zoufangyu1987 opened a new issue #5462: URL: https://github.com/apache/incubator-tvm/issues/5462
File "/data_1/TVM/TVM/tvm/python/tvm/_ffi/_ctypes/packed_func.py", line 219, in __call__ raise get_last_ffi_error() tvm._ffi.base.TVMError: Traceback (most recent call last): [bt] (8) /data_1/TVM/TVM/tvm/build/libtvm.so(TVMFuncCall+0x65) [0x7f95b6864615] [bt] (7) /data_1/TVM/TVM/tvm/build/libtvm.so(+0xa0dfb4) [0x7f95b5f25fb4] [bt] (6) /data_1/TVM/TVM/tvm/build/libtvm.so(tvm::IRModule::FromExpr(tvm::RelayExpr const&, tvm::Map<tvm::GlobalVar, tvm::BaseFunc, void, void> const&, tvm::Map<tvm::GlobalTypeVar, tvm::TypeData, void, void> const&)+0x26e) [0x7f95b5f21d9e] [bt] (5) /data_1/TVM/TVM/tvm/build/libtvm.so(tvm::IRModuleNode::Add(tvm::GlobalVar const&, tvm::BaseFunc const&, bool)+0x3cf) [0x7f95b5f2191f] [bt] (4) /data_1/TVM/TVM/tvm/build/libtvm.so(tvm::RunTypeCheck(tvm::IRModule const&, tvm::GlobalVar const&, tvm::relay::Function)+0x25e) [0x7f95b5f1de5e] [bt] (3) /data_1/TVM/TVM/tvm/build/libtvm.so(tvm::relay::InferType(tvm::relay::Function const&, tvm::IRModule const&, tvm::GlobalVar const&)+0x1dd) [0x7f95b661c4fd] [bt] (2) /data_1/TVM/TVM/tvm/build/libtvm.so(tvm::relay::TypeInferencer::Infer(tvm::RelayExpr)+0x71) [0x7f95b661bd31] [bt] (1) /data_1/TVM/TVM/tvm/build/libtvm.so(tvm::ErrorReporter::RenderErrors(tvm::IRModule const&, bool)+0x2292) [0x7f95b5f5ea22] [bt] (0) /data_1/TVM/TVM/tvm/build/libtvm.so(dmlc::LogMessageFatal::~LogMessageFatal()+0x7c) [0x7f95b5ed859c] File "/data_1/TVM/TVM/tvm/src/ir/error.cc", line 133 TVMError: Error(s) have occurred. The program has been annotated with them: In `main`: v0.0.4 %181 = nn.conv2d_transpose(%180, %v1479, channels=1, kernel_size=[4, 4], strides=[2, 2], padding=[1, 1, 1, 1], groups=256) in particular dimension 1 conflicts 0 does not match 1; unable to unify: `Tensor[(256, 0, 4, 4), float32]` and `Tensor[(256, 1, 4, 4), float32]`; ; %182 = (%175, %181); %183 = concatenate(%182, axis=1); nn.conv2d(%183, %v1505, padding=[1, 1, 1, 1], channels=256, kernel_size=[3, 3]) in particular dimension 1 conflicts 257 does not match 512; unable to unify: `Tensor[(256, 257, 3, 3), float32]` and `Tensor[(256, 512, 3, 3), float32]`; } ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org