SSD_ERROR can not find inference_model.zip

Questions
1

gist.github.com/kevinthesun/c1904e900848df4548ce5dfb18c719c7/archive/a28c4856c827fe766aa3da0e35bad41d44f0fb26.zip Connection timed out

2

I can still download it. Can you ry it again?

3

File “/opt/software/tvm/vta/tests/python/integration/resnet2.py”, line 219, in
device)
File “/opt/software/tvm/vta/tests/python/integration/resnet2.py”, line 95, in generate_graph
params = nnvm.compiler.load_param_dict(t1)
File “/opt/software/tvm/nnvm/python/nnvm/compiler/param_dict.py”, line 60, in load_param_dict
load_arr = _load_param_dict(param_bytes)
File “/opt/software/tvm/python/tvm/_ffi/_ctypes/function.py”, line 184, in call
ctypes.byref(ret_val), ctypes.byref(ret_tcode)))
File “/opt/software/tvm/python/tvm/_ffi/base.py”, line 66, in check_call
raise TVMError(py_str(_LIB.TVMGetLastError()))
tvm._ffi.base.TVMError: [10:34:57] /opt/software/tvm/tvm/nnvm/src/compiler/graph_runtime.cc:79: Check failed: header == kTVMNDArrayListMagic Invalid parameters file format

4

can you solve ? resnet_qt18.params has no problem ,but ssd_resnet50_512-0000.params has this problem

5

The issue is - the parameter file you are passing needs to be massaged to be able to run on VTA (which the current resnet_qt18.params is compatible with). Please stay tuned with the current relay release: we’re working on VTA compatibility so you can convert other parameter files to the VTA format (https://github.com/dmlc/tvm/issues/1673)