Link Copied
Personnally i never retrained model throught openVino.
I used only tensorflow object detection API.
In order to do this, i :
- Created a VOC Like Dataset with a VOC Tool. It generates PNG, with one color per class and one color per object + original file.
- Edited dataset_tool from TF object detection API in order to load my masks.
- Edited the config file corresponding to my network (samples\configs directory)
- Put it in a "training dir"
- Executed the command in order to start training (on a powerful computer)
python model_main.py --alsologtostderr --model_dir=training_inception_mask2019/ --pipeline_config_path=training_inception_mask2019/z_mask_rcnn_inception_v2_coco.config
- Generate inference graph
python export_inference_graph.py --input_type image_tensor --pipeline_config_path training_inception_mask/z_mask_rcnn_inception_v2_coco.config --trained_checkpoint_prefix training_inception_mask/model.ckpt-10835 --output_directory 2018_12_22_inception_mask/
- Used model optimiser on .pb generated file
- Used OpenCV Gengraph script...
- Did inference with Tensorflow / OpenCV and tried OpenVino (with bad results)
For source code :
I used this code in order to make OpenVino TF compatible :
def image_to_tensor(image,channels,h,w,info="",KeepRatio=False):
image_tensor=np.zeros(shape=(1,channels,h,w),dtype=np.uint8)
if image.shape[:-1]!=(h,w):
log.warning("Image {} is resized from {} to {}".format(info, image.shape[:-1],(h,w)))
if (KeepRatio):
h0,w0=image.shape[0],image.shape[1]
print((h0,w0))
ratio=float(max(h,w))/float(max(h0,w0))
h1=int(ratio*h0)
w1=int(ratio*w0)
image=cv2.resize(image,(w1,h1))
#Normalise between [0-1]
image=image.transpose((2,0,1))
image_tensor[0][:,0:h1,0:w1]=image
else:
image=cv2.resize(image,(w,h))
image = image.transpose((2, 0, 1))
image_tensor[0]=image
return image_tensor
def getMask_From_BBoxMask(Bbox,OriginalMask,original_image):
#Cette méthode à pour but de recréer un masque [0-1] de la taille de l'image
[Height,Width]=original_image.shape[0],original_image.shape[1]
Result=np.zeros((Height,Width),dtype=np.uint8)
y0, x0, y1, x1 = Bbox
ymin=min(y1,y0)
ymax=max(y1,y0)
xmin=min(x1,x0)
xmax=max(x1,x0)
xmin=int(min(max(xmin*Width,0),Width))
xmax=int(max(min(xmax*Width,Width),0))
ymin=int(min(max(ymin*Height,0),Height))
ymax=int(max(min(ymax*Height,Height),0))
BboxW=int(abs(xmax-xmin))
BboxH=int(abs(ymax-ymin))
if(BboxW>0 and BboxH>0):
MaxMask=(np.amax(OriginalMask,axis=0)*255).astype(np.uint8)
ResizedMask = cv2.resize(MaxMask, dsize=(BboxW, BboxH), interpolation=cv2.INTER_CUBIC)
Result[ymin:ymin+BboxH,xmin:xmin+BboxW]=(ResizedMask>128)*1
return Result
def get_OutputDict_FromVino(result,original_image,image_tensor,KeepRatio=False):
output_dict={}
Detection=result['detection_output'][0][0] # (?,?,[batch], label, prob, x1, y1, x2, y2)
Labels=Detection[:,1]
Scores=Detection[:,2]
coef=1
h0,w0=original_image.shape[0],original_image.shape[1]
if(KeepRatio):
h,w=image_tensor.shape[2],image_tensor.shape[3]
ratio=float(max(h,w))/float(max(h0,w0))
coef=float(max(h,w))/(ratio*float(min(h0,w0)))
print(coef)
if h0<w0:
Bboxs=np.array([Detection[:,4]*coef,Detection[:,3],Detection[:,6]*coef,Detection[:,5]]).transpose()
else:
Bboxs=np.array([Detection[:,4],Detection[:,3]*coef,Detection[:,6],Detection[:,5]*coef]).transpose()
output_dict['detection_boxes']=Bboxs
output_dict['detection_classes']=Labels.astype(np.uint8)
print(Labels[:5])
print(Scores[:5])
output_dict['detection_scores']=Scores
# Masks est l'image de taille 15x15 de l'intérieur Bbox
Masks=[]
for i in range(len(result['masks'])):
Masks.append(getMask_From_BBoxMask(Bboxs,result['masks'],original_image))
output_dict['detection_masks']=np.array(Masks)
print(output_dict['detection_masks'].shape)
return output_dict
Please, let me now if you face the same issue than me !
Because i didn't solve it yet and i tried to go on C++ code in order to solve the problem (without success yet).
