Namespace(batch_size=1, conf_thres=0.25, device='cpu', dynamic=False, dynamic_batch=False, end2end=False, fp16=False, grid=True, img_size=[640, 640], include_nms=False, int8=False, iou_thres=0.45, max_wh=None, simplify=True, topk_all=100, weights='yolov7-tiny.pt')
YOLOR 🚀 v0.1-107-g44d8ab4 torch 1.12.1+cu102 CPU

Fusing layers... 
Model Summary: 200 layers, 6219709 parameters, 6219709 gradients
/home/cyrus/.local/lib/python3.8/site-packages/torch/functional.py:478: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at  ../aten/src/ATen/native/TensorShape.cpp:2895.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]

Starting TorchScript export with torch 1.12.1+cu102...
/home/cyrus/work/repos/yolov7/models/yolo.py:52: TracerWarning: Converting a tensor to a Python boolean 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!
  if self.grid[i].shape[2:4] != x[i].shape[2:4]:
TorchScript export success, saved as yolov7-tiny.torchscript.pt
CoreML export failure: No module named 'coremltools'

Starting TorchScript-Lite export with torch 1.12.1+cu102...
TorchScript-Lite export success, saved as yolov7-tiny.torchscript.ptl

Starting ONNX export with onnx 1.12.0...
/home/cyrus/work/repos/yolov7/models/yolo.py:582: TracerWarning: Converting a tensor to a Python boolean 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!
  if augment:
/home/cyrus/work/repos/yolov7/models/yolo.py:614: TracerWarning: Converting a tensor to a Python boolean 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!
  if profile:
/home/cyrus/work/repos/yolov7/models/yolo.py:629: TracerWarning: Converting a tensor to a Python boolean 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!
  if profile:
Simplifier failure: No module named 'onnxsim'
ONNX export success, saved as yolov7-tiny.onnx

Export complete (4.02s). Visualize with https://github.com/lutzroeder/netron.

Namespace(calib_batch_size=8, calib_cache='./calibration.cache', calib_input=None, calib_num_images=5000, conf_thres=0.4, end2end=True, engine='yolov7-tiny.trt', iou_thres=0.5, max_det=100, onnx='yolov7-tiny.onnx', precision='fp16', verbose=False, workspace=1)
[09/12/2022-15:41:59] [TRT] [I] [MemUsageChange] Init CUDA: CPU +449, GPU +0, now: CPU 475, GPU 283 (MiB)
[09/12/2022-15:41:59] [TRT] [I] [MemUsageSnapshot] Begin constructing builder kernel library: CPU 475 MiB, GPU 283 MiB
[09/12/2022-15:41:59] [TRT] [I] [MemUsageSnapshot] End constructing builder kernel library: CPU 629 MiB, GPU 327 MiB
[09/12/2022-15:41:59] [TRT] [W] onnx2trt_utils.cpp:366: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
Failed to load ONNX file: /home/cyrus/work/repos/TensorRT-For-YOLO-Series/yolov7-tiny.onnx
In node 88 (importResize): UNSUPPORTED_NODE: Assertion failed: scales.is_weights() && "Resize scales must be an initializer!"

python export.py --weights ./yolov7-tiny.pt --grid --end2end --simplify --topk-all 100 --iou-thres 0.65 --conf-thres 0.35 --img-size 640 640

git clone https://github.com/Linaom1214/tensorrt-python.git
python ./tensorrt-python/export.py -o yolov7-tiny.onnx -e yolov7-tiny-nms.trt -p fp16

修改 export_onnx.py 为 model.head.decode_in_inference = True

修改 yolox/models/yolox_head.py文件

# [batch, n_anchors_all, 85]
# outputs = torch.cat(
#     [x.flatten(start_dim=2) for x in outputs], dim=2

# ).permute(0, 2, 1)
outputs = torch.cat(
    [x.view(-1,int(x.size(1)),int(x.size(2)*x.size(3))) for x in outputs], dim=2

).permute(0, 2, 1)

# 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) 

[09/19/2022-11:35:56] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:35:56] [TRT] [W] Weights [name=Conv_613 + PWN(PWN(Sigmoid_614), Mul_615).weight] had the following issues when converted to FP16:
[09/19/2022-11:35:56] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:35:56] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:35:56] [TRT] [W] Weights [name=Conv_613 + PWN(PWN(Sigmoid_614), Mul_615).weight] had the following issues when converted to FP16:
[09/19/2022-11:35:56] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:35:56] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:35:56] [TRT] [W] Weights [name=Conv_613 + PWN(PWN(Sigmoid_614), Mul_615).weight] had the following issues when converted to FP16:
[09/19/2022-11:35:56] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:35:56] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:35:56] [TRT] [W] Weights [name=Conv_613 + PWN(PWN(Sigmoid_614), Mul_615).weight] had the following issues when converted to FP16:
[09/19/2022-11:35:56] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:35:56] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:35:57] [TRT] [W] Weights [name=Conv_613 + PWN(PWN(Sigmoid_614), Mul_615).weight] had the following issues when converted to FP16:
[09/19/2022-11:35:57] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:35:57] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:35:57] [TRT] [W] Weights [name=Conv_613 + PWN(PWN(Sigmoid_614), Mul_615).weight] had the following issues when converted to FP16:
[09/19/2022-11:35:57] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:35:57] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:00] [TRT] [W] Weights [name=Conv_817 + PWN(PWN(Sigmoid_818), Mul_819).weight] had the following issues when converted to FP16:
[09/19/2022-11:36:00] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:00] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:01] [TRT] [W] Weights [name=Conv_817 + PWN(PWN(Sigmoid_818), Mul_819).weight] had the following issues when converted to FP16:
[09/19/2022-11:36:01] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:01] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:01] [TRT] [W] Weights [name=Conv_817 + PWN(PWN(Sigmoid_818), Mul_819).weight] had the following issues when converted to FP16:
[09/19/2022-11:36:01] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:01] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:01] [TRT] [W] Weights [name=Conv_817 + PWN(PWN(Sigmoid_818), Mul_819).weight] had the following issues when converted to FP16:
[09/19/2022-11:36:01] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:01] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:01] [TRT] [W] Weights [name=Conv_817 + PWN(PWN(Sigmoid_818), Mul_819).weight] had the following issues when converted to FP16:
[09/19/2022-11:36:01] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:01] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:01] [TRT] [W] Weights [name=Conv_817 + PWN(PWN(Sigmoid_818), Mul_819).weight] had the following issues when converted to FP16:
[09/19/2022-11:36:01] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:01] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:01] [TRT] [W] Weights [name=Conv_817 + PWN(PWN(Sigmoid_818), Mul_819).weight] had the following issues when converted to FP16:
[09/19/2022-11:36:01] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:01] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:01] [TRT] [W] Weights [name=Conv_817 + PWN(PWN(Sigmoid_818), Mul_819).weight] had the following issues when converted to FP16:
[09/19/2022-11:36:01] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:01] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:03] [TRT] [W] Weights [name=Conv_620 + PWN(PWN(Sigmoid_621), Mul_622).weight] had the following issues when converted to FP16:
[09/19/2022-11:36:03] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:03] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:03] [TRT] [W] Weights [name=Conv_620 + PWN(PWN(Sigmoid_621), Mul_622).weight] had the following issues when converted to FP16:
[09/19/2022-11:36:03] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:03] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:03] [TRT] [W] Weights [name=Conv_620 + PWN(PWN(Sigmoid_621), Mul_622).weight] had the following issues when converted to FP16:
[09/19/2022-11:36:03] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:03] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:03] [TRT] [W] Weights [name=Conv_620 + PWN(PWN(Sigmoid_621), Mul_622).weight] had the following issues when converted to FP16:
[09/19/2022-11:36:03] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:03] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:03] [TRT] [W] Weights [name=Conv_620 + PWN(PWN(Sigmoid_621), Mul_622).weight] had the following issues when converted to FP16:
[09/19/2022-11:36:03] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:03] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:03] [TRT] [W] Weights [name=Conv_620 + PWN(PWN(Sigmoid_621), Mul_622).weight] had the following issues when converted to FP16:
[09/19/2022-11:36:03] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:03] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:03] [TRT] [W] Weights [name=Conv_620 + PWN(PWN(Sigmoid_621), Mul_622).weight] had the following issues when converted to FP16:
[09/19/2022-11:36:03] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:03] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:03] [TRT] [W] Weights [name=Conv_620 + PWN(PWN(Sigmoid_621), Mul_622).weight] had the following issues when converted to FP16:
[09/19/2022-11:36:03] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:03] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:03] [TRT] [W] Weights [name=Conv_620 + PWN(PWN(Sigmoid_621), Mul_622).weight] had the following issues when converted to FP16:
[09/19/2022-11:36:03] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:03] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:03] [TRT] [W] Weights [name=Conv_620 + PWN(PWN(Sigmoid_621), Mul_622).weight] had the following issues when converted to FP16:
[09/19/2022-11:36:03] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:03] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:03] [TRT] [W] Weights [name=Conv_620 + PWN(PWN(Sigmoid_621), Mul_622).weight] had the following issues when converted to FP16:
[09/19/2022-11:36:03] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:03] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:03] [TRT] [W] Weights [name=Conv_620 + PWN(PWN(Sigmoid_621), Mul_622).weight] had the following issues when converted to FP16:
[09/19/2022-11:36:03] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:03] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:03] [TRT] [W] Weights [name=Conv_620 + PWN(PWN(Sigmoid_621), Mul_622).weight] had the following issues when converted to FP16:
[09/19/2022-11:36:03] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:03] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:03] [TRT] [W] Weights [name=Conv_620 + PWN(PWN(Sigmoid_621), Mul_622).weight] had the following issues when converted to FP16:
[09/19/2022-11:36:03] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:03] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:04] [TRT] [W] Weights [name=Conv_616 + PWN(PWN(Sigmoid_617), Mul_618).weight] had the following issues when converted to FP16:
[09/19/2022-11:36:04] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:04] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:04] [TRT] [W] Weights [name=Conv_616 + PWN(PWN(Sigmoid_617), Mul_618).weight] had the following issues when converted to FP16:
[09/19/2022-11:36:04] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:04] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:04] [TRT] [W] Weights [name=Conv_616 + PWN(PWN(Sigmoid_617), Mul_618).weight] had the following issues when converted to FP16:
[09/19/2022-11:36:04] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:04] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:04] [TRT] [W] Weights [name=Conv_616 + PWN(PWN(Sigmoid_617), Mul_618).weight] had the following issues when converted to FP16:
[09/19/2022-11:36:04] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:04] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:04] [TRT] [W] Weights [name=Conv_616 + PWN(PWN(Sigmoid_617), Mul_618).weight] had the following issues when converted to FP16:
[09/19/2022-11:36:04] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:04] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:04] [TRT] [W] Weights [name=Conv_616 + PWN(PWN(Sigmoid_617), Mul_618).weight] had the following issues when converted to FP16:
[09/19/2022-11:36:04] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:04] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:04] [TRT] [W] Weights [name=Conv_616 + PWN(PWN(Sigmoid_617), Mul_618).weight] had the following issues when converted to FP16:
[09/19/2022-11:36:04] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:04] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:04] [TRT] [W] Weights [name=Conv_616 + PWN(PWN(Sigmoid_617), Mul_618).weight] had the following issues when converted to FP16:
[09/19/2022-11:36:04] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:04] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:05] [TRT] [W] Weights [name=Conv_829.weight] had the following issues when converted to FP16:
[09/19/2022-11:36:05] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:05] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:05] [TRT] [W] Weights [name=Conv_829.weight] had the following issues when converted to FP16:
[09/19/2022-11:36:05] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:05] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:05] [TRT] [W] Weights [name=Conv_829.weight] had the following issues when converted to FP16:
[09/19/2022-11:36:05] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:05] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:05] [TRT] [W] Weights [name=Conv_829.weight] had the following issues when converted to FP16:
[09/19/2022-11:36:05] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:05] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:05] [TRT] [W] Weights [name=Conv_829.weight] had the following issues when converted to FP16:
[09/19/2022-11:36:05] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:05] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:05] [TRT] [W] Weights [name=Conv_829.weight] had the following issues when converted to FP16:
[09/19/2022-11:36:05] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:05] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:05] [TRT] [W] Weights [name=Conv_829.weight] had the following issues when converted to FP16:
[09/19/2022-11:36:05] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:05] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:05] [TRT] [W] Weights [name=Conv_829.weight] had the following issues when converted to FP16:
[09/19/2022-11:36:05] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:05] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:05] [TRT] [W] Weights [name=Conv_829.weight] had the following issues when converted to FP16:
[09/19/2022-11:36:05] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:05] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:05] [TRT] [W] Weights [name=Conv_829.weight] had the following issues when converted to FP16:
[09/19/2022-11:36:05] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:05] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:05] [TRT] [W] Weights [name=Conv_829.weight] had the following issues when converted to FP16:
[09/19/2022-11:36:05] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:05] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:05] [TRT] [W] Weights [name=Conv_829.weight] had the following issues when converted to FP16:
[09/19/2022-11:36:05] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:05] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:05] [TRT] [W] Weights [name=Conv_829.weight] had the following issues when converted to FP16:
[09/19/2022-11:36:05] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:05] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:05] [TRT] [W] Weights [name=Conv_829.weight] had the following issues when converted to FP16:
[09/19/2022-11:36:05] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:05] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:35] [TRT] [W] Weights [name=Conv_624 || Conv_627 || Conv_652 || Conv_655.weight] had the following issues when converted to FP16:
[09/19/2022-11:36:35] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:35] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:35] [TRT] [W] Weights [name=Conv_624 || Conv_627 || Conv_652 || Conv_655.weight] had the following issues when converted to FP16:
[09/19/2022-11:36:35] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:35] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:35] [TRT] [W] Weights [name=Conv_624 || Conv_627 || Conv_652 || Conv_655.weight] had the following issues when converted to FP16:
[09/19/2022-11:36:35] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:35] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:35] [TRT] [W] Weights [name=Conv_624 || Conv_627 || Conv_652 || Conv_655.weight] had the following issues when converted to FP16:
[09/19/2022-11:36:35] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:35] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:35] [TRT] [W] Weights [name=Conv_624 || Conv_627 || Conv_652 || Conv_655.weight] had the following issues when converted to FP16:
[09/19/2022-11:36:35] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:35] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:35] [TRT] [W] Weights [name=Conv_624 || Conv_627 || Conv_652 || Conv_655.weight] had the following issues when converted to FP16:
[09/19/2022-11:36:35] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:35] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:35] [TRT] [W] Weights [name=Conv_624 || Conv_627 || Conv_652 || Conv_655.weight] had the following issues when converted to FP16:
[09/19/2022-11:36:35] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:35] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:35] [TRT] [W] Weights [name=Conv_624 || Conv_627 || Conv_652 || Conv_655.weight] had the following issues when converted to FP16:
[09/19/2022-11:36:35] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:35] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
[09/19/2022-11:36:35] [TRT] [W] Weights [name=Conv_624 || Conv_627 || Conv_652 || Conv_655.weight] had the following issues when converted to FP16:
[09/19/2022-11:36:35] [TRT] [W]  - Subnormal FP16 values detected. 
[09/19/2022-11:36:35] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.

 pip install nvidia-pyindex
Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple, https://pypi.ngc.nvidia.com
Requirement already satisfied: nvidia-pyindex in d:\anaconda3\lib\site-packages (1.0.9)

(yolov7) PS D:\> pip install --upgrade nvidia-tensorrt

Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple, https://pypi.ngc.nvidia.com
Collecting nvidia-tensorrt
  Downloading https://pypi.tuna.tsinghua.edu.cn/packages/b8/a3/3da2bd25b6243d7a19b6c08c0e92f7c04f9863e70d213fee3141d574dccb/nvidia-tensorrt-0.0.1.dev5.tar.gz (7.9 kB)
  Preparing metadata (setup.py) ... error
  error: subprocess-exited-with-error

  × python setup.py egg_info did not run successfully.
  │ exit code: 1
  ╰─> [17 lines of output]
      Traceback (most recent call last):
        File "<string>", line 2, in <module>
        File "<pip-setuptools-caller>", line 34, in <module>
        File "C:\Users\mm\AppData\Local\Temp\pip-install-86qwtshw\nvidia-tensorrt_2f4607caa6e542a3bcb5c92aa2e31d0e\setup.py", line 150, in <module>
          raise RuntimeError(open("ERROR.txt", "r").read())
      RuntimeError:
      ###########################################################################################
      The package you are trying to install is only a placeholder project on PyPI.org repository.
      This package is hosted on NVIDIA Python Package Index.

      This package can be installed as:
      ```
      $ pip install nvidia-pyindex
      $ pip install nvidia-tensorrt
      ```
      ###########################################################################################

      [end of output]

  note: This error originates from a subprocess, and is likely not a problem with pip.
error: metadata-generation-failed

× Encountered error while generating package metadata.
╰─> See above for output.

note: This is an issue with the package mentioned above, not pip.
hint: See above for details.

F:\tensorrt-python-main>python export.py -o v6n.onnx -e v6n.trt -p fp16
[07/04/2022-19:11:00] [TRT] [I] [MemUsageChange] Init CUDA: CPU +291, GPU +0, now: CPU 4590, GPU 1091 (MiB)
[07/04/2022-19:11:00] [TRT] [I] [MemUsageSnapshot] Begin constructing builder kernel library: CPU 4650 MiB, GPU 1091 MiB
[07/04/2022-19:11:01] [TRT] [I] [MemUsageSnapshot] End constructing builder kernel library: CPU 4870 MiB, GPU 1161 MiB
F:\tensorrt-python-main\export.py:109: DeprecationWarning: Use set_memory_pool_limit instead.
  self.config.max_workspace_size = workspace * (2 ** 30)
[07/04/2022-19:11:01] [TRT] [W] onnx2trt_utils.cpp:365: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
[07/04/2022-19:11:01] [TRT] [W] onnx2trt_utils.cpp:391: One or more weights outside the range of INT32 was clamped
[07/04/2022-19:11:01] [TRT] [W] onnx2trt_utils.cpp:391: One or more weights outside the range of INT32 was clamped
[07/04/2022-19:11:01] [TRT] [W] onnx2trt_utils.cpp:391: One or more weights outside the range of INT32 was clamped
Network Description
Input 'image_arrays' with shape (1, 3, 416, 416) and dtype DataType.FLOAT
Output 'outputs' with shape (1, 3549, 7) and dtype DataType.FLOAT
Building fp16 Engine in F:\tensorrt-python-main\v6n.trt
F:\tensorrt-python-main\export.py:187: DeprecationWarning: Use build_serialized_network instead.
  with self.builder.build_engine(self.network, self.config) as engine, open(engine_path, "wb") as f:
[07/04/2022-19:11:01] [TRT] [I] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +195, GPU +70, now: CPU 5034, GPU 1231 (MiB)
[07/04/2022-19:11:01] [TRT] [I] [MemUsageChange] Init cuDNN: CPU +110, GPU +46, now: CPU 5144, GPU 1277 (MiB)
[07/04/2022-19:11:01] [TRT] [I] Local timing cache in use. Profiling results in this builder pass will not be stored.
Could not load library cudnn_cnn_infer64_8.dll. Error code 193