# line 55 forward function in yolov5/models/yolo.py 
# bs, _, ny, nx = x[i].shape  # x(bs,255,20,20) to x(bs,3,20,20,85)
# x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
# modified into:

bs, _, ny, nx = x[i].shape  # x(bs,255,20,20) to x(bs,3,20,20,85)
bs = -1
ny = int(ny)
nx = int(nx)
x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()

# line 70 in yolov5/models/yolo.py
#  z.append(y.view(bs, -1, self.no))
# modified into：
z.append(y.view(bs, self.na * ny * nx, self.no))

############# for yolov5-6.0 #####################
# line 65 in yolov5/models/yolo.py
# if self.grid[i].shape[2:4] != x[i].shape[2:4] or self.onnx_dynamic:
#    self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i)
# modified into:
if self.grid[i].shape[2:4] != x[i].shape[2:4] or self.onnx_dynamic:
    self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i)

# disconnect for pytorch trace
anchor_grid = (self.anchors[i].clone() * self.stride[i]).view(1, -1, 1, 1, 2)

# line 70 in yolov5/models/yolo.py
# y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh
# modified into:
y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * anchor_grid  # wh

# line 73 in yolov5/models/yolo.py
# wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh
# modified into:
wh = (y[..., 2:4] * 2) ** 2 * anchor_grid  # wh
############# for yolov5-6.0 #####################


# line 52 in yolov5/export.py
# torch.onnx.export(dynamic_axes={'images': {0: 'batch', 2: 'height', 3: 'width'},  # shape(1,3,640,640)
#                                'output': {0: 'batch', 1: 'anchors'}  # shape(1,25200,85)  修改为
# modified into:
torch.onnx.export(dynamic_axes={'images': {0: 'batch'},  # shape(1,3,640,640)
                                'output': {0: 'batch'}  # shape(1,25200,85) 

# line 45 forward function in yolov7/models/yolo.py 
# bs, _, ny, nx = x[i].shape  # x(bs,255,20,20) to x(bs,3,20,20,85)
# x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
# modified into:

bs, _, ny, nx = map(int, x[i].shape)  # x(bs,255,20,20) to x(bs,3,20,20,85)
bs = -1
x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()

# line 52 in yolov7/models/yolo.py
# y = x[i].sigmoid()
# y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i]  # xy
# y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh
# z.append(y.view(bs, -1, self.no))
# modified into：
y = x[i].sigmoid()
xy = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i]  # xy
wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i].view(1, -1, 1, 1, 2)  # wh
classif = y[..., 4:]
y = torch.cat([xy, wh, classif], dim=-1)
z.append(y.view(bs, self.na * ny * nx, self.no))

# line 57 in yolov7/models/yolo.py
# return x if self.training else (torch.cat(z, 1), x)
# modified into:
return x if self.training else torch.cat(z, 1)


# line 52 in yolov7/models/export.py
# output_names=['classes', 'boxes'] if y is None else ['output'],
# dynamic_axes={'images': {0: 'batch', 2: 'height', 3: 'width'},  # size(1,3,640,640)
#               'output': {0: 'batch', 2: 'y', 3: 'x'}} if opt.dynamic else None)
# modified into:
output_names=['classes', 'boxes'] if y is None else ['output'],
dynamic_axes={'images': {0: 'batch'},  # size(1,3,640,640)
              'output': {0: 'batch'}} if opt.dynamic else None)

# line 206 forward fuction in yolox/models/yolo_head.py. Replace the commented code with the uncommented code
# self.hw = [x.shape[-2:] for x in outputs] 
self.hw = [list(map(int, x.shape[-2:])) for x in outputs]


# line 208 forward function in yolox/models/yolo_head.py. Replace the commented code with the uncommented code
# [batch, n_anchors_all, 85]
# outputs = torch.cat(
#     [x.flatten(start_dim=2) for x in outputs], dim=2
# ).permute(0, 2, 1)
proc_view = lambda x: x.view(-1, int(x.size(1)), int(x.size(2) * x.size(3)))
outputs = torch.cat(
    [proc_view(x) for x in outputs], dim=2
).permute(0, 2, 1)


# line 253 decode_output function in yolox/models/yolo_head.py Replace the commented code with the uncommented code
#outputs[..., :2] = (outputs[..., :2] + grids) * strides
#outputs[..., 2:4] = torch.exp(outputs[..., 2:4]) * strides
#return outputs
xy = (outputs[..., :2] + grids) * strides
wh = torch.exp(outputs[..., 2:4]) * strides
return torch.cat((xy, wh, outputs[..., 4:]), dim=-1)

# line 77 in tools/export_onnx.py
model.head.decode_in_inference = True

# line 55 forward function in yolov3/models/yolo.py 
# bs, _, ny, nx = x[i].shape  # x(bs,255,20,20) to x(bs,3,20,20,85)
# x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
# modified into:

bs, _, ny, nx = map(int, x[i].shape)  # x(bs,255,20,20) to x(bs,3,20,20,85)
bs = -1
x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()


# line 70 in yolov3/models/yolo.py
#  z.append(y.view(bs, -1, self.no))
# modified into：
z.append(y.view(bs, self.na * ny * nx, self.no))

# line 62 in yolov3/models/yolo.py
# if self.grid[i].shape[2:4] != x[i].shape[2:4] or self.onnx_dynamic:
#    self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i)
# modified into:
if self.grid[i].shape[2:4] != x[i].shape[2:4] or self.onnx_dynamic:
    self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i)
anchor_grid = (self.anchors[i].clone() * self.stride[i]).view(1, -1, 1, 1, 2)

# line 70 in yolov3/models/yolo.py
# y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh
# modified into:
y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * anchor_grid  # wh

# line 73 in yolov3/models/yolo.py
# wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh
# modified into:
wh = (y[..., 2:4] * 2) ** 2 * anchor_grid  # wh


# line 52 in yolov3/export.py
# torch.onnx.export(dynamic_axes={'images': {0: 'batch', 2: 'height', 3: 'width'},  # shape(1,3,640,640)
#                                'output': {0: 'batch', 1: 'anchors'}  # shape(1,25200,85) 
# modified into:
torch.onnx.export(dynamic_axes={'images': {0: 'batch'},  # shape(1,3,640,640)
                                'output': {0: 'batch'}  # shape(1,25200,85) 

# line 24 in models/retinaface.py
# return out.view(out.shape[0], -1, 2) is modified into 
return out.view(-1, int(out.size(1) * out.size(2) * 2), 2)

# line 35 in models/retinaface.py
# return out.view(out.shape[0], -1, 4) is modified into
return out.view(-1, int(out.size(1) * out.size(2) * 2), 4)

# line 46 in models/retinaface.py
# return out.view(out.shape[0], -1, 10) is modified into
return out.view(-1, int(out.size(1) * out.size(2) * 2), 10)

# The following modification ensures the output of resize node is based on scale rather than shape such that dynamic batch can be achieved.
# line 89 in models/net.py
# up3 = F.interpolate(output3, size=[output2.size(2), output2.size(3)], mode="nearest") is modified into
up3 = F.interpolate(output3, scale_factor=2, mode="nearest")

# line 93 in models/net.py
# up2 = F.interpolate(output2, size=[output1.size(2), output1.size(3)], mode="nearest") is modified into
up2 = F.interpolate(output2, scale_factor=2, mode="nearest")

# The following code removes softmax (bug sometimes happens). At the same time, concatenate the output to simplify the decoding.
# line 123 in models/retinaface.py
# if self.phase == 'train':
#     output = (bbox_regressions, classifications, ldm_regressions)
# else:
#     output = (bbox_regressions, F.softmax(classifications, dim=-1), ldm_regressions)
# return output
# the above is modified into:
output = (bbox_regressions, classifications, ldm_regressions)
return torch.cat(output, dim=-1)

# set 'opset_version=11' to ensure a successful export
# torch_out = torch.onnx._export(net, inputs, output_onnx, export_params=True, verbose=False,
#     input_names=input_names, output_names=output_names)
# is modified into:
torch_out = torch.onnx._export(net, inputs, output_onnx, export_params=True, verbose=False, opset_version=11,
    input_names=input_names, output_names=output_names)

import pytrt

model = models.resnet18(True).eval()
pytrt.from_torch(
    model, 
    dummy_input, 
    max_batch_size=16, 
    onnx_save_file="test.onnx", 
    engine_save_file="engine.trtmodel"
)

import pytrt

yolo   = tp.Yolo(engine_file, type=tp.YoloType.X)   # engine_file is the trtmodel file
image  = cv2.imread("inference/car.jpg")
bboxes = yolo.commit(image).get()

import pytrt

model     = models.resnet18(True).eval().to(device) # pt model
trt_model = tp.from_torch(model, input)
trt_out   = trt_model(input)