zjc
/
yolov5
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

torch.cuda.amp bug fix (#2750) 

PR https://github.com/ultralytics/yolov5/pull/2725 introduced a very specific bug that only affects multi-GPU trainings. Apparently the cause was using the torch.cuda.amp decorator in the autoShape forward method. I've implemented amp more traditionally in this PR, and the bug is resolved.
This commit is contained in:
Glenn Jocher 2021-04-09 18:19:49 +02:00 committed by GitHub
parent fca5e2a48f
commit b5de52c4cd
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 13 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
models/common.py
View File

@ -10,6 +10,7 @@ import requests
import torch import torch
import torch.nn as nn import torch.nn as nn
from PIL import Image from PIL import Image
from torch.cuda import amp
from utils.datasets import letterbox from utils.datasets import letterbox
from utils.general import non_max_suppression, make_divisible, scale_coords, increment_path, xyxy2xywh from utils.general import non_max_suppression, make_divisible, scale_coords, increment_path, xyxy2xywh
@ -237,7 +238,6 @@ class autoShape(nn.Module):
return self return self
@torch.no_grad() @torch.no_grad()
@torch.cuda.amp.autocast(torch.cuda.is_available())
def forward(self, imgs, size=640, augment=False, profile=False): def forward(self, imgs, size=640, augment=False, profile=False):
# Inference from various sources. For height=640, width=1280, RGB images example inputs are: # Inference from various sources. For height=640, width=1280, RGB images example inputs are:
# filename: imgs = 'data/samples/zidane.jpg' # filename: imgs = 'data/samples/zidane.jpg'
@ -251,6 +251,7 @@ class autoShape(nn.Module):
t = [time_synchronized()] t = [time_synchronized()]
p = next(self.model.parameters()) # for device and type p = next(self.model.parameters()) # for device and type
if isinstance(imgs, torch.Tensor): # torch if isinstance(imgs, torch.Tensor): # torch
with amp.autocast(enabled=p.device.type != 'cpu'):
return self.model(imgs.to(p.device).type_as(p), augment, profile) # inference return self.model(imgs.to(p.device).type_as(p), augment, profile) # inference
# Pre-process # Pre-process
@ -278,6 +279,7 @@ class autoShape(nn.Module):
x = torch.from_numpy(x).to(p.device).type_as(p) / 255. # uint8 to fp16/32 x = torch.from_numpy(x).to(p.device).type_as(p) / 255. # uint8 to fp16/32
t.append(time_synchronized()) t.append(time_synchronized())
with amp.autocast(enabled=p.device.type != 'cpu'):
# Inference # Inference
y = self.model(x, augment, profile)[0] # forward y = self.model(x, augment, profile)[0] # forward
t.append(time_synchronized()) t.append(time_synchronized())