nihui/ncnn - ncnn - 开源协同云脑生态支撑系统

Commit Graph

Author	SHA1	Message	Date
nihui	ae4f630467	pnnx fuse multiheadattention (#4544 ) * torch baddbmm * always convert to fp32 for shape inference * silence info on nonetype and devicetype	3 years ago
nihui	242e775d21	pnnx convert torch log10, pow 2 as square (#4518 )	3 years ago
Yoh	0fffefd3c9	fix crop bug and eliminate Tensor.clone (#4416 ) * fix crop bug and eliminate Tensor.clone * fix crop slice bug on msvc * fix slice bug on msvc	3 years ago
nihui	6967baaccc	pnnx convert torch bitwise left_shift right_shift (#4349 )	3 years ago
nihui	eceac35a7f	implement MultiheadAttention kdim vdim (#4347 )	3 years ago
nihui	a2af6369d9	match inplace slice copy pattern, rewrite copy uses (#4338 )	3 years ago
nihui	cb88e16fdf	pnnx save onnx zero (#4077 )	3 years ago
nihui	0f9a3bb9dc	fix slice end index, fix fp16 model weight alignment (#4317 )	3 years ago
Fangjun Kuang	5281d51535	implement GLU and pnnx conversion (#4283 )	3 years ago
nihui	cef95f64a4	pnnx math operation (#4251 )	3 years ago
moozae	94ec06a8a5	delete unused variables (#3965 )	3 years ago
nihui	08e2dd5a0c	pnnx ncnn fp16 storage conversion as a pass (#3939 )	3 years ago
nihui	53fa52e78a	pnnx support complex data type, convert torch complex/imag/real/fft.rfft2/fft.irfft2 (#3890 )	4 years ago
nihui	0daad605e0	fix make slice expression with dynamic parameters	4 years ago
nihui	2dc1ae45fe	pnnx bitwise and compare op (#3791 ) * bitwise and compare op * masked_fill and gather test	4 years ago
nihui	d476191ff1	pnnx export_onnx function (#3784 )	4 years ago
nihui	318dc4f5f5	convert Tensor.select to ncnn, fuse multiheadattention unpack, add vit_b_32 end2end test (#3763 )	4 years ago
nihui	a2b25c88b0	pnnx convert torch.einsum (#3744 ) * normalize einsum equation * replace dot pair with alphabet word * shorten permute equation	4 years ago
nihui	a14acbc6dd	pnnx save ncnn bin with fp16 storage (#3715 )	4 years ago
nihui	41cd40ac1f	convert pnnx torch.unbind and torch.ones/ones_like family (#3583 ) * convert torch.unbind * torch.ones torch.ones_like * torch.full torch.full_like * torch.randn_like * torch.empty torch.empty_like	4 years ago
nihui	6b2495cc24	add reshape before and after pooling 123d with no batch dimension (#3566 )	4 years ago
nihui	d452eca28f	convert torch.matmul, eliminate noop pad and identity op, fuse transpose matmul, fuse select to unbind (#3554 )	4 years ago
nihui	340b4e673e	pnnx fold constant (#3521 )	4 years ago
nihui	7d3503c06a	pnnx Tensor index (#3483 ) * pnnx Tensor index * add test	4 years ago
nihuini	1db16ce9fc	pnnx torch norm stack test	4 years ago
nihui	143258e317	pnnx torchvision deformconv2d (#3459 )	4 years ago
nihuini	c5efaf02b7	unique attribute identifier	4 years ago
nihui	a3aea3fe99	support torch dequantize, quantize_per_tensor and quantized linearrelu, fix #3429	4 years ago
nihui	db1fed6e11	pnnx cmdline argument inputshape with type (#3419 )	4 years ago
nihui	7b0f3fbb78	pnnx user provided parameter (#3417 )	4 years ago
nihui	999e640d43	dynamic convolution weight (#3408 )	4 years ago
nihui	e4c821a468	PNNX is an open standard for PyTorch model interoperability (#3262 ) Co-authored-by: nihui <nihui@users.noreply.github.com> Co-authored-by: xiaooquanwu <546749317@qq.com>	4 years ago

32 Commits (ae4f6304676cb6ec9f0afccd0bee3f42e5020e11)