webcam updates
This commit is contained in:
Glenn Jocher
parent
585f2e2cc1
commit
e23b1a3d73
13
detect.py
13
detect.py
|
|
@ -50,13 +50,16 @@ def detect(
|
|||
|
||||
for i, (path, img, im0) in enumerate(dataloader):
|
||||
t = time.time()
|
||||
print("%g/%g '%s': " % (i + 1, len(dataloader), path if not webcam else 'webcam'), end='')
|
||||
if webcam:
|
||||
print('webcam frame %g: ' % (i + 1), end='')
|
||||
else:
|
||||
print('image %g/%g %s: ' % (i + 1, len(dataloader), path), end='')
|
||||
save_path = os.path.join(output, path.split('/')[-1])
|
||||
|
||||
# Get detections
|
||||
img = torch.from_numpy(img).unsqueeze(0).to(device)
|
||||
if ONNX_EXPORT:
|
||||
torch.onnx._export(model, img, 'weights/model.onnx', verbose=True)
|
||||
torch.onnx.export(model, img, 'weights/model.onnx', verbose=True)
|
||||
return # ONNX export
|
||||
pred = model(img)
|
||||
pred = pred[pred[:, :, 4] > conf_thres] # remove boxes < threshold
|
||||
|
|
@ -70,9 +73,9 @@ def detect(
|
|||
|
||||
# Print results to screen
|
||||
unique_classes = detections[:, -1].cpu().unique()
|
||||
for i in unique_classes:
|
||||
n = (detections[:, -1].cpu() == i).sum()
|
||||
print('%g %ss' % (n, classes[int(i)]), end=', ')
|
||||
for c in unique_classes:
|
||||
n = (detections[:, -1].cpu() == c).sum()
|
||||
print('%g %ss' % (n, classes[int(c)]), end=', ')
|
||||
|
||||
# Draw bounding boxes and labels of detections
|
||||
for x1, y1, x2, y2, conf, cls_conf, cls in detections:
|
||||
|
|
|
|||
20
models.py
20
models.py
|
|
@ -82,6 +82,9 @@ class EmptyLayer(nn.Module):
|
|||
def __init__(self):
|
||||
super(EmptyLayer, self).__init__()
|
||||
|
||||
def forward(self, x):
|
||||
return x
|
||||
|
||||
|
||||
class Upsample(nn.Module):
|
||||
# Custom Upsample layer (nn.Upsample gives deprecated warning message)
|
||||
|
|
@ -121,8 +124,8 @@ class YOLOLayer(nn.Module):
|
|||
|
||||
# Build anchor grids
|
||||
nG = int(self.img_dim / stride) # number grid points
|
||||
self.grid_x = torch.arange(nG).repeat(nG, 1).view([1, 1, nG, nG]).float()
|
||||
self.grid_y = torch.arange(nG).repeat(nG, 1).t().view([1, 1, nG, nG]).float()
|
||||
self.grid_x = torch.arange(nG).repeat((nG, 1)).view((1, 1, nG, nG)).float()
|
||||
self.grid_y = torch.arange(nG).repeat((nG, 1)).t().view((1, 1, nG, nG)).float()
|
||||
self.anchor_wh = torch.FloatTensor([(a_w / stride, a_h / stride) for a_w, a_h in anchors]) # scale anchors
|
||||
self.anchor_w = self.anchor_wh[:, 0].view((1, nA, 1, 1))
|
||||
self.anchor_h = self.anchor_wh[:, 1].view((1, nA, 1, 1))
|
||||
|
|
@ -169,8 +172,8 @@ class YOLOLayer(nn.Module):
|
|||
# Width and height (yolo method)
|
||||
w = p[..., 2] # Width
|
||||
h = p[..., 3] # Height
|
||||
width = torch.exp(w.data) * self.anchor_w
|
||||
height = torch.exp(h.data) * self.anchor_h
|
||||
# width = torch.exp(w.data) * self.anchor_w
|
||||
# height = torch.exp(h.data) * self.anchor_h
|
||||
|
||||
# Width and height (power method)
|
||||
# w = torch.sigmoid(p[..., 2]) # Width
|
||||
|
|
@ -217,8 +220,8 @@ class YOLOLayer(nn.Module):
|
|||
|
||||
# Broadcasting only supported on first dimension in CoreML. See onnx-coreml/_operators.py
|
||||
# p_cls = F.softmax(p_cls, 2) * p_conf # SSD-like conf
|
||||
p_cls = torch.exp(p_cls).permute(2, 1, 0)
|
||||
p_cls = p_cls / p_cls.sum(0).unsqueeze(0) * p_conf.permute(2, 1, 0) # F.softmax() equivalent
|
||||
p_cls = torch.exp(p_cls).permute((2, 1, 0))
|
||||
p_cls = p_cls / p_cls.sum(0).unsqueeze(0) * p_conf.permute((2, 1, 0)) # F.softmax() equivalent
|
||||
p_cls = p_cls.permute(2, 1, 0)
|
||||
|
||||
return torch.cat((xy / nG, width_height, p_conf, p_cls), 2).squeeze().t()
|
||||
|
|
@ -246,6 +249,7 @@ class Darknet(nn.Module):
|
|||
self.hyperparams, self.module_list = create_modules(self.module_defs)
|
||||
self.img_size = img_size
|
||||
self.loss_names = ['loss', 'x', 'y', 'w', 'h', 'conf', 'cls', 'nT']
|
||||
self.losses = []
|
||||
|
||||
def forward(self, x, targets=None, var=0):
|
||||
self.losses = defaultdict(float)
|
||||
|
|
@ -296,8 +300,8 @@ def load_darknet_weights(self, weights, cutoff=-1):
|
|||
if not os.path.isfile(weights):
|
||||
try:
|
||||
os.system('wget https://pjreddie.com/media/files/' + weights_file + ' -P ' + weights)
|
||||
except:
|
||||
assert os.path.isfile(weights)
|
||||
except IOError:
|
||||
print(weights + ' not found')
|
||||
|
||||
# Establish cutoffs
|
||||
if weights_file == 'darknet53.conv.74':
|
||||
|
|
|
|||
5
train.py
5
train.py
|
|
@ -36,7 +36,6 @@ def train(
|
|||
|
||||
# Configure run
|
||||
data_cfg = parse_data_cfg(data_cfg)
|
||||
num_classes = int(data_cfg['classes'])
|
||||
train_path = data_cfg['train']
|
||||
|
||||
# Initialize model
|
||||
|
|
@ -62,7 +61,7 @@ def train(
|
|||
# p.requires_grad = False
|
||||
|
||||
# Set optimizer
|
||||
optimizer = torch.optim.SGD(filter(lambda p: p.requires_grad, model.parameters()), lr=lr0, momentum=.9)
|
||||
optimizer = torch.optim.SGD(filter(lambda x: x.requires_grad, model.parameters()), lr=lr0, momentum=.9)
|
||||
|
||||
start_epoch = checkpoint['epoch'] + 1
|
||||
if checkpoint['optimizer'] is not None:
|
||||
|
|
@ -85,7 +84,7 @@ def train(
|
|||
model.to(device).train()
|
||||
|
||||
# Set optimizer
|
||||
optimizer = torch.optim.SGD(filter(lambda p: p.requires_grad, model.parameters()), lr=lr0, momentum=.9)
|
||||
optimizer = torch.optim.SGD(filter(lambda x: x.requires_grad, model.parameters()), lr=lr0, momentum=.9)
|
||||
|
||||
# Set scheduler
|
||||
# scheduler = torch.optim.lr_scheduler.MultiStepLR(optimizer, milestones=[54, 61], gamma=0.1)
|
||||
|
|
|
|||
|
|
@ -58,7 +58,6 @@ class LoadImages: # for inference
|
|||
class LoadWebcam: # for inference
|
||||
def __init__(self, img_size=416):
|
||||
self.cam = cv2.VideoCapture(0)
|
||||
self.nF = 9999 # number of image files
|
||||
self.height = img_size
|
||||
|
||||
def __iter__(self):
|
||||
|
|
@ -88,7 +87,7 @@ class LoadWebcam: # for inference
|
|||
return img_path, img, img0
|
||||
|
||||
def __len__(self):
|
||||
return self.nF # number of files
|
||||
return 0
|
||||
|
||||
|
||||
class LoadImagesAndLabels: # for training
|
||||
|
|
|
|||
|
|
@ -1,208 +0,0 @@
|
|||
import os
|
||||
import onnx
|
||||
from onnx import onnx_pb
|
||||
from onnx_coreml import convert
|
||||
import glob
|
||||
|
||||
|
||||
# https://github.com/onnx/onnx-coreml
|
||||
# http://machinethink.net/blog/mobilenet-ssdlite-coreml/
|
||||
# https://github.com/hollance/YOLO-CoreML-MPSNNGraph
|
||||
|
||||
def main():
|
||||
os.system('rm -rf saved_models && mkdir saved_models')
|
||||
files = glob.glob('saved_models/*.onnx') + glob.glob('../yolov3/weights/*.onnx')
|
||||
|
||||
for f in files:
|
||||
# 1. ONNX to CoreML
|
||||
name = 'saved_models/' + f.split('/')[-1].replace('.onnx', '')
|
||||
|
||||
# # Load the ONNX model
|
||||
model = onnx.load(f)
|
||||
|
||||
# Check that the IR is well formed
|
||||
print(onnx.checker.check_model(model))
|
||||
|
||||
# Print a human readable representation of the graph
|
||||
print(onnx.helper.printable_graph(model.graph))
|
||||
|
||||
model_file = open(f, 'rb')
|
||||
model_proto = onnx_pb.ModelProto()
|
||||
model_proto.ParseFromString(model_file.read())
|
||||
yolov3_model = convert(model_proto, image_input_names=['0'], preprocessing_args={'image_scale': 1. / 255})
|
||||
|
||||
# 2. Reduce model to FP16, change outputs to DOUBLE and save
|
||||
import coremltools
|
||||
|
||||
spec = yolov3_model.get_spec()
|
||||
for i in range(2):
|
||||
spec.description.output[i].type.multiArrayType.dataType = \
|
||||
coremltools.proto.FeatureTypes_pb2.ArrayFeatureType.ArrayDataType.Value('DOUBLE')
|
||||
|
||||
spec = coremltools.utils.convert_neural_network_spec_weights_to_fp16(spec)
|
||||
yolov3_model = coremltools.models.MLModel(spec)
|
||||
|
||||
name_out0 = spec.description.output[0].name
|
||||
name_out1 = spec.description.output[1].name
|
||||
|
||||
num_classes = 80
|
||||
num_anchors = 507 # 507 for yolov3-tiny,
|
||||
spec.description.output[0].type.multiArrayType.shape.append(num_anchors)
|
||||
spec.description.output[0].type.multiArrayType.shape.append(num_classes)
|
||||
# spec.description.output[0].type.multiArrayType.shape.append(1)
|
||||
|
||||
spec.description.output[1].type.multiArrayType.shape.append(num_anchors)
|
||||
spec.description.output[1].type.multiArrayType.shape.append(4)
|
||||
# spec.description.output[1].type.multiArrayType.shape.append(1)
|
||||
|
||||
# rename
|
||||
# input_mlmodel = input_tensor.replace(":", "__").replace("/", "__")
|
||||
# class_output_mlmodel = class_output_tensor.replace(":", "__").replace("/", "__")
|
||||
# bbox_output_mlmodel = bbox_output_tensor.replace(":", "__").replace("/", "__")
|
||||
#
|
||||
# for i in range(len(spec.neuralNetwork.layers)):
|
||||
# if spec.neuralNetwork.layers[i].input[0] == input_mlmodel:
|
||||
# spec.neuralNetwork.layers[i].input[0] = 'image'
|
||||
# if spec.neuralNetwork.layers[i].output[0] == class_output_mlmodel:
|
||||
# spec.neuralNetwork.layers[i].output[0] = 'scores'
|
||||
# if spec.neuralNetwork.layers[i].output[0] == bbox_output_mlmodel:
|
||||
# spec.neuralNetwork.layers[i].output[0] = 'boxes'
|
||||
|
||||
spec.neuralNetwork.preprocessing[0].featureName = '0'
|
||||
|
||||
yolov3_model.save(name + '.mlmodel')
|
||||
# yolov3_model.visualize_spec()
|
||||
print(spec.description)
|
||||
|
||||
# 2.5. Try to Predict:
|
||||
from PIL import Image
|
||||
img = Image.open('../yolov3/data/samples/zidane_416.jpg')
|
||||
out = yolov3_model.predict({'0': img}, useCPUOnly=True)
|
||||
print(out[name_out0].shape, out[name_out1].shape)
|
||||
|
||||
# 3. Create NMS protobuf
|
||||
import numpy as np
|
||||
|
||||
nms_spec = coremltools.proto.Model_pb2.Model()
|
||||
nms_spec.specificationVersion = 3
|
||||
|
||||
for i in range(2):
|
||||
decoder_output = yolov3_model._spec.description.output[i].SerializeToString()
|
||||
|
||||
nms_spec.description.input.add()
|
||||
nms_spec.description.input[i].ParseFromString(decoder_output)
|
||||
|
||||
nms_spec.description.output.add()
|
||||
nms_spec.description.output[i].ParseFromString(decoder_output)
|
||||
|
||||
nms_spec.description.output[0].name = 'confidence'
|
||||
nms_spec.description.output[1].name = 'coordinates'
|
||||
|
||||
output_sizes = [num_classes, 4]
|
||||
for i in range(2):
|
||||
ma_type = nms_spec.description.output[i].type.multiArrayType
|
||||
ma_type.shapeRange.sizeRanges.add()
|
||||
ma_type.shapeRange.sizeRanges[0].lowerBound = 0
|
||||
ma_type.shapeRange.sizeRanges[0].upperBound = -1
|
||||
ma_type.shapeRange.sizeRanges.add()
|
||||
ma_type.shapeRange.sizeRanges[1].lowerBound = output_sizes[i]
|
||||
ma_type.shapeRange.sizeRanges[1].upperBound = output_sizes[i]
|
||||
del ma_type.shape[:]
|
||||
|
||||
nms = nms_spec.nonMaximumSuppression
|
||||
nms.confidenceInputFeatureName = name_out0 # 1x507x80
|
||||
nms.coordinatesInputFeatureName = name_out1 # 1x507x4
|
||||
nms.confidenceOutputFeatureName = 'confidence'
|
||||
nms.coordinatesOutputFeatureName = 'coordinates'
|
||||
nms.iouThresholdInputFeatureName = 'iouThreshold'
|
||||
nms.confidenceThresholdInputFeatureName = 'confidenceThreshold'
|
||||
|
||||
nms.iouThreshold = 0.4
|
||||
nms.confidenceThreshold = 0.5
|
||||
nms.pickTop.perClass = True
|
||||
|
||||
labels = np.loadtxt('../yolov3/data/coco.names', dtype=str, delimiter='\n')
|
||||
nms.stringClassLabels.vector.extend(labels)
|
||||
|
||||
nms_model = coremltools.models.MLModel(nms_spec)
|
||||
nms_model.save(name + '_nms.mlmodel')
|
||||
|
||||
# out_nms = nms_model.predict({
|
||||
# '143': out['143'].squeeze().reshape((80, 507)),
|
||||
# '144': out['144'].squeeze().reshape((4, 507))
|
||||
# })
|
||||
# print(out_nms['confidence'].shape, out_nms['coordinates'].shape)
|
||||
|
||||
# # # 3.5 Add Softmax model
|
||||
# from coremltools.models import datatypes
|
||||
# from coremltools.models import neural_network
|
||||
#
|
||||
# input_features = [
|
||||
# ("141", datatypes.Array(num_anchors, num_classes, 1)),
|
||||
# ("143", datatypes.Array(num_anchors, 4, 1))
|
||||
# ]
|
||||
#
|
||||
# output_features = [
|
||||
# ("141", datatypes.Array(num_anchors, num_classes, 1)),
|
||||
# ("143", datatypes.Array(num_anchors, 4, 1))
|
||||
# ]
|
||||
#
|
||||
# builder = neural_network.NeuralNetworkBuilder(input_features, output_features)
|
||||
# builder.add_softmax(name="softmax_pcls",
|
||||
# dim=(0, 3, 2, 1),
|
||||
# input_name="scores",
|
||||
# output_name="permute_scores_output")
|
||||
# softmax_model = coremltools.models.MLModel(builder.spec)
|
||||
# softmax_model.save("softmax.mlmodel")
|
||||
|
||||
# 4. Pipeline models togethor
|
||||
from coremltools.models import datatypes
|
||||
# from coremltools.models import neural_network
|
||||
from coremltools.models.pipeline import Pipeline
|
||||
|
||||
input_features = [('0', datatypes.Array(3, 416, 416)),
|
||||
('iouThreshold', datatypes.Double()),
|
||||
('confidenceThreshold', datatypes.Double())]
|
||||
|
||||
output_features = ['confidence', 'coordinates']
|
||||
|
||||
pipeline = Pipeline(input_features, output_features)
|
||||
|
||||
# Add 3rd dimension of size 1 (apparently not needed, produces error on compile)
|
||||
yolov3_output = yolov3_model._spec.description.output
|
||||
yolov3_output[0].type.multiArrayType.shape[:] = [num_anchors, num_classes, 1]
|
||||
yolov3_output[1].type.multiArrayType.shape[:] = [num_anchors, 4, 1]
|
||||
|
||||
nms_input = nms_model._spec.description.input
|
||||
for i in range(2):
|
||||
nms_input[i].type.multiArrayType.shape[:] = yolov3_output[i].type.multiArrayType.shape[:]
|
||||
|
||||
# And now we can add the three models, in order:
|
||||
pipeline.add_model(yolov3_model)
|
||||
|
||||
pipeline.add_model(nms_model)
|
||||
|
||||
# Correct datatypes
|
||||
pipeline.spec.description.input[0].ParseFromString(yolov3_model._spec.description.input[0].SerializeToString())
|
||||
pipeline.spec.description.output[0].ParseFromString(nms_model._spec.description.output[0].SerializeToString())
|
||||
pipeline.spec.description.output[1].ParseFromString(nms_model._spec.description.output[1].SerializeToString())
|
||||
|
||||
# Update metadata
|
||||
pipeline.spec.description.metadata.versionString = 'yolov3-tiny.pt imported from PyTorch'
|
||||
pipeline.spec.description.metadata.shortDescription = 'https://github.com/ultralytics/yolov3'
|
||||
pipeline.spec.description.metadata.author = 'glenn.jocher@ultralytics.com'
|
||||
pipeline.spec.description.metadata.license = 'https://github.com/ultralytics/yolov3'
|
||||
|
||||
user_defined_metadata = {'classes': ','.join(labels),
|
||||
'iou_threshold': str(nms.iouThreshold),
|
||||
'confidence_threshold': str(nms.confidenceThreshold)}
|
||||
pipeline.spec.description.metadata.userDefined.update(user_defined_metadata)
|
||||
|
||||
# Save the model
|
||||
pipeline.spec.specificationVersion = 3
|
||||
final_model = coremltools.models.MLModel(pipeline.spec)
|
||||
final_model.save((name + '_pipelined.mlmodel'))
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
|
|
@ -1,14 +1,12 @@
|
|||
|
||||
|
||||
def parse_model_config(path):
|
||||
"""Parses the yolo-v3 layer configuration file and returns module definitions"""
|
||||
file = open(path, 'r')
|
||||
lines = file.read().split('\n')
|
||||
lines = [x for x in lines if x and not x.startswith('#')]
|
||||
lines = [x.rstrip().lstrip() for x in lines] # get rid of fringe whitespaces
|
||||
lines = [x.rstrip().lstrip() for x in lines] # get rid of fringe whitespaces
|
||||
module_defs = []
|
||||
for line in lines:
|
||||
if line.startswith('['): # This marks the start of a new block
|
||||
if line.startswith('['): # This marks the start of a new block
|
||||
module_defs.append({})
|
||||
module_defs[-1]['type'] = line[1:-1].rstrip()
|
||||
if module_defs[-1]['type'] == 'convolutional':
|
||||
|
|
@ -20,6 +18,7 @@ def parse_model_config(path):
|
|||
|
||||
return module_defs
|
||||
|
||||
|
||||
def parse_data_cfg(path):
|
||||
"""Parses the data configuration file"""
|
||||
options = dict()
|
||||
|
|
|
|||
|
|
@ -254,7 +254,7 @@ def build_targets(target, anchor_wh, nA, nC, nG):
|
|||
iou_order = torch.argsort(-iou_best) # best to worst
|
||||
|
||||
# Unique anchor selection
|
||||
u = torch.cat((gi, gj, a), 0).view(3, -1)
|
||||
u = torch.cat((gi, gj, a), 0).view((3, -1))
|
||||
_, first_unique = np.unique(u[:, iou_order], axis=1, return_index=True) # first unique indices
|
||||
# _, first_unique = torch.unique(u[:, iou_order], dim=1, return_inverse=True) # different than numpy?
|
||||
|
||||
|
|
@ -340,7 +340,8 @@ def non_max_suppression(prediction, conf_thres=0.5, nms_thres=0.4):
|
|||
# x = np.concatenate((log_w.reshape(-1, 1), log_h.reshape(-1, 1)), 1)
|
||||
# from scipy.stats import multivariate_normal
|
||||
# for c in range(60):
|
||||
# shape_likelihood[:, c] = multivariate_normal.pdf(x, mean=mat['class_mu'][c, :2], cov=mat['class_cov'][c, :2, :2])
|
||||
# shape_likelihood[:, c] =
|
||||
# multivariate_normal.pdf(x, mean=mat['class_mu'][c, :2], cov=mat['class_cov'][c, :2, :2])
|
||||
|
||||
class_prob, class_pred = torch.max(F.softmax(pred[:, 5:], 1), 1)
|
||||
|
||||
|
|
@ -436,7 +437,6 @@ def coco_class_count(path='../coco/labels/train2014/'):
|
|||
def plot_results():
|
||||
# Plot YOLO training results file 'results.txt'
|
||||
import glob
|
||||
import numpy as np
|
||||
import matplotlib.pyplot as plt
|
||||
# import os; os.system('rm -rf results.txt && wget https://storage.googleapis.com/ultralytics/results_v1_0.txt')
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue