deepvac

deepvac copied to clipboard

TypeError: 'Proxy' object cannot be interpreted as an integer

4

## 🐛 Bug I get an error - loop in forward and loop count num from input x - call torch.quantization.quantize_fx.prepare_fx ## To Reproduce Steps to reproduce the behavior: 1....

MHGL

[BUG]没有看到量化训练的地方阿？

2

**bug描述** 请描述该bug。 **如何复现** 复现步骤: 1. 步骤1xxxx 2. 步骤2xxxx 3. 步骤3xxxx 4. 看，错误就是这个...... **预期结果** 请描述你原本期望的结果是什么。 **截图** 如果有必要的话，请添加截图。 **如果使用的是MLab HomePod，请填写** - 宿主机 cpu/ram/cuda设备： [比如. intel i9-9820X/32GB/RTX2080ti ] - 宿主机操作系统/内核版本/GPU驱动： [比如. ubuntu 20.04/5.4.0-74-generic/460.80...

cqray1990

[BUG]CoreML模型转换双线差值上采样问题

1

**bug描述** 在转化coreml过程中，如果代码中存在pytorch双线差值上采样，在ios13上会报错，在ios14上可以顺利执行。 **如何复现** 复现步骤: ```python3 # -*- coding:utf-8 -*- import torch from torch.nn import functional as F class MyModule(torch.nn.Module): def __init__(self): super(MyModule, self).__init__() ... def forward(self, x): return F.interpolate(x, scale_factor=2,...

MHGL

**bug描述** 我们将ESP网络转换成TNN模型部署在华为手机上和骁龙处理器手机上。在骁龙处理器手机上，GPU/opencl 是cpu模型推理速度的2倍，而在华为麒麟980手机上，GPU/opencl 比cpu模型推理速度还要慢（从13fps下降到10fps）。 **如何复现** 复现步骤: 1. config.py 中配置ESP网络，打开转换TNN模型的开关； 2. 运行test.py输出TNN模型； 3. 集成到安卓项目中，然后安装到华为麒麟980手机上； 4. 测试摄像头输入时的fps速度。 **预期结果** 华为麒麟980手机上，GPU/opencl 应该大于等于cpu的推理速度。 **截图** 如果有必要的话，请添加截图。 **如果使用的是MLab HomePod，请填写** - 宿主机 cpu/ram/cuda设备： intel i9-9820X/32GB/RTX2080ti - 宿主机操作系统/内核版本/GPU驱动：ubuntu 20.04/5.4.0-74-generic/460.80...

gemfield

Error Code 1: Cask (isConsistent)

3

## question I get this error while convert module to tensorrt - module has 5 down sample - upsample at last down sample - torch.cat ## To Reproduce Steps to...

MHGL

NCNN: Unsupported unsqueeze axes !

1

## 🐛 Bug I get this error while convert yolov5 Focus module to ncnn ## To Reproduce Steps to reproduce the behavior: 1. code example ```python3 import torch # init...

MHGL

void onnxruntime::BroadcastIterator::Init(ptrdiff_t, ptrdiff_t) axis == 1 || axis == largest was false. Attempting to broadcast an axis by a dimension other than 1. 3 by 224

2

## 🐛 Bug I get an error - reigster_buffer in Module - onnxruntime on onnx from torch.onnx.export ## To Reproduce Steps to reproduce the behavior: 1. code example ```python3 import...

MHGL

torch.fx.proxy.TraceError: symbolically traced variables cannot be used as inputs to control flow

1

## 🐛 Bug I get an error - if-else in forward method - call torch.quantization.quantize_fx.prepare_fx ## To Reproduce Steps to reproduce the behavior: 1. code example ```python3 import torch from...

MHGL

## 🐞Describe the bug I got this error while: nn.BatchNorm2d -> torch.jit.script -> coreml ## Trace ```python3 Traceback (most recent call last): File "mini_code.py", line 13, in model = ct.convert(...

MHGL

## 🐞Describe the bug torch_model -> torch.jit.script -> coreml I got this error while try to setattr in forward. ## Trace ```python3 Traceback (most recent call last): File "mini_code.py", line...

MHGL