Hi there, I was trying to deploying with TVM with slight changes on model weights, however, it seems that the GraphModule always yields the same output even the params are updated.
g = graph_executor.GraphModule(lib["default"](dev))
g.set_input(input_name, data)
g.run()
output = g.get_output(0)
print(np.mean(output.numpy()) * 10000000 )
#### 94.54726750846021
# try to change the weights
tmp = params["fc_weight"].numpy()
params["fc_weight"] = tvm.nd.array(np.random.randn(*tmp.shape), tvm.cpu(0))
params["fc_weight"] = tvm.nd.array(np.zeros_like(tmp.shape), tvm.cpu(0))
g.load_params(tvm.runtime.save_param_dict(params))
g.set_input(input_name, data)
g.run()
output = g.get_output(0)
print(np.mean(output.numpy()) * 10000000 )
#### 94.54726750846021
The output keeps the same after new parameters are loaded. I have confirmed that the issue appear on both X86 and ARM arch. The TVM I am using is the based on commit 6720d3593d4dac6015418d4b7e9ad875bbf0b0a2 (submitted on Jan 24 2022)