schihei/simple-keras
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Coding style changes

Browse Source
This commit is contained in:
Heiko J Schick
2020-10-20 23:01:28 +02:00
parent f0d1b50727
commit 65c7cd2178
1 changed files with 324 additions and 308 deletions
Download Patch File Download Diff File Expand all files Collapse all files
yolov3.py
+64 -48
View File
@@ -3,41 +3,33 @@ YOLO v3 object detection with Keras
Source: https://towardsdatascience.com/yolo-v3-object-detection-with-keras-461d2cfccef6 Source: https://towardsdatascience.com/yolo-v3-object-detection-with-keras-461d2cfccef6
""" """
# import os
# import scipy.io
# import scipy.misc
import numpy as np
# import pandas as pd
# import PIL
import struct import struct
# import cv2 import glob
import numpy as np
from numpy import expand_dims from numpy import expand_dims
# import tensorflow as tf from keras.layers import Input, Conv2D, BatchNormalization, LeakyReLU, ZeroPadding2D, UpSampling2D
# from skimage.transform import resize from keras.models import Model
from keras import backend as K
from keras.layers import Input, Lambda, Conv2D, BatchNormalization, LeakyReLU, ZeroPadding2D, UpSampling2D
from keras.models import load_model, Model
from keras.layers.merge import add, concatenate from keras.layers.merge import add, concatenate
from keras.preprocessing.image import load_img from keras.preprocessing.image import load_img
from keras.preprocessing.image import img_to_array from keras.preprocessing.image import img_to_array
from matplotlib import pyplot from matplotlib import pyplot
import matplotlib.pyplot as plt
from matplotlib.pyplot import imshow
from matplotlib.patches import Rectangle from matplotlib.patches import Rectangle
# %matplotlib inline
"""**Step 1:** `WeightReader` class is used to parse the "yolov3.weights" file and load the model weights into memory in a format that we can set into keras model"""
# Step 1:
# WeightReader class is used to parse the "yolov3.weights" file and load the model weights into
# memory in a format that we can set into keras model
class WeightReader: class WeightReader:
def __init__(self, weight_file): def __init__(self, weight_file):
with open(weight_file, 'rb') as w_f: with open(weight_file, 'rb') as w_f:
major, = struct.unpack('i', w_f.read(4)) major, = struct.unpack('i', w_f.read(4))
minor, = struct.unpack('i', w_f.read(4)) minor, = struct.unpack('i', w_f.read(4))
revision, = struct.unpack('i', w_f.read(4)) revision, = struct.unpack('i', w_f.read(4))
if (major*10 + minor) >= 2 and major < 1000 and minor < 1000: if (major*10 + minor) >= 2 and major < 1000 and minor < 1000:
w_f.read(8) w_f.read(8)
else: else:
w_f.read(4) w_f.read(4)
transpose = (major > 1000) or (minor > 1000) transpose = (major > 1000) or (minor > 1000)
binary = w_f.read() binary = w_f.read()
self.offset = 0 self.offset = 0
@@ -52,6 +44,7 @@ class WeightReader:
try: try:
conv_layer = model.get_layer('conv_' + str(i)) conv_layer = model.get_layer('conv_' + str(i))
print("loading weights of convolution #" + str(i)) print("loading weights of convolution #" + str(i))
if i not in [81, 93, 105]: if i not in [81, 93, 105]:
norm_layer = model.get_layer('bnorm_' + str(i)) norm_layer = model.get_layer('bnorm_' + str(i))
size = np.prod(norm_layer.get_weights()[0].shape) size = np.prod(norm_layer.get_weights()[0].shape)
@@ -60,6 +53,7 @@ class WeightReader:
mean = self.read_bytes(size) # mean mean = self.read_bytes(size) # mean
var = self.read_bytes(size) # variance var = self.read_bytes(size) # variance
weights = norm_layer.set_weights([gamma, beta, mean, var]) weights = norm_layer.set_weights([gamma, beta, mean, var])
if len(conv_layer.get_weights()) > 1: if len(conv_layer.get_weights()) > 1:
bias = self.read_bytes(np.prod(conv_layer.get_weights()[1].shape)) bias = self.read_bytes(np.prod(conv_layer.get_weights()[1].shape))
kernel = self.read_bytes(np.prod(conv_layer.get_weights()[0].shape)) kernel = self.read_bytes(np.prod(conv_layer.get_weights()[0].shape))
@@ -71,110 +65,135 @@ class WeightReader:
kernel = kernel.reshape(list(reversed(conv_layer.get_weights()[0].shape))) kernel = kernel.reshape(list(reversed(conv_layer.get_weights()[0].shape)))
kernel = kernel.transpose([2,3,1,0]) kernel = kernel.transpose([2,3,1,0])
conv_layer.set_weights([kernel]) conv_layer.set_weights([kernel])
except ValueError: except ValueError:
print("no convolution #" + str(i)) print("no convolution #" + str(i))
def reset(self): def reset(self):
self.offset = 0 self.offset = 0
"""**Step 2:** # Step 2:
- `_conv_block(input, convs, skip=True)` is a function to create convolutional layer # _cb(input, convs, skip=True) is a function to create convolutional layer
- `make_yolov3_model()` is a function to create layers of convoluational and stack together as a whole yolo model def _cb(inp, convs, skip=True):
"""
def _conv_block(inp, convs, skip=True):
x = inp x = inp
count = 0 count = 0
for conv in convs: for conv in convs:
if count == (len(convs) - 2) and skip: if count == (len(convs) - 2) and skip:
skip_connection = x skip_connection = x
count += 1 count += 1
if conv['stride'] > 1: x = ZeroPadding2D(((1,0),(1,0)))(x) # peculiar padding as darknet prefer left and top if conv['stride'] > 1: x = ZeroPadding2D(((1,0),(1,0)))(x) # peculiar padding as darknet
# prefer left and top
x = Conv2D(conv['filter'], x = Conv2D(conv['filter'],
conv['kernel'], conv['kernel'],
strides=conv['stride'], strides=conv['stride'],
padding='valid' if conv['stride'] > 1 else 'same', # peculiar padding as darknet prefer left and top padding='valid' if conv['stride'] > 1 else 'same', # peculiar padding as darknet
# prefer left and top
name='conv_' + str(conv['layer_idx']), name='conv_' + str(conv['layer_idx']),
use_bias=False if conv['bnorm'] else True)(x) use_bias=False if conv['bnorm'] else True)(x)
if conv['bnorm']: x = BatchNormalization(epsilon=0.001, name='bnorm_' + str(conv['layer_idx']))(x)
if conv['leaky']: x = LeakyReLU(alpha=0.1, name='leaky_' + str(conv['layer_idx']))(x) if conv['bnorm']: x = BatchNormalization(epsilon=0.001, name='bnorm_'
+ str(conv['layer_idx']))(x)
if conv['leaky']: x = LeakyReLU(alpha=0.1, name='leaky_'
+ str(conv['layer_idx']))(x)
return add([skip_connection, x]) if skip else x return add([skip_connection, x]) if skip else x
# make_yolov3_model() is a function to create layers of convoluational and stack together as a
# whole yolo model
def make_yolov3_model(): def make_yolov3_model():
input_image = Input(shape=(None, None, 3)) input_image = Input(shape=(None, None, 3))
# Layer 0 => 4 # Layer 0 => 4
x = _conv_block(input_image, [{'filter': 32, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 0}, x = _cb(input_image, [{'filter': 32, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 0},
{'filter': 64, 'kernel': 3, 'stride': 2, 'bnorm': True, 'leaky': True, 'layer_idx': 1}, {'filter': 64, 'kernel': 3, 'stride': 2, 'bnorm': True, 'leaky': True, 'layer_idx': 1},
{'filter': 32, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 2}, {'filter': 32, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 2},
{'filter': 64, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 3}]) {'filter': 64, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 3}])
# Layer 5 => 8 # Layer 5 => 8
x = _conv_block(x, [{'filter': 128, 'kernel': 3, 'stride': 2, 'bnorm': True, 'leaky': True, 'layer_idx': 5}, x = _cb(x, [{'filter': 128, 'kernel': 3, 'stride': 2, 'bnorm': True, 'leaky': True, 'layer_idx': 5},
{'filter': 64, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 6}, {'filter': 64, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 6},
{'filter': 128, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 7}]) {'filter': 128, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 7}])
# Layer 9 => 11 # Layer 9 => 11
x = _conv_block(x, [{'filter': 64, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 9}, x = _cb(x, [{'filter': 64, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 9},
{'filter': 128, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 10}]) {'filter': 128, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 10}])
# Layer 12 => 15 # Layer 12 => 15
x = _conv_block(x, [{'filter': 256, 'kernel': 3, 'stride': 2, 'bnorm': True, 'leaky': True, 'layer_idx': 12}, x = _cb(x, [{'filter': 256, 'kernel': 3, 'stride': 2, 'bnorm': True, 'leaky': True, 'layer_idx': 12},
{'filter': 128, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 13}, {'filter': 128, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 13},
{'filter': 256, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 14}]) {'filter': 256, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 14}])
# Layer 16 => 36 # Layer 16 => 36
for i in range(7): for i in range(7):
x = _conv_block(x, [{'filter': 128, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 16+i*3}, x = _cb(x, [{'filter': 128, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 16+i*3},
{'filter': 256, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 17+i*3}]) {'filter': 256, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 17+i*3}])
skip_36 = x skip_36 = x
# Layer 37 => 40 # Layer 37 => 40
x = _conv_block(x, [{'filter': 512, 'kernel': 3, 'stride': 2, 'bnorm': True, 'leaky': True, 'layer_idx': 37}, x = _cb(x, [{'filter': 512, 'kernel': 3, 'stride': 2, 'bnorm': True, 'leaky': True, 'layer_idx': 37},
{'filter': 256, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 38}, {'filter': 256, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 38},
{'filter': 512, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 39}]) {'filter': 512, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 39}])
# Layer 41 => 61 # Layer 41 => 61
for i in range(7): for i in range(7):
x = _conv_block(x, [{'filter': 256, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 41+i*3}, x = _cb(x, [{'filter': 256, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 41+i*3},
{'filter': 512, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 42+i*3}]) {'filter': 512, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 42+i*3}])
skip_61 = x skip_61 = x
# Layer 62 => 65 # Layer 62 => 65
x = _conv_block(x, [{'filter': 1024, 'kernel': 3, 'stride': 2, 'bnorm': True, 'leaky': True, 'layer_idx': 62}, x = _cb(x, [{'filter': 1024, 'kernel': 3, 'stride': 2, 'bnorm': True, 'leaky': True, 'layer_idx': 62},
{'filter': 512, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 63}, {'filter': 512, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 63},
{'filter': 1024, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 64}]) {'filter': 1024, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 64}])
# Layer 66 => 74 # Layer 66 => 74
for i in range(3): for i in range(3):
x = _conv_block(x, [{'filter': 512, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 66+i*3}, x = _cb(x, [{'filter': 512, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 66+i*3},
{'filter': 1024, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 67+i*3}]) {'filter': 1024, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 67+i*3}])
# Layer 75 => 79 # Layer 75 => 79
x = _conv_block(x, [{'filter': 512, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 75}, x = _cb(x, [{'filter': 512, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 75},
{'filter': 1024, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 76}, {'filter': 1024, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 76},
{'filter': 512, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 77}, {'filter': 512, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 77},
{'filter': 1024, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 78}, {'filter': 1024, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 78},
{'filter': 512, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 79}], skip=False) {'filter': 512, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 79}],
skip=False)
# Layer 80 => 82 # Layer 80 => 82
yolo_82 = _conv_block(x, [{'filter': 1024, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 80}, yolo_82 = _cb(x, [{'filter': 1024, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 80},
{'filter': 255, 'kernel': 1, 'stride': 1, 'bnorm': False, 'leaky': False, 'layer_idx': 81}], skip=False) {'filter': 255, 'kernel': 1, 'stride': 1, 'bnorm': False, 'leaky': False, 'layer_idx': 81}],
skip=False)
# Layer 83 => 86 # Layer 83 => 86
x = _conv_block(x, [{'filter': 256, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 84}], skip=False) x = _cb(x, [{'filter': 256, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 84}],
skip=False)
x = UpSampling2D(2)(x) x = UpSampling2D(2)(x)
x = concatenate([x, skip_61]) x = concatenate([x, skip_61])
# Layer 87 => 91 # Layer 87 => 91
x = _conv_block(x, [{'filter': 256, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 87}, x = _cb(x, [{'filter': 256, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 87},
{'filter': 512, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 88}, {'filter': 512, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 88},
{'filter': 256, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 89}, {'filter': 256, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 89},
{'filter': 512, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 90}, {'filter': 512, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 90},
{'filter': 256, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 91}], skip=False) {'filter': 256, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 91}], skip=False)
# Layer 92 => 94 # Layer 92 => 94
yolo_94 = _conv_block(x, [{'filter': 512, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 92}, yolo_94 = _cb(x, [{'filter': 512, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 92},
{'filter': 255, 'kernel': 1, 'stride': 1, 'bnorm': False, 'leaky': False, 'layer_idx': 93}], skip=False) {'filter': 255, 'kernel': 1, 'stride': 1, 'bnorm': False, 'leaky': False, 'layer_idx': 93}], skip=False)
# Layer 95 => 98 # Layer 95 => 98
x = _conv_block(x, [{'filter': 128, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 96}], skip=False) x = _cb(x, [{'filter': 128, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 96}], skip=False)
x = UpSampling2D(2)(x) x = UpSampling2D(2)(x)
x = concatenate([x, skip_36]) x = concatenate([x, skip_36])
# Layer 99 => 106 # Layer 99 => 106
yolo_106 = _conv_block(x, [{'filter': 128, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 99}, yolo_106 = _cb(x, [{'filter': 128, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 99},
{'filter': 256, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 100}, {'filter': 256, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 100},
{'filter': 128, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 101}, {'filter': 128, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 101},
{'filter': 256, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 102}, {'filter': 256, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 102},
{'filter': 128, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 103}, {'filter': 128, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 103},
{'filter': 256, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 104}, {'filter': 256, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 104},
{'filter': 255, 'kernel': 1, 'stride': 1, 'bnorm': False, 'leaky': False, 'layer_idx': 105}], skip=False) {'filter': 255, 'kernel': 1, 'stride': 1, 'bnorm': False, 'leaky': False, 'layer_idx': 105}], skip=False)
model = Model(input_image, [yolo_82, yolo_94, yolo_106]) model = Model(input_image, [yolo_82, yolo_94, yolo_106])
return model return model
"""**Step 3:** """**Step 3:**
@@ -394,8 +413,6 @@ labels = ["person", "bicycle", "car", "motorbike", "aeroplane", "bus", "train",
# from google.colab import files # from google.colab import files
# upload = files.upload() # upload = files.upload()
import glob
for photo_filename in glob.glob("images/test/dog/*"): for photo_filename in glob.glob("images/test/dog/*"):
# for fn in upload.keys(): # for fn in upload.keys():
@@ -434,4 +451,3 @@ for photo_filename in glob.glob("images/test/dog/*"):
draw_boxes(photo_filename, v_boxes, v_labels, v_scores) draw_boxes(photo_filename, v_boxes, v_labels, v_scores)
print([a.shape for a in yhat]) print([a.shape for a in yhat])