>.........] - ETA: 6s
189595648/267313385 [====================>.........] - ETA: 6s
190185472/267313385 [====================>.........] - ETA: 6s
190775296/267313385 [====================>.........] - ETA: 6s
191365120/267313385 [====================>.........] - ETA: 6s
191954944/267313385 [====================>.........] - ETA: 6s
192544768/267313385 [====================>.........] - ETA: 6s
193134592/267313385 [====================>.........] - ETA: 6s
193724416/267313385 [====================>.........] - ETA: 6s
194314240/267313385 [====================>.........] - ETA: 6s
194904064/267313385 [====================>.........] - ETA: 6s
195493888/267313385 [====================>.........] - ETA: 6s
196083712/267313385 [=====================>........] - ETA: 6s
196673536/267313385 [=====================>........] - ETA: 6s
197263360/267313385 [=====================>........] - ETA: 6s
197853184/267313385 [=====================>........] - ETA: 6s
198443008/267313385 [=====================>........] - ETA: 6s
199032832/267313385 [=====================>........] - ETA: 6s
199573504/267313385 [=====================>........] - ETA: 6s
200097792/267313385 [=====================>........] - ETA: 5s
200638464/267313385 [=====================>........] - ETA: 5s
201162752/267313385 [=====================>........] - ETA: 5s
201687040/267313385 [=====================>........] - ETA: 5s
202244096/267313385 [=====================>........] - ETA: 5s
202833920/267313385 [=====================>........] - ETA: 5s
203423744/267313385 [=====================>........] - ETA: 5s
204013568/267313385 [=====================>........] - ETA: 5s
204603392/267313385 [=====================>........] - ETA: 5s
205193216/267313385 [======================>.......] - ETA: 5s
205783040/267313385 [======================>.......] - ETA: 5s
206372864/267313385 [======================>.......] - ETA: 5s
206962688/267313385 [======================>.......] - ETA: 5s
207552512/267313385 [======================>.......] - ETA: 5s
208142336/267313385 [======================>.......] - ETA: 5s
208732160/267313385 [======================>.......] - ETA: 5s
209321984/267313385 [======================>.......] - ETA: 5s
209911808/267313385 [======================>.......] - ETA: 5s
210501632/267313385 [======================>.......] - ETA: 5s
211091456/267313385 [======================>.......] - ETA: 5s
211681280/267313385 [======================>.......] - ETA: 4s
212271104/267313385 [======================>.......] - ETA: 4s
212860928/267313385 [======================>.......] - ETA: 4s
213450752/267313385 [======================>.......] - ETA: 4s
214040576/267313385 [=======================>......] - ETA: 4s
214630400/267313385 [=======================>......] - ETA: 4s
215220224/267313385 [=======================>......] - ETA: 4s
215810048/267313385 [=======================>......] - ETA: 4s
216399872/267313385 [=======================>......] - ETA: 4s
216989696/267313385 [=======================>......] - ETA: 4s
217579520/267313385 [=======================>......] - ETA: 4s
218169344/267313385 [=======================>......] - ETA: 4s
218759168/267313385 [=======================>......] - ETA: 4s
219348992/267313385 [=======================>......] - ETA: 4s
219938816/267313385 [=======================>......] - ETA: 4s
220528640/267313385 [=======================>......] - ETA: 4s
221118464/267313385 [=======================>......] - ETA: 4s
221708288/267313385 [=======================>......] - ETA: 4s
222298112/267313385 [=======================>......] - ETA: 4s
222887936/267313385 [========================>.....] - ETA: 3s
223477760/267313385 [========================>.....] - ETA: 3s
224067584/267313385 [========================>.....] - ETA: 3s
224673792/267313385 [========================>.....] - ETA: 3s
225263616/267313385 [========================>.....] - ETA: 3s
225853440/267313385 [========================>.....] - ETA: 3s
226443264/267313385 [========================>.....] - ETA: 3s
227033088/267313385 [========================>.....] - ETA: 3s
227622912/267313385 [========================>.....] - ETA: 3s
228212736/267313385 [========================>.....] - ETA: 3s
228802560/267313385 [========================>.....] - ETA: 3s
229392384/267313385 [========================>.....] - ETA: 3s
229982208/267313385 [========================>.....] - ETA: 3s
230572032/267313385 [========================>.....] - ETA: 3s
231161856/267313385 [========================>.....] - ETA: 3s
231768064/267313385 [=========================>....] - ETA: 3s
232357888/267313385 [=========================>....] - ETA: 3s
232947712/267313385 [=========================>....] - ETA: 3s
233537536/267313385 [=========================>....] - ETA: 2s
234127360/267313385 [=========================>....] - ETA: 2s
234684416/267313385 [=========================>....] - ETA: 2s
235208704/267313385 [=========================>....] - ETA: 2s
235454464/267313385 [=========================>....] - ETA: 2s
236388352/267313385 [=========================>....] - ETA: 2s
237748224/267313385 [=========================>....] - ETA: 2s
238714880/267313385 [=========================>....] - ETA: 2s
239304704/267313385 [=========================>....] - ETA: 2s
239894528/267313385 [=========================>....] - ETA: 2s
240467968/267313385 [=========================>....] - ETA: 2s
241057792/267313385 [==========================>...] - ETA: 2s
241647616/267313385 [==========================>...] - ETA: 2s
242237440/267313385 [==========================>...] - ETA: 2s
242827264/267313385 [==========================>...] - ETA: 2s
243417088/267313385 [==========================>...] - ETA: 2s
244006912/267313385 [==========================>...] - ETA: 2s
244596736/267313385 [==========================>...] - ETA: 2s
245137408/267313385 [==========================>...] - ETA: 1s
245727232/267313385 [==========================>...] - ETA: 1s
246317056/267313385 [==========================>...] - ETA: 1s
246906880/267313385 [==========================>...] - ETA: 1s
247496704/267313385 [==========================>...] - ETA: 1s
248086528/267313385 [==========================>...] - ETA: 1s
248676352/267313385 [==========================>...] - ETA: 1s
249233408/267313385 [==========================>...] - ETA: 1s
249823232/267313385 [===========================>..] - ETA: 1s
250413056/267313385 [===========================>..] - ETA: 1s
251002880/267313385 [===========================>..] - ETA: 1s
251592704/267313385 [===========================>..] - ETA: 1s
252182528/267313385 [===========================>..] - ETA: 1s
252772352/267313385 [===========================>..] - ETA: 1s
253362176/267313385 [===========================>..] - ETA: 1s
253952000/267313385 [===========================>..] - ETA: 1s
254541824/267313385 [===========================>..] - ETA: 1s
255131648/267313385 [===========================>..] - ETA: 1s
255705088/267313385 [===========================>..] - ETA: 1s
256278528/267313385 [===========================>..] - ETA: 0s
256868352/267313385 [===========================>..] - ETA: 0s
257458176/267313385 [===========================>..] - ETA: 0s
258048000/267313385 [===========================>..] - ETA: 0s
258637824/267313385 [============================>.] - ETA: 0s
259211264/267313385 [============================>.] - ETA: 0s
259801088/267313385 [============================>.] - ETA: 0s
260390912/267313385 [============================>.] - ETA: 0s
260980736/267313385 [============================>.] - ETA: 0s
261570560/267313385 [============================>.] - ETA: 0s
262160384/267313385 [============================>.] - ETA: 0s
262750208/267313385 [============================>.] - ETA: 0s
263340032/267313385 [============================>.] - ETA: 0s
263929856/267313385 [============================>.] - ETA: 0s
264519680/267313385 [============================>.] - ETA: 0s
265109504/267313385 [============================>.] - ETA: 0s
265699328/267313385 [============================>.] - ETA: 0s
266289152/267313385 [============================>.] - ETA: 0s
266878976/267313385 [============================>.] - ETA: 0s
267313385/267313385 [==============================] - 24s 0us/step

2. Load a pre-trained native Keras model

The model used in this example is AkidaUNet. It has an AkidaNet (0.5) backbone to extract features combined with a succession of separable transposed convolutional blocks to build an image segmentation map. A pre-trained floating point keras model is downloaded to save training time.

Note

  • The “transposed” convolutional feature is new in Akida 2.0.

  • The “separable transposed” operation is realized through the combination of a QuantizeML custom DepthwiseConv2DTranspose layer with a standard pointwise convolution.

The performance of the model is evaluated using both pixel accuracy and Binary IoU. The pixel accuracy describes how well the model can predict the segmentation mask pixel by pixel and the Binary IoU takes into account how close the predicted mask is to the ground truth.

from akida_models.model_io import load_model

# Retrieve the model file from Brainchip data server
model_file = fetch_file(fname="akida_unet_portrait128.h5",
                        origin="https://data.brainchip.com/models/AkidaV2/akida_unet/akida_unet_portrait128.h5",
                        cache_subdir='models')

# Load the native Keras pre-trained model
model_keras = load_model(model_file)
model_keras.summary()

Downloading data from https://data.brainchip.com/models/AkidaV2/akida_unet/akida_unet_portrait128.h5.

      0/4493952 [..............................] - ETA: 0s
 196608/4493952 [>.............................] - ETA: 1s
 770048/4493952 [====>.........................] - ETA: 0s
1359872/4493952 [========>.....................] - ETA: 0s
1933312/4493952 [===========>..................] - ETA: 0s
2531328/4493952 [===============>..............] - ETA: 0s
3129344/4493952 [===================>..........] - ETA: 0s
3710976/4493952 [=======================>......] - ETA: 0s
4259840/4493952 [===========================>..] - ETA: 0s
4493952/4493952 [==============================] - 0s 0us/step
Model: "akida_unet"
_________________________________________________________________
 Layer (type)                Output Shape              Param #
=================================================================
 input (InputLayer)          [(None, 128, 128, 3)]     0

 rescaling (Rescaling)       (None, 128, 128, 3)       0

 conv_0 (Conv2D)             (None, 64, 64, 16)        432

 conv_0/BN (BatchNormalizati  (None, 64, 64, 16)       64
 on)

 conv_0/relu (ReLU)          (None, 64, 64, 16)        0

 conv_1 (Conv2D)             (None, 64, 64, 32)        4608

 conv_1/BN (BatchNormalizati  (None, 64, 64, 32)       128
 on)

 conv_1/relu (ReLU)          (None, 64, 64, 32)        0

 conv_2 (Conv2D)             (None, 32, 32, 64)        18432

 conv_2/BN (BatchNormalizati  (None, 32, 32, 64)       256
 on)

 conv_2/relu (ReLU)          (None, 32, 32, 64)        0

 conv_3 (Conv2D)             (None, 32, 32, 64)        36864

 conv_3/BN (BatchNormalizati  (None, 32, 32, 64)       256
 on)

 conv_3/relu (ReLU)          (None, 32, 32, 64)        0

 dw_separable_4 (DepthwiseCo  (None, 16, 16, 64)       576
 nv2D)

 pw_separable_4 (Conv2D)     (None, 16, 16, 128)       8192

 pw_separable_4/BN (BatchNor  (None, 16, 16, 128)      512
 malization)

 pw_separable_4/relu (ReLU)  (None, 16, 16, 128)       0

 dw_separable_5 (DepthwiseCo  (None, 16, 16, 128)      1152
 nv2D)

 pw_separable_5 (Conv2D)     (None, 16, 16, 128)       16384

 pw_separable_5/BN (BatchNor  (None, 16, 16, 128)      512
 malization)

 pw_separable_5/relu (ReLU)  (None, 16, 16, 128)       0

 dw_separable_6 (DepthwiseCo  (None, 8, 8, 128)        1152
 nv2D)

 pw_separable_6 (Conv2D)     (None, 8, 8, 256)         32768

 pw_separable_6/BN (BatchNor  (None, 8, 8, 256)        1024
 malization)

 pw_separable_6/relu (ReLU)  (None, 8, 8, 256)         0

 dw_separable_7 (DepthwiseCo  (None, 8, 8, 256)        2304
 nv2D)

 pw_separable_7 (Conv2D)     (None, 8, 8, 256)         65536

 pw_separable_7/BN (BatchNor  (None, 8, 8, 256)        1024
 malization)

 pw_separable_7/relu (ReLU)  (None, 8, 8, 256)         0

 dw_separable_8 (DepthwiseCo  (None, 8, 8, 256)        2304
 nv2D)

 pw_separable_8 (Conv2D)     (None, 8, 8, 256)         65536

 pw_separable_8/BN (BatchNor  (None, 8, 8, 256)        1024
 malization)

 pw_separable_8/relu (ReLU)  (None, 8, 8, 256)         0

 dw_separable_9 (DepthwiseCo  (None, 8, 8, 256)        2304
 nv2D)

 pw_separable_9 (Conv2D)     (None, 8, 8, 256)         65536

 pw_separable_9/BN (BatchNor  (None, 8, 8, 256)        1024
 malization)

 pw_separable_9/relu (ReLU)  (None, 8, 8, 256)         0

 dw_separable_10 (DepthwiseC  (None, 8, 8, 256)        2304
 onv2D)

 pw_separable_10 (Conv2D)    (None, 8, 8, 256)         65536

 pw_separable_10/BN (BatchNo  (None, 8, 8, 256)        1024
 rmalization)

 pw_separable_10/relu (ReLU)  (None, 8, 8, 256)        0

 dw_separable_11 (DepthwiseC  (None, 8, 8, 256)        2304
 onv2D)

 pw_separable_11 (Conv2D)    (None, 8, 8, 256)         65536

 pw_separable_11/BN (BatchNo  (None, 8, 8, 256)        1024
 rmalization)

 pw_separable_11/relu (ReLU)  (None, 8, 8, 256)        0

 dw_separable_12 (DepthwiseC  (None, 4, 4, 256)        2304
 onv2D)

 pw_separable_12 (Conv2D)    (None, 4, 4, 512)         131072

 pw_separable_12/BN (BatchNo  (None, 4, 4, 512)        2048
 rmalization)

 pw_separable_12/relu (ReLU)  (None, 4, 4, 512)        0

 dw_separable_13 (DepthwiseC  (None, 4, 4, 512)        4608
 onv2D)

 pw_separable_13 (Conv2D)    (None, 4, 4, 512)         262144

 pw_separable_13/BN (BatchNo  (None, 4, 4, 512)        2048
 rmalization)

 pw_separable_13/relu (ReLU)  (None, 4, 4, 512)        0

 dw_sepconv_t_0 (DepthwiseCo  (None, 8, 8, 512)        5120
 nv2DTranspose)

 pw_sepconv_t_0 (Conv2D)     (None, 8, 8, 256)         131328

 pw_sepconv_t_0/BN (BatchNor  (None, 8, 8, 256)        1024
 malization)

 pw_sepconv_t_0/relu (ReLU)  (None, 8, 8, 256)         0

 dropout (Dropout)           (None, 8, 8, 256)         0

 dw_sepconv_t_1 (DepthwiseCo  (None, 16, 16, 256)      2560
 nv2DTranspose)

 pw_sepconv_t_1 (Conv2D)     (None, 16, 16, 128)       32896

 pw_sepconv_t_1/BN (BatchNor  (None, 16, 16, 128)      512
 malization)

 pw_sepconv_t_1/relu (ReLU)  (None, 16, 16, 128)       0

 dropout_1 (Dropout)         (None, 16, 16, 128)       0

 dw_sepconv_t_2 (DepthwiseCo  (None, 32, 32, 128)      1280
 nv2DTranspose)

 pw_sepconv_t_2 (Conv2D)     (None, 32, 32, 64)        8256

 pw_sepconv_t_2/BN (BatchNor  (None, 32, 32, 64)       256
 malization)

 pw_sepconv_t_2/relu (ReLU)  (None, 32, 32, 64)        0

 dropout_2 (Dropout)         (None, 32, 32, 64)        0

 dw_sepconv_t_3 (DepthwiseCo  (None, 64, 64, 64)       640
 nv2DTranspose)

 pw_sepconv_t_3 (Conv2D)     (None, 64, 64, 32)        2080

 pw_sepconv_t_3/BN (BatchNor  (None, 64, 64, 32)       128
 malization)

 pw_sepconv_t_3/relu (ReLU)  (None, 64, 64, 32)        0

 dropout_3 (Dropout)         (None, 64, 64, 32)        0

 dw_sepconv_t_4 (DepthwiseCo  (None, 128, 128, 32)     320
 nv2DTranspose)

 pw_sepconv_t_4 (Conv2D)     (None, 128, 128, 16)      528

 pw_sepconv_t_4/BN (BatchNor  (None, 128, 128, 16)     64
 malization)

 pw_sepconv_t_4/relu (ReLU)  (None, 128, 128, 16)      0

 dropout_4 (Dropout)         (None, 128, 128, 16)      0

 head (Conv2D)               (None, 128, 128, 1)       17

 sigmoid_act (Activation)    (None, 128, 128, 1)       0

=================================================================
Total params: 1,058,865
Trainable params: 1,051,889
Non-trainable params: 6,976
_________________________________________________________________

from keras.metrics import BinaryIoU

# Compile the native Keras model (required to evaluate the metrics)
model_keras.compile(loss='binary_crossentropy', metrics=[BinaryIoU(), 'accuracy'])

# Check Keras model performance
_, biou, acc = model_keras.evaluate(x_val, y_val, steps=steps, verbose=0)

print(f"Keras binary IoU / pixel accuracy: {biou:.4f} / {100*acc:.2f}%")

Keras binary IoU / pixel accuracy: 0.9455 / 97.28%

3. Load a pre-trained quantized Keras model

The next step is to quantize and potentially perform Quantize Aware Training (QAT) on the Keras model from the previous step. After the Keras model is quantized to 8-bits for all weights and activations, QAT is used to maintain the performance of the quantized model. Again, a pre-trained model is downloaded to save runtime.

from akida_models import akida_unet_portrait128_pretrained

# Load the pre-trained quantized model
model_quantized_keras = akida_unet_portrait128_pretrained()
model_quantized_keras.summary()

Downloading data from https://data.brainchip.com/models/AkidaV2/akida_unet/akida_unet_portrait128_i8_w8_a8.h5.

      0/4520576 [..............................] - ETA: 0s
  98304/4520576 [..............................] - ETA: 2s
 524288/4520576 [==>...........................] - ETA: 0s
1081344/4520576 [======>.......................] - ETA: 0s
1622016/4520576 [=========>....................] - ETA: 0s
2170880/4520576 [=============>................] - ETA: 0s
2727936/4520576 [=================>............] - ETA: 0s
3284992/4520576 [====================>.........] - ETA: 0s
3833856/4520576 [========================>.....] - ETA: 0s
4374528/4520576 [============================>.] - ETA: 0s
4520576/4520576 [==============================] - 0s 0us/step
Model: "akida_unet"
_________________________________________________________________
 Layer (type)                Output Shape              Param #
=================================================================
 input (InputLayer)          [(None, 128, 128, 3)]     0

 rescaling (QuantizedRescali  (None, 128, 128, 3)      0
 ng)

 conv_0 (QuantizedConv2D)    (None, 64, 64, 16)        448

 conv_0/relu (QuantizedReLU)  (None, 64, 64, 16)       32

 conv_1 (QuantizedConv2D)    (None, 64, 64, 32)        4640

 conv_1/relu (QuantizedReLU)  (None, 64, 64, 32)       64

 conv_2 (QuantizedConv2D)    (None, 32, 32, 64)        18496

 conv_2/relu (QuantizedReLU)  (None, 32, 32, 64)       128

 conv_3 (QuantizedConv2D)    (None, 32, 32, 64)        36928

 conv_3/relu (QuantizedReLU)  (None, 32, 32, 64)       128

 dw_separable_4 (QuantizedDe  (None, 16, 16, 64)       704
 pthwiseConv2D)

 pw_separable_4 (QuantizedCo  (None, 16, 16, 128)      8320
 nv2D)

 pw_separable_4/relu (Quanti  (None, 16, 16, 128)      256
 zedReLU)

 dw_separable_5 (QuantizedDe  (None, 16, 16, 128)      1408
 pthwiseConv2D)

 pw_separable_5 (QuantizedCo  (None, 16, 16, 128)      16512
 nv2D)

 pw_separable_5/relu (Quanti  (None, 16, 16, 128)      256
 zedReLU)

 dw_separable_6 (QuantizedDe  (None, 8, 8, 128)        1408
 pthwiseConv2D)

 pw_separable_6 (QuantizedCo  (None, 8, 8, 256)        33024
 nv2D)

 pw_separable_6/relu (Quanti  (None, 8, 8, 256)        512
 zedReLU)

 dw_separable_7 (QuantizedDe  (None, 8, 8, 256)        2816
 pthwiseConv2D)

 pw_separable_7 (QuantizedCo  (None, 8, 8, 256)        65792
 nv2D)

 pw_separable_7/relu (Quanti  (None, 8, 8, 256)        512
 zedReLU)

 dw_separable_8 (QuantizedDe  (None, 8, 8, 256)        2816
 pthwiseConv2D)

 pw_separable_8 (QuantizedCo  (None, 8, 8, 256)        65792
 nv2D)

 pw_separable_8/relu (Quanti  (None, 8, 8, 256)        512
 zedReLU)

 dw_separable_9 (QuantizedDe  (None, 8, 8, 256)        2816
 pthwiseConv2D)

 pw_separable_9 (QuantizedCo  (None, 8, 8, 256)        65792
 nv2D)

 pw_separable_9/relu (Quanti  (None, 8, 8, 256)        512
 zedReLU)

 dw_separable_10 (QuantizedD  (None, 8, 8, 256)        2816
 epthwiseConv2D)

 pw_separable_10 (QuantizedC  (None, 8, 8, 256)        65792
 onv2D)

 pw_separable_10/relu (Quant  (None, 8, 8, 256)        512
 izedReLU)

 dw_separable_11 (QuantizedD  (None, 8, 8, 256)        2816
 epthwiseConv2D)

 pw_separable_11 (QuantizedC  (None, 8, 8, 256)        65792
 onv2D)

 pw_separable_11/relu (Quant  (None, 8, 8, 256)        512
 izedReLU)

 dw_separable_12 (QuantizedD  (None, 4, 4, 256)        2816
 epthwiseConv2D)

 pw_separable_12 (QuantizedC  (None, 4, 4, 512)        131584
 onv2D)

 pw_separable_12/relu (Quant  (None, 4, 4, 512)        1024
 izedReLU)

 dw_separable_13 (QuantizedD  (None, 4, 4, 512)        5632
 epthwiseConv2D)

 pw_separable_13 (QuantizedC  (None, 4, 4, 512)        262656
 onv2D)

 pw_separable_13/relu (Quant  (None, 4, 4, 512)        1024
 izedReLU)

 dw_sepconv_t_0 (QuantizedDe  (None, 8, 8, 512)        6144
 pthwiseConv2DTranspose)

 pw_sepconv_t_0 (QuantizedCo  (None, 8, 8, 256)        131328
 nv2D)

 pw_sepconv_t_0/relu (Quanti  (None, 8, 8, 256)        512
 zedReLU)

 dropout (QuantizedDropout)  (None, 8, 8, 256)         0

 dw_sepconv_t_1 (QuantizedDe  (None, 16, 16, 256)      3072
 pthwiseConv2DTranspose)

 pw_sepconv_t_1 (QuantizedCo  (None, 16, 16, 128)      32896
 nv2D)

 pw_sepconv_t_1/relu (Quanti  (None, 16, 16, 128)      256
 zedReLU)

 dropout_1 (QuantizedDropout  (None, 16, 16, 128)      0
 )

 dw_sepconv_t_2 (QuantizedDe  (None, 32, 32, 128)      1536
 pthwiseConv2DTranspose)

 pw_sepconv_t_2 (QuantizedCo  (None, 32, 32, 64)       8256
 nv2D)

 pw_sepconv_t_2/relu (Quanti  (None, 32, 32, 64)       128
 zedReLU)

 dropout_2 (QuantizedDropout  (None, 32, 32, 64)       0
 )

 dw_sepconv_t_3 (QuantizedDe  (None, 64, 64, 64)       768
 pthwiseConv2DTranspose)

 pw_sepconv_t_3 (QuantizedCo  (None, 64, 64, 32)       2080
 nv2D)

 pw_sepconv_t_3/relu (Quanti  (None, 64, 64, 32)       64
 zedReLU)

 dropout_3 (QuantizedDropout  (None, 64, 64, 32)       0
 )

 dw_sepconv_t_4 (QuantizedDe  (None, 128, 128, 32)     384
 pthwiseConv2DTranspose)

 pw_sepconv_t_4 (QuantizedCo  (None, 128, 128, 16)     528
 nv2D)

 pw_sepconv_t_4/relu (Quanti  (None, 128, 128, 16)     32
 zedReLU)

 dropout_4 (QuantizedDropout  (None, 128, 128, 16)     0
 )

 head (QuantizedConv2D)      (None, 128, 128, 1)       17

 dequantizer (Dequantizer)   (None, 128, 128, 1)       0

 sigmoid_act (Activation)    (None, 128, 128, 1)       0

=================================================================
Total params: 1,061,601
Trainable params: 1,047,905
Non-trainable params: 13,696
_________________________________________________________________

# Compile the quantized Keras model (required to evaluate the metrics)
model_quantized_keras.compile(loss='binary_crossentropy', metrics=[BinaryIoU(), 'accuracy'])

# Check Keras model performance
_, biou, acc = model_quantized_keras.evaluate(x_val, y_val, steps=steps, verbose=0)

print(f"Keras quantized binary IoU / pixel accuracy: {biou:.4f} / {100*acc:.2f}%")

Keras quantized binary IoU / pixel accuracy: 0.9399 / 97.01%

4. Conversion to Akida

Finally, the quantized Keras model from the previous step is converted into an Akida model and its performance is evaluated. Note that the original performance of the keras floating point model is maintained throughout the conversion process in this example.

from cnn2snn import convert

# Convert the model
model_akida = convert(model_quantized_keras)
model_akida.summary()

                  Model Summary
_________________________________________________
Input shape    Output shape   Sequences  Layers
=================================================
[128, 128, 3]  [128, 128, 1]  1          36
_________________________________________________

_____________________________________________________________________________
Layer (type)                               Output shape    Kernel shape

====================== SW/conv_0-dequantizer (Software) =====================

conv_0 (InputConv2D)                       [64, 64, 16]    (3, 3, 3, 16)
_____________________________________________________________________________
conv_1 (Conv2D)                            [64, 64, 32]    (3, 3, 16, 32)
_____________________________________________________________________________
conv_2 (Conv2D)                            [32, 32, 64]    (3, 3, 32, 64)
_____________________________________________________________________________
conv_3 (Conv2D)                            [32, 32, 64]    (3, 3, 64, 64)
_____________________________________________________________________________
dw_separable_4 (DepthwiseConv2D)           [16, 16, 64]    (3, 3, 64, 1)
_____________________________________________________________________________
pw_separable_4 (Conv2D)                    [16, 16, 128]   (1, 1, 64, 128)
_____________________________________________________________________________
dw_separable_5 (DepthwiseConv2D)           [16, 16, 128]   (3, 3, 128, 1)
_____________________________________________________________________________
pw_separable_5 (Conv2D)                    [16, 16, 128]   (1, 1, 128, 128)
_____________________________________________________________________________
dw_separable_6 (DepthwiseConv2D)           [8, 8, 128]     (3, 3, 128, 1)
_____________________________________________________________________________
pw_separable_6 (Conv2D)                    [8, 8, 256]     (1, 1, 128, 256)
_____________________________________________________________________________
dw_separable_7 (DepthwiseConv2D)           [8, 8, 256]     (3, 3, 256, 1)
_____________________________________________________________________________
pw_separable_7 (Conv2D)                    [8, 8, 256]     (1, 1, 256, 256)
_____________________________________________________________________________
dw_separable_8 (DepthwiseConv2D)           [8, 8, 256]     (3, 3, 256, 1)
_____________________________________________________________________________
pw_separable_8 (Conv2D)                    [8, 8, 256]     (1, 1, 256, 256)
_____________________________________________________________________________
dw_separable_9 (DepthwiseConv2D)           [8, 8, 256]     (3, 3, 256, 1)
_____________________________________________________________________________
pw_separable_9 (Conv2D)                    [8, 8, 256]     (1, 1, 256, 256)
_____________________________________________________________________________
dw_separable_10 (DepthwiseConv2D)          [8, 8, 256]     (3, 3, 256, 1)
_____________________________________________________________________________
pw_separable_10 (Conv2D)                   [8, 8, 256]     (1, 1, 256, 256)
_____________________________________________________________________________
dw_separable_11 (DepthwiseConv2D)          [8, 8, 256]     (3, 3, 256, 1)
_____________________________________________________________________________
pw_separable_11 (Conv2D)                   [8, 8, 256]     (1, 1, 256, 256)
_____________________________________________________________________________
dw_separable_12 (DepthwiseConv2D)          [4, 4, 256]     (3, 3, 256, 1)
_____________________________________________________________________________
pw_separable_12 (Conv2D)                   [4, 4, 512]     (1, 1, 256, 512)
_____________________________________________________________________________
dw_separable_13 (DepthwiseConv2D)          [4, 4, 512]     (3, 3, 512, 1)
_____________________________________________________________________________
pw_separable_13 (Conv2D)                   [4, 4, 512]     (1, 1, 512, 512)
_____________________________________________________________________________
dw_sepconv_t_0 (DepthwiseConv2DTranspose)  [8, 8, 512]     (3, 3, 512, 1)
_____________________________________________________________________________
pw_sepconv_t_0 (Conv2D)                    [8, 8, 256]     (1, 1, 512, 256)
_____________________________________________________________________________
dw_sepconv_t_1 (DepthwiseConv2DTranspose)  [16, 16, 256]   (3, 3, 256, 1)
_____________________________________________________________________________
pw_sepconv_t_1 (Conv2D)                    [16, 16, 128]   (1, 1, 256, 128)
_____________________________________________________________________________
dw_sepconv_t_2 (DepthwiseConv2DTranspose)  [32, 32, 128]   (3, 3, 128, 1)
_____________________________________________________________________________
pw_sepconv_t_2 (Conv2D)                    [32, 32, 64]    (1, 1, 128, 64)
_____________________________________________________________________________
dw_sepconv_t_3 (DepthwiseConv2DTranspose)  [64, 64, 64]    (3, 3, 64, 1)
_____________________________________________________________________________
pw_sepconv_t_3 (Conv2D)                    [64, 64, 32]    (1, 1, 64, 32)
_____________________________________________________________________________
dw_sepconv_t_4 (DepthwiseConv2DTranspose)  [128, 128, 32]  (3, 3, 32, 1)
_____________________________________________________________________________
pw_sepconv_t_4 (Conv2D)                    [128, 128, 16]  (1, 1, 32, 16)
_____________________________________________________________________________
head (Conv2D)                              [128, 128, 1]   (1, 1, 16, 1)
_____________________________________________________________________________
dequantizer (Dequantizer)                  [128, 128, 1]   N/A
_____________________________________________________________________________

import tensorflow as tf

# Check Akida model performance
labels, pots = None, None

for s in range(steps):
    batch = x_val[s * batch_size: (s + 1) * batch_size, :]
    label_batch = y_val[s * batch_size: (s + 1) * batch_size, :]
    pots_batch = model_akida.predict(batch.astype('uint8'))

    if labels is None:
        labels = label_batch
        pots = pots_batch
    else:
        labels = np.concatenate((labels, label_batch))
        pots = np.concatenate((pots, pots_batch))
preds = tf.keras.activations.sigmoid(pots)

m_binary_iou = tf.keras.metrics.BinaryIoU(target_class_ids=[0, 1], threshold=0.5)
m_binary_iou.update_state(labels, preds)
binary_iou = m_binary_iou.result().numpy()

m_accuracy = tf.keras.metrics.Accuracy()
m_accuracy.update_state(labels, preds > 0.5)
accuracy = m_accuracy.result().numpy()
print(f"Akida binary IoU / pixel accuracy: {binary_iou:.4f} / {100*accuracy:.2f}%")

# For non-regression purpose
assert binary_iou > 0.9

Akida binary IoU / pixel accuracy: 0.9388 / 97.01%

5. Segment a single image

For visualization of the person segmentation performed by the Akida model, display a single image along with the segmentation produced by the original floating point model and the ground truth segmentation.

import matplotlib.pyplot as plt

# Estimate age on a random single image and display Keras and Akida outputs
sample = np.expand_dims(x_val[id, :], 0)
keras_out = model_keras(sample)
akida_out = tf.keras.activations.sigmoid(model_akida.forward(sample.astype('uint8')))

fig, axs = plt.subplots(1, 3, constrained_layout=True)
axs[0].imshow(keras_out[0] * sample[0] / 255.)
axs[0].set_title('Keras segmentation', fontsize=10)
axs[0].axis('off')

axs[1].imshow(akida_out[0] * sample[0] / 255.)
axs[1].set_title('Akida segmentation', fontsize=10)
axs[1].axis('off')

axs[2].imshow(y_val[id] * sample[0] / 255.)
axs[2].set_title('Expected segmentation', fontsize=10)
axs[2].axis('off')

plt.show()
Keras segmentation, Akida segmentation, Expected segmentation

Total running time of the script: (1 minutes 42.545 seconds)

Gallery generated by Sphinx-Gallery