I’m converting a model into jit tracer and keep getting a tracer warning for the code below.
Can someone give me some advise？
class YOLOLayer(nn.Module):
"""Detection layer"""
def __init__(self, anchors, num_classes, img_dim=512):
super(YOLOLayer, self).__init__()
self.anchors = anchors
self.num_anchors = len(anchors)
self.num_classes = num_classes
self.bbox_attrs = 5 + num_classes
self.ignore_thres = 0.5
self.mse_loss = nn.MSELoss()
self.bce_loss = nn.BCELoss()
self.ce_loss = nn.CrossEntropyLoss()
self.l1_loss = nn.L1Loss()
self.obj_scale = 1
self.noobj_scale = 10
self.metrics = {}
self.img_dim = img_dim
def forward(self, x, targets=None):
nA = self.num_anchors
nB = x.size(0)
nG = x.size(2)
stride = self.img_dim / nG
# Tensors for cuda support
FloatTensor = torch.cuda.FloatTensor if x.is_cuda else torch.FloatTensor
LongTensor = torch.cuda.LongTensor if x.is_cuda else torch.LongTensor
ByteTensor = torch.cuda.ByteTensor if x.is_cuda else torch.ByteTensor
prediction = x.view(nB, nA, self.bbox_attrs, nG, nG).permute(0, 1, 3, 4, 2).contiguous()
# Get outputs
x = torch.sigmoid(prediction[..., 0]) # Center x
y = torch.sigmoid(prediction[..., 1]) # Center y
w = prediction[..., 2] # Width
h = prediction[..., 3] # Height
pred_conf = torch.sigmoid(prediction[..., 4]) # Conf
pred_cls = torch.sigmoid(prediction[..., 5:]) # Cls pred.
# Calculate offsets for each grid
grid_x = torch.arange(nG).repeat(nG, 1).view([1, 1, nG, nG]).type(FloatTensor)
grid_y = torch.arange(nG).repeat(nG, 1).t().view([1, 1, nG, nG]).type(FloatTensor)
scaled_anchors = FloatTensor([(a_w / stride, a_h / stride) for a_w, a_h in self.anchors])
anchor_w = scaled_anchors[:, 0:1].view((1, nA, 1, 1))
anchor_h = scaled_anchors[:, 1:2].view((1, nA, 1, 1))
# Add offset and scale with anchors
pred_boxes = FloatTensor(prediction[..., :4].shape)
pred_boxes[..., 0] = x.data + grid_x
pred_boxes[..., 1] = y.data + grid_y
pred_boxes[..., 2] = torch.exp(w.data) * anchor_w
pred_boxes[..., 3] = torch.exp(h.data) * anchor_h
output = torch.cat(
(pred_boxes.view(nB, -1, 4) * stride, pred_conf.view(nB, -1, 1), pred_cls.view(nB, -1, self.num_classes)),
-1,
)
The TracerWarning infomatiom:
E:\DetectionYoloV3\models.py:157: TracerWarning: Converting a tensor to a Python float might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
scaled_anchors = FloatTensor([(a_w / stride, a_h / stride) for a_w, a_h in self.anchors])
E:\DetectionYoloV3\models.py:162: TracerWarning: Converting a tensor to a Python index might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
pred_boxes = FloatTensor(prediction[..., :4].shape)
D:\Anoconda\envs\pytorch_gpu_1.1_CUDA10.1\lib\site-packages\torch\jit\__init__.py:702: TracerWarning: Output nr 1. of the traced function does not match the corresponding output of the Python function. Detailed error:
Not within tolerance rtol=1e-05 atol=1e-05 at input[0, 3754, 2] (2.9778142945768974e+38 vs. inf) and 99135 other locations (21.00%)
_check_trace([example_inputs], func, executor_options, traced, check_tolerance, _force_outplace)