pytorch-YOLOv4

pytorch-YOLOv4 copied to clipboard

Does anyone encounter the situation that CPU can run but GPU will be stuck in the first epoch?

5

Does anyone encounter the situation that CPU can run but GPU will be stuck in the first epoch? Results can be obtained when training with CPU. But when I train...

EternalEvan

您好！ 我有一个问题。请帮我一下。  这一个情况的时候怎么解决？ ONNX -> TensorRT

seogihyun

I am using JETPACK 4.5.1 with tensorrt- 7.3.1 on AGX with yolov4-tiny_416-VIDS The bounding boxes are not appropriate Please help 

prashant36

inference problem

7

sorry, I don't understand the way of inference.my way: (follow this: python models.py ) (!!!INTERRUPTED.pth is my traing result) python models.py 80 "/home/cad429/code/lzh/my_yolo/INTERRUPTED.pth" "/home/cad429/code/lzh/my_yolo/data/dog.jpg" 576 768 but error: RuntimeError: Error(s)...

Lsmartworld

It should be `minShapes`, not `minShape` ``` --minShapes=spec Build with dynamic shapes using a profile with the min shapes provided --optShapes=spec Build with dynamic shapes using a profile with the...

kHarshit

Transfer to ONNX model, but speed is down a lot （from 5fps to 0.5 fps）

2

When I transfer the pth model to ONNX model, and use the ONNX model for detection, I find the speed is downed from 5fps to 0.5 fps, anybody meets this...

beys90

Hello, what do the variables **cutmix** and **mosaic** in the CFG do? Thanks

mburges-cvl

Cannot freeze conv layers?

1

I didn't find the keyword of freezing layers

forever208

Is the class Yolov4 in models.py and class Darknet in darknet2pytorch.py the same model?

10

I'm curious why do i have to train with Yolov4 instance model in train.py and inference with Darknet instance model. Are they same models?? Oh, I think I have to...

sykimm

NotImplementedError: Create your own 'get_image_id' function

7

Traceback (most recent call last): File "train.py", line 626, in # device=device, ) File "train.py", line 425, in train evaluator = evaluate(eval_model, val_loader, config, device) File "/data/anaconda3/lib/python3.7/site-packages/torch/autograd/grad_mode.py", line 49, in...

yuxx0218