Comments (3)
Sorry I'm on vacation this weekend and not at my computer. Can you paste the full error message? Also make sure you have the latest version of the repo, you might want to do a git pull if you haven't recently.
from ssd.pytorch.
The error as follow:
Finished loading model!
Testing image 1/2510....
Traceback (most recent call last):
File "test.py", line 105, in
test_net(args.save_folder, net, args.cuda, valset, base_transform(net.size,(104,117,123)), args.top_k, thresh=args.confidence_threshold)
File "test.py", line 56, in test_net
y = net(x) # forward pass
File "/home/hd/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 206, in call
result = self.forward(*input, **kwargs)
File "/home/hd/ssd.pytorch/ssd.py", line 107, in forward
self.priors # default boxes
File "/home/hd/ssd.pytorch/functions/detection.py", line 59, in forward
self.nms_threshold, self.keep_top_k)
File "/home/hd/ssd.pytorch/box_utils.py", line 256, in nms
return torch.cat((scores[keep[:count]],boxes[keep[:count]]),1),count
RuntimeError: dimension out of range - got 1 but the tensor is only 1D
from ssd.pytorch.
Hey sorry for leaving you hanging. I was pretty confused about this issue because it just randomly showed up but I found out it's because of a recent PyTorch update you can find here. It turns out torch.cat used to support catting along non-existent dimensions, but 3 days ago that was disallowed. So I'll fix that right now
from ssd.pytorch.
Related Issues (20)
- what does target actually look like in criterion(out, target)? HOT 3
- Result produced too many boxes HOT 1
- About training only VOC2007 HOT 1
- eval my voc dataset ' __init__() missing 5 required positional arguments' HOT 4
- RuntimeError: Error(s) in loading state_dict for SSD:
- How can I get precision and recall in eval.py
- setting an array element with a sequence. HOT 4
- np.random.choice doesn't support tuple (or something like that) anymore
- the result in onnx model is all zero.
- ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (6,) + inhomogeneous part. HOT 4
- Do you calculate mAP in the right way ?
- ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (6,) + inhomogeneous part. HOT 5
- sh code error report
- Follow this to get this ancient code works HOT 1
- ValueError: operands could not be broadcast together with shapes HOT 1
- What environment is the best to run test.py?
- Packages versions
- RuntimeError: index 1 is out of bounds for dimension 1 with size 1
- TypeError: forward() missing 1 required positional argument: 'x' HOT 5
- Extract loss for each image in the batch
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from ssd.pytorch.