Add new file

llvm/projects/keras/src/resnet50_imagenet.py

+import os
+import glob
+
+import scipy
+import scipy.io
+import cv2
+import numpy as np
+
+import keras
+from keras.models import Sequential, Model
+from keras.layers import *
+from keras.applications.resnet50 import ResNet50, preprocess_input
+from keras.utils import to_categorical
+from keras import backend as K
+
+from frontend.approxhpvm_translator import translate_to_approxhpvm
+from frontend.weight_utils import dumpCalibrationData
+
+
+np.random.seed(2020)
+
+os.environ["CUDA_VISIBLE_DEVICES"] = "1"
+
+K.set_image_data_format('channels_first')
+
+
+num_images = 1000
+val_size = 100
+
+data_format = 'channels_first'
+
+
+
+def identity_block(input_tensor, kernel_size, filters, stage, block):
+    filters1, filters2, filters3 = filters
+    bn_axis = 1
+
+    x = Conv2D(filters1, (1, 1))(input_tensor)
+    x = BatchNormalization(axis=bn_axis)(x)
+    x = Activation('relu')(x)
+
+    x = Conv2D(filters2, kernel_size,
+                      padding='same')(x)
+    x = BatchNormalization(axis=bn_axis)(x)
+    x = Activation('relu')(x)
+
+    x = Conv2D(filters3, (1, 1))(x)
+    x = BatchNormalization(axis=bn_axis)(x)
+
+    x = add([x, input_tensor])
+    x = Activation('relu')(x)
+    return x
+
+
+def conv_block(input_tensor,
+               kernel_size,
+               filters,
+               stage,
+               block,
+               strides=(2, 2)):
+    filters1, filters2, filters3 = filters
+    bn_axis = 1
+    x = Conv2D(filters1, (1, 1), strides=strides)(input_tensor)
+    x = BatchNormalization(axis=bn_axis)(x)
+    x = Activation('relu')(x)
+
+    x = Conv2D(filters2, kernel_size, padding='same')(x)
+    x = BatchNormalization(axis=bn_axis)(x)
+    x = Activation('relu')(x)
+
+    x = Conv2D(filters3, (1, 1))(x)
+    x = BatchNormalization(axis=bn_axis)(x)
+
+    shortcut = Conv2D(filters3, (1, 1), strides=strides)(input_tensor)
+    shortcut = BatchNormalization(
+        axis=bn_axis)(shortcut)
+
+    x = add([x, shortcut])
+    x = Activation('relu')(x)
+    return x
+
+
+def get_resnet50_nchw_keras():
+
+    img_input = Input(shape=(3, 224, 224))
+    bn_axis = 1
+
+    x = ZeroPadding2D((3, 3))(img_input)
+    x = Conv2D(64, (7, 7), strides=(2, 2))(x)
+    x = BatchNormalization(axis=bn_axis)(x)
+    x = Activation('relu')(x)
+    x = MaxPooling2D((3, 3), strides=(2, 2))(x)
+
+    x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1))
+    x = identity_block(x, 3, [64, 64, 256], stage=2, block='b')
+    x = identity_block(x, 3, [64, 64, 256], stage=2, block='c')
+
+    x = conv_block(x, 3, [128, 128, 512], stage=3, block='a')
+    x = identity_block(x, 3, [128, 128, 512], stage=3, block='b')
+    x = identity_block(x, 3, [128, 128, 512], stage=3, block='c')
+    x = identity_block(x, 3, [128, 128, 512], stage=3, block='d')
+
+    x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a')
+    x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b')
+    x = identity_block(x, 3, [256, 256, 1024], stage=4, block='c')
+    x = identity_block(x, 3, [256, 256, 1024], stage=4, block='d')
+    x = identity_block(x, 3, [256, 256, 1024], stage=4, block='e')
+    x = identity_block(x, 3, [256, 256, 1024], stage=4, block='f')
+
+    x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a')
+    x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b')
+    x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c')
+
+    x = AveragePooling2D((7, 7))(x)
+    x = Flatten()(x)
+    x = Dense(1000)(x)
+    x = Activation('softmax')(x)
+        
+    model = Model(img_input, x)
+
+    return model
+
+
+# def get_resnet50_nchw_keras():
+    
+#     model = ResNet50()
+    
+#     for x in model.layers:
+#         print (x.name)
+    
+#     x = model.get_layer('flatten_1').output
+#     x = Dense(1000, name='fc1000')(x)
+#     x = Activation('softmax')(x)
+    
+#     model_nchw = Model(model.input, x)
+    
+#     model_nchw.get_layer('fc1000').set_weights(model.get_layer('fc1000').get_weights())
+    
+#     return model_nchw
+
+
+def load_image(x):
+    image = cv2.imread(x)
+        
+    height, width, _ = image.shape
+    new_height = height * 256 // min(image.shape[:2])
+    new_width = width * 256 // min(image.shape[:2])
+    image = cv2.resize(image, (new_width, new_height), interpolation=cv2.INTER_CUBIC)
+    
+    height, width, _ = image.shape
+    startx = width // 2 - (224 // 2)
+    starty = height // 2 - (224 // 2)
+    image = image[starty:starty + 224, startx:startx + 224]
+    
+    image = image[:, :, ::-1]
+    image = np.transpose(image, (2, 0, 1))
+    image = preprocess_input(image.astype(np.float32), data_format=data_format)
+        
+    return image.astype(np.float32)
+
+
+
+# model = ResNet50()
+model_nchw = get_resnet50_nchw_keras()
+
+# i = 0
+# j = 0
+# for k in range(len(model_nchw.layers)):
+#     if 'pool' in model.layers[j].name or 'pad' in model.layers[j].name:
+#         j += 1
+#     elif 'pool' in model_nchw.layers[i].name or 'pad' in model_nchw.layers[i].name:
+#         i += 1
+#     else:
+#         model_nchw.layers[i].set_weights(model.layers[j].get_weights())
+#         i += 1
+#         j += 1
+        
+
+
+classes = os.listdir('/home/nz11/ILSVRC2012/train')
+train_images = glob.glob('/home/nz11/ILSVRC2012/train/*/*')
+val_images = glob.glob('/home/nz11/ILSVRC2012/val/*/*')
+val_images = sorted(val_images, key=lambda x: x.split('/')[-1].split('_')[-1].split('.')[0])
+
+idx = np.random.permutation(len(val_images))[:num_images]
+val_images = np.array(val_images)[idx]
+
+d = {k:v for v, k in enumerate(classes)}
+
+
+
+X_test = []
+for x in val_images:
+    X_test.append(load_image(x))
+X_test = np.array(X_test)    
+
+
+meta = scipy.io.loadmat("/home/nz11/ILSVRC2012/ILSVRC2012_devkit_t12/data/meta.mat")
+original_idx_to_synset = {}
+synset_to_name = {}
+
+for i in range(1000):
+    ilsvrc2012_id = int(meta["synsets"][i,0][0][0][0])
+    synset = meta["synsets"][i,0][1][0]
+    name = meta["synsets"][i,0][2][0]
+    original_idx_to_synset[ilsvrc2012_id] = synset
+    synset_to_name[synset] = name
+
+synset_to_keras_idx = {}
+keras_idx_to_name = {}
+f = open("/home/nz11/ILSVRC2012/ILSVRC2012_devkit_t12/data/synset_words.txt","r")
+c = 0
+for line in f:
+    parts = line.split(" ")
+    synset_to_keras_idx[parts[0]] = c
+    keras_idx_to_name[c] = " ".join(parts[1:])
+    c += 1
+f.close()
+
+def convert_original_idx_to_keras_idx(idx):
+    return synset_to_keras_idx[original_idx_to_synset[idx]]
+
+
+with open("/home/nz11/ILSVRC2012/ILSVRC2012_devkit_t12/data/ILSVRC2012_validation_ground_truth.txt","r") as f:
+    y_true = f.read().strip().split("\n")
+    y_true = list(map(int, y_true))
+    y_true = np.array([convert_original_idx_to_keras_idx(idx) for idx in y_true])[idx]    
+    y_true = y_true.astype(np.uint32)
+    y_true = np.expand_dims(y_true, axis=-1)
+
+
+translate_to_approxhpvm(model_nchw, "data/resnet50_imagenet/", X_test[:val_size], y_true[:val_size], 1000)
+
+dumpCalibrationData("data/resnet50_imagenet/test_input.bin", X_test, "data/resnet50_imagenet/test_labels.bin", y_true)        
+
+pred = np.argmax(model_nchw.predict(X_test), axis=1)
+print ('val accuracy', np.sum(pred == y_true.ravel()) / len(X_test))    
+
+    
\ No newline at end of file