PYNQ: PYTHON PRODUCTIVITY

Output features of PYNQ-DPU

Hi,

After successfully running the MNIST classifier example on the ZCU104 board using DPU-PYNQ,

I am trying to store the output features of the final convolution layers, so I tried this :

total = test_data.shape[0]
array = np.empty_like (output_data)
for i in range(total):
image[0,…] = test_data[i]
job_id = dpu.execute_async(input_data, output_data)
dpu.wait(job_id)
temp = [j.reshape(1, outputSize) for j in output_data]
array= np.vstack((array, temp))

I was wondering if what I did Is correct?