Qingchao Shen

[Bug][Relay] cannot squeeze axis with dimension not equal to 1 at Keras frontend

4

For the LSTM below, when `batch_size != 1` (i.e., the size of first dimension input), compiling will lead to an unexpected crash and throw `Check failed: *axis_ptr == 1 (2...

[Bug] [Relay] data types float64 and float32 do not match in BroadcastRel

1

The PyTorch model with `hardswish` operator and input_dtype=float64 crashed when load to relay. ## Actual behavior ``` data types float64 and float32 do not match in BroadcastRel data types float64...

### Actual behavior  What actually happened ### Environment Any environment details, such as: Operating System, TVM version, etc ### Steps to reproduce ``` import tvm import tvm.relay as relay...

[Bug]: Inconsistency output produced between OpenVINO and ONNXRuntime

3

### OpenVINO Version openvino-nightly 2023.2.0.dev20231101 ### Operating System Ubuntu 18.04 (LTS) ### Device used for inference BATCH ### Framework ONNX ### Model used https://github.com/jikechao/onnx_models/blob/main/SoftmaxCrossEntropyLoss.onnx ### Issue description The given model...

[Bug]: 'min_val' and 'max_val' should have the same type as 'out_type' attribute.

1

### OpenVINO Version openvino-nightly 2023.2.0.dev20231101 ### Operating System Ubuntu 18.04 (LTS) ### Device used for inference CPU ### Framework ONNX ### Model used https://github.com/jikechao/onnx_models/blob/main/RandomUniformLike.onnx ### Issue description For the type...

[Bug]: ONNX translation:invalid attribute type in Bernoulli operator

1

### OpenVINO Version openvino-nightly 2023.2.0.dev20231101 ### Operating System Ubuntu 18.04 (LTS) ### Device used for inference CPU ### Framework ONNX ### Model used https://github.com/jikechao/onnx_models/blob/main/Bernoulli.onnx ### Issue description  The conversion...

[Bug] [Relax] Segmentation fault when executeing inference for the IR with branch in the runtime

4

### Actual behavior ```shell ... [09:37:39] /software/tvm/src/runtime/relax_vm/vm.cc:735: pc = 21, execute: vm.builtin.alloc_tensor Segmentation fault (core dumped) ``` ### Steps to reproduce ```python import tvm from tvm import relax import numpy...