rebuild

tools/model_rknn_transform.py

@@ -0,0 +1,186 @@
+import os
+import pdb
+import urllib
+import traceback
+import time
+import sys
+import numpy as np
+import cv2
+from config import config as conf
+from rknn.api import RKNN
+
+import config
+
+# ONNX_MODEL = 'resnet50v2.onnx'
+# RKNN_MODEL = 'resnet50v2.rknn'
+ONNX_MODEL = 'checkpoints/resnet18_scale=1.0/best.onnx'
+RKNN_MODEL = 'checkpoints/resnet18_scale=1.0/best.rknn'
+
+
+# ONNX_MODEL = 'v3_small_0424.onnx'
+# RKNN_MODEL = 'v3_small_0424.rknn'
+
+def show_outputs(outputs):
+    # print('***************outputs', outputs)
+    output = outputs[0][0]
+    # print('len(outputs)',len(output), output)
+    output_sorted = sorted(output, reverse=True)
+    top5_str = 'resnet50v2\n-----TOP 5-----\n'
+    for i in range(5):
+        value = output_sorted[i]
+        index = np.where(output == value)
+        for j in range(len(index)):
+            if (i + j) >= 5:
+                break
+            if value > 0:
+                topi = '{}: {}\n'.format(index[j], value)
+            else:
+                topi = '-1: 0.0\n'
+            top5_str += topi
+    # pdb.set_trace()
+    print(top5_str)
+
+
+def readable_speed(speed):
+    speed_bytes = float(speed)
+    speed_kbytes = speed_bytes / 1024
+    if speed_kbytes > 1024:
+        speed_mbytes = speed_kbytes / 1024
+        if speed_mbytes > 1024:
+            speed_gbytes = speed_mbytes / 1024
+            return "{:.2f} GB/s".format(speed_gbytes)
+        else:
+            return "{:.2f} MB/s".format(speed_mbytes)
+    else:
+        return "{:.2f} KB/s".format(speed_kbytes)
+
+
+def show_progress(blocknum, blocksize, totalsize):
+    speed = (blocknum * blocksize) / (time.time() - start_time)
+    speed_str = " Speed: {}".format(readable_speed(speed))
+    recv_size = blocknum * blocksize
+
+    f = sys.stdout
+    progress = (recv_size / totalsize)
+    progress_str = "{:.2f}%".format(progress * 100)
+    n = round(progress * 50)
+    s = ('#' * n).ljust(50, '-')
+    f.write(progress_str.ljust(8, ' ') + '[' + s + ']' + speed_str)
+    f.flush()
+    f.write('\r\n')
+
+
+if __name__ == '__main__':
+
+    # Create RKNN object
+    rknn = RKNN(verbose=True)
+
+    # If resnet50v2 does not exist, download it.
+    # Download address:
+    # https://s3.amazonaws.com/onnx-model-zoo/resnet/resnet50v2/resnet50v2.onnx
+    if not os.path.exists(ONNX_MODEL):
+        print('--> Download {}'.format(ONNX_MODEL))
+        url = 'https://s3.amazonaws.com/onnx-model-zoo/resnet/resnet50v2/resnet50v2.onnx'
+        download_file = ONNX_MODEL
+        try:
+            start_time = time.time()
+            urllib.request.urlretrieve(url, download_file, show_progress)
+        except:
+            print('Download {} failed.'.format(download_file))
+            print(traceback.format_exc())
+            exit(-1)
+        print('done')
+
+    # pre-process config
+    print('--> config model')
+    # rknn.config(mean_values=[123.675, 116.28, 103.53], std_values=[58.82, 58.82, 58.82])
+    rknn.config(
+        mean_values=[[127.5, 127.5, 127.5]],
+        std_values=[[127.5, 127.5, 127.5]],
+        target_platform='rk3588',
+        model_pruning=False,
+        compress_weight=False,
+        single_core_mode=True)
+    # rknn.config(
+    #     mean_values=[[127.5, 127.5, 127.5]],  # 对于单通道图像，可以设置为 [[127.5]]
+    #     std_values=[[127.5, 127.5, 127.5]],  # 对于单通道图像，可以设置为 [[127.5]]
+    #     target_platform='rk3588',  # 设置目标平台
+    #     # quantize_dtype='int8',
+    #     # quantize_algo='normal',
+    #     # output_optimize=False,
+    #     # output_format='rknnb'
+    # )
+    print('done')
+
+    # Load model
+    print('--> Loading model')
+    ret = rknn.load_onnx(model=ONNX_MODEL)
+    if ret != 0:
+        print('Load model failed!')
+        exit(ret)
+    print('done')
+
+    # Build model
+    print('--> Building model')
+    ret = rknn.build(do_quantization=True, dataset='./dataset.txt')
+    # ret = rknn.build(do_quantization=False, dataset='./dataset.txt')
+    if ret != 0:
+        print('Build model failed!')
+        exit(ret)
+    print('done')
+
+    # Export rknn model
+    print('--> Export rknn model')
+    ret = rknn.export_rknn(RKNN_MODEL)
+    if ret != 0:
+        print('Export rknn model failed!')
+        exit(ret)
+    print('done')
+
+    # Set inputs
+    img = cv2.imread('./dog_224x224.jpg')
+    # img = cv2.imread('./data/gift_test/Havegift/20241213-161415-cb8e0762-f376-45d1-8f36-7dc070990fa5/subimg/cam1_9_tid2_fid(18, 33250169482).png')
+    # print('img', img)
+    # with open('pixel_values.txt', 'w') as file:
+
+    #    for y in range(img.shape[0]):
+    #        for x in range(img.shape[1]):
+    #            b, g, r = img[y, x]
+    #            file.write(f'{r},{g},{b}\n')
+
+    # img = cv2.imread('./810115161912_810115161912_20240131-145622_0da14e4d-a3da-499f-b512-2d4168ab1c87_front_addGood_70f75407b7ae_29_01.jpg')
+    img = cv2.resize(img, (224, 224))
+    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
+
+    # img = conf.test_transform(img)
+    # img = img.numpy()
+    # img = img.transpose(1, 2, 0)
+
+    # Init runtime environment
+    print('--> Init runtime environment')
+    ret = rknn.init_runtime()
+    # ret = rknn.init_runtime('rk3588')
+    if ret != 0:
+        print('Init runtime environment failed!')
+        exit(ret)
+    print('done')
+
+    # Inference
+    print('--> Running model')
+    T1 = time.time()
+    outputs = rknn.inference(inputs=[img])
+    # outputs = rknn.inference(inputs=img)
+    T2 = time.time()
+    print('消耗时间 >>> {}'.format(T2 - T1))
+    with open('result_0415_128.txt', 'a') as f:
+        f.write(str(outputs))
+    # pdb.set_trace()
+    print('***outputs', outputs)
+    np.save('./onnx_resnet50v2_0.npy', outputs[0])
+    x = outputs[0]
+    output = np.exp(x) / np.sum(np.exp(x))
+    outputs = [output]
+    show_outputs(outputs)
+    print('done')
+
+    rknn.release()