-
Hello, after installing all the recommended packages and successfully runnning inference on demo images with the original scripts, I face a training obstruction.
Old issue similar to #https://githu…
-
paddleX转换的模型，摄像头调用有问题
result = module.predict(images=[(r"XXXX.jpg")])
调用图片 没问题
但是
cv2.VideoCapture(0)
ret, frame = cap.read()
result = module.predict(images=frame,use_gpu=True)
摄像头调用的时候 …
-
First, thanks for the great work.
When I run without distributed mode, it works fine: This means that it created "output/training/" folder and saved the training results there.
However, when I try…
-
Traceback (most recent call last):
File "train.py", line 163, in
tf.app.run()
File "C:\Users\haiL\Anaconda2\envs\tf15\lib\site-packages\tensorflow\python\platform\app.py", line 125, in run…
-
目前看文档好像只有coco、imagenet等官方数据集，数据集太大了，现在没法进行测试，自己的数据集也没法加载
-
Hello,
## 🚀 Feature
I think it would be more generic to have `transform`(https://github.com/pytorch/vision/blob/3d65fc6723f1e0709916f24d819d6e17a925b394/torchvision/models/detection/faster_rcnn.…
-
## Context
* torchserve version: 0.3.0
* torch-model-archiver version: 0.3.0
* torch version: 1.7.1+cpu
* torchvision version [if any]: 0.8.2+cpu
* Operating System and version: Ubuntu 20.04
…
lgvaz updated
2 years ago
-
```
model = dict(
type='FasterRCNN',
pretrained='torchvision://resnet50',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2…
-
```
import os
os.environ['CUDA_VISIBLE_DEVICES'] = '1'
import cv2
import torch
import torchvision
from vpf import PyNvCodec as nvc
from vpf import PytorchNvCodec as pnvc
print("PyTorch Version…
-
Dashboard to track the performance of torchinductor on CPU.
cc @ezyang @msaroufim @wconstab @bdhirsh @anijain2305 @zou3519 @soumith @ngimel @chauhang