andreasfloros / rwnn Goto Github PK
View Code? Open in Web Editor NEWRecursive Wavelet Neural Networks for Image Restoration
License: MIT License
Recursive Wavelet Neural Networks for Image Restoration
License: MIT License
python train.py --should_prepare True
PyTorch is running on NVIDIA GeForce RTX 4090
training set # samples 43200
validation set # samples 100
Traceback (most recent call last):
File "E:\AI\RWNN\train.py", line 50, in
dtmins, info = coordinator.train()
File "E:\AI\RWNN\coordinator\coordinator.py", line 71, in train
fyi, loss = self.model.module.get_training_loss(data)
File "E:\AI\RWNN\coordinator\wrapper.py", line 26, in get_training_loss
res, ne = self.alg(inp, layer = self.decode_depth, show_ne = True)
File "E:\AI\RWNN\coordinator\wrapper_algorithms.py", line 16, in dae
[cn, dn], nes = self.transform_net.forward(x, map = map, J = layer)
File "E:\AI\RWNN\models\transform_model.py", line 35, in forward
x, yd = self.inn(x, ne)
File "E:\AI\RWNN\env\lib\site-packages\torch\nn\modules\module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "E:\AI\RWNN\models\inn.py", line 14, in forward
x = lift(x, sigma)
File "E:\AI\RWNN\env\lib\site-packages\torch\nn\modules\module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "E:\AI\RWNN\models\inn.py", line 40, in forward
c = c + self.u(nd, sigma)
File "E:\AI\RWNN\env\lib\site-packages\torch\nn\modules\module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "E:\AI\RWNN\models\inn.py", line 68, in forward
return self.net(x, sigma)
File "E:\AI\RWNN\env\lib\site-packages\torch\nn\modules\module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
RuntimeError: The following operation failed in the TorchScript interpreter.
Traceback of TorchScript (most recent call last):
RuntimeError: nvrtc: error: invalid value for --gpu-architecture (-arch)
nvrtc compilation failed:
#define NAN __int_as_float(0x7fffffff)
#define POS_INFINITY __int_as_float(0x7f800000)
#define NEG_INFINITY __int_as_float(0xff800000)
template
device T maximum(T a, T b) {
return isnan(a) ? a : (a > b ? a : b);
}
template
device T minimum(T a, T b) {
return isnan(a) ? a : (a < b ? a : b);
}
extern "C" global
void fused_mul_add_relu(float* tout_7, float* tthreshold_2, float* tsigma_1, float* aten_relu) {
{
float tout_7_1 = __ldg(tout_7 + (long long)(threadIdx.x) + 512ll * (long long)(blockIdx.x));
float tthreshold_2_1 = __ldg(tthreshold_2 + (((long long)(threadIdx.x) + 512ll * (long long)(blockIdx.x)) / 1024ll) % 32ll);
float tsigma_1_1 = __ldg(tsigma_1 + 0ll);
aten_relu[(long long)(threadIdx.x) + 512ll * (long long)(blockIdx.x)] = tout_7_1 + tthreshold_2_1 * tsigma_1_1<0.f ? 0.f : tout_7_1 + tthreshold_2_1 * tsigma_1_1;
}
}
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.