.py输出中间层数据配置与过程
给出CNN_convert_bin_and_print_featuremap.py（RuyiStudio版本为2.0.28）:（见此文件放置到mobileface工程data目录下）
1 #from __future__ import print_function 2 import caffe 3 import pickle 4 from datetime import datetime 5 import numpy as np 6 import struct 7 import sys, getopt 8 import cv2, os, re 9 import pickle as p 10 import matplotlib.pyplot as pyplot 11 import ctypes 12 import codecs 13 import caffe.proto.caffe_pb2 as caffe_pb2 14 import google.protobuf as caffe_protobuf 15 import google.protobuf.text_format 16 import platform 17 18 supported_layers=[ 19 "Convolution", "Deconvolution", "Pooling", "InnerProduct", "LRN", "BatchNorm", "Scale", "Bias", "Eltwise", "ReLU", "PReLU", "AbsVal", "TanH", "Sigmoid", "BNLL", "ELU", "LSTM", "RNN", "Softmax", "Exp", "Log", "Reshape", "Flattern", "Split", "Slice", "Concat", "SPP", "Power", "Threshold", "MVN", "Parameter", "Reduction", "Proposal", "Custom", "Input", "Dropout"] 20 21 def isSupportedLayer(layer_type): 22 for type in supported_layers: 23 if(layer_type == type): 24 return True 25 return False 26 27 28 def image_to_array(img_file, shape_c_h_w, output_dir): 29 result = np.array([]) 30 print("converting begins ...") 31 resizeimage = cv2.resize(cv2.imread(img_file), (shape_c_h_w[2],shape_c_h_w[1])) 32 b,g,r = cv2.split(resizeimage ) 33 height, width, channels = resizeimage.shape 34 length = height*width 35 #print(channels ) 36 r_arr = np.array(r).reshape(length) 37 g_arr = np.array(g).reshape(length) 38 b_arr = np.array(b).reshape(length) 39 image_arr = np.concatenate((r_arr, g_arr, b_arr)) 40 result = image_arr.reshape((1, length*3)) 41 print("converting finished ...") 42 file_path = os.path.join(output_dir, "test_input_img_%d_%d_%d.bin"%(channels,height,width)) 43 with open(file_path, mode='wb') as f: 44 p.dump(result, f) 45 print("save bin file success") 46 47 def image_to_rgb(img_file,shape_c_h_w, output_dir): 48 print("converting begins ...") 49 #image = cv2.imread(img_file) 50 image = cv2.imdecode(np.fromfile(img_file, dtype=np.uint8), 1) 51 image = cv2.resize(image, (shape_c_h_w[2],shape_c_h_w[1])) 52 image = image.astype('uint8') 53 height = image.shape[0] 54 width = image.shape[1] 55 channels = image.shape[2] 56 file_path = os.path.join(output_dir, "test_input_img_%d_%d_%d.rgb"%(channels,height,width)) 57 fileSave = open(file_path,'wb') 58 for step in range(0,height): 59 for step2 in range (0, width): 60 fileSave.write(image[step,step2,2]) 61 for step in range(0,height): 62 for step2 in range (0, width): 63 fileSave.write(image[step,step2,1]) 64 for step in range(0,height): 65 for step2 in range (0, width): 66 fileSave.write(image[step,step2,0]) 67 68 fileSave.close() 69 print("converting finished ...") 70 71 def image_to_bin(img_file,shape_c_h_w, output_dir): 72 print("converting begins ...") 73 #image = cv2.imread(img_file) 74 image = cv2.imdecode(np.fromfile(img_file, dtype=np.uint8), 1) 75 image = cv2.resize(image, (shape_c_h_w[2],shape_c_h_w[1])) 76 image = image.astype('uint8') 77 height = image.shape[0] 78 width = image.shape[1] 79 channels = image.shape[2] 80 file_path = os.path.join(output_dir, "test_input_img_%d_%d_%d.bin"%(channels,height,width)) 81 fileSave = open(file_path,'wb') 82 for step in range(0,height): 83 for step2 in range (0, width): 84 fileSave.write(image[step,step2,2]) 85 for step in range(0,height): 86 for step2 in range (0, width): 87 fileSave.write(image[step,step2,1]) 88 for step in range(0,height): 89 for step2 in range (0, width): 90 fileSave.write(image[step,step2,0]) 91 92 fileSave.close() 93 print("converting finished ...") 94 95 def image_to_bgr(img_file,shape_c_h_w, output_dir): 96 print("converting begins ...") 97 #image = cv2.imread(img_file) 98 #print(shape_c_h_w[2]) 99 #print(shape_c_h_w[1]) 100 image = cv2.imdecode(np.fromfile(img_file, dtype=np.uint8), -1) 101 image = cv2.resize(image, (shape_c_h_w[2],shape_c_h_w[1])) 102 image = image.astype('uint8') 103 b,g,r = cv2.split(image) 104 height = image.shape[0] 105 width = image.shape[1] 106 channels = image.shape[2] 107 file_path = os.path.join(output_dir, "test_input_img_%d_%d_%d.bgr"%(channels,height,width)) 108 fileSave = open(file_path,'wb') 109 for step in range(0,height): 110 for step2 in range (0, width): 111 fileSave.write(b[step,step2]) 112 for step in range(0,height): 113 for step2 in range (0, width): 114 fileSave.write(g[step,step2]) 115 for step in range(0,height): 116 for step2 in range (0, width): 117 fileSave.write(r[step,step2]) 118 119 fileSave.close() 120 print("converting finished ...") 121 122 def bin_to_image(bin_file,shape_c_h_w): 123 #fileReader = open(bin_file,'rb', encoding='utf-8') 124 if(platform.system()=="Linux"): 125 fileReader = open(bin_file,'rb') 126 else: 127 fileReader = open(bin_file.encode('gbk'),'rb') 128 height = shape_c_h_w[1] 129 width = shape_c_h_w[2] 130 channel = shape_c_h_w[0] 131 imageRead = np.zeros((shape_c_h_w[1], shape_c_h_w[2], shape_c_h_w[0]), np.uint8) 132 for step in range(0,height): 133 for step2 in range (0, width): 134 a = struct.unpack("B", fileReader.read(1)) 135 imageRead[step,step2,2] = a[0] 136 for step in range(0,height): 137 for step2 in range (0, width): 138 a = struct.unpack("B", fileReader.read(1)) 139 imageRead[step,step2,1] = a[0] 140 for step in range(0,height): 141 for step2 in range (0, width): 142 a = struct.unpack("B", fileReader.read(1)) 143 imageRead[step,step2,0] = a[0] 144 fileReader.close() 145 return imageRead 146 147 def isfloat(value): 148 try: 149 float(value) 150 return True 151 except ValueError: 152 return False 153 154 155 def get_float_numbers(floatfile): 156 mat = [] 157 if(platform.system()=="Linux"): 158 with open(floatfile, 'rb') as input_file: 159 for line in input_file: 160 line = line.strip() 161 for number in line.split(): 162 if isfloat(number): 163 mat.append(float(number)) 164 else: 165 with open(floatfile.encode('gbk'), 'rb') as input_file: 166 for line in input_file: 167 line = line.strip() 168 for number in line.split(): 169 if isfloat(number): 170 mat.append(float(number)) 171 return mat 172 173 def isHex(value): 174 try: 175 int(value,16) 176 return True 177 except ValueError: 178 return False 179 180 def isHex_old(value): 181 strvalue=str(value) 182 length = len(strvalue) 183 if length == 0: 184 return False 185 i = 0 186 while(i < length): 187 if not (strvalue[i] >= 'a' and strvalue[i] <= 'e' or strvalue[i] >= 'A' and strvalue[i] <= 'E' or strvalue[i] >= '0' and strvalue[i] <= '9'): 188 return False 189 i += 1 190 return True 191 192 def get_hex_numbers(hexfile): 193 mat = [] 194 if(platform.system()=="Linux"): 195 with open(hexfile) as input_file: 196 for line in input_file: 197 line = line.strip() 198 for number in line.split(): 199 if isHex(number): 200 mat.append(1.0*ctypes.c_int32(int(number,16)).value/4096) 201 else: 202 with open(hexfile.encode("gbk")) as input_file: 203 for line in input_file: 204 line = line.strip() 205 for number in line.split(): 206 if isHex(number): 207 mat.append(1.0*ctypes.c_int32(int(number,16)).value/4096) 208 return mat 209 210 def print_CNNfeaturemap(net, output_dir): 211 params = list(net.blobs.keys()) 212 print (params) 213 for pr in params[0:]: 214 print (pr) 215 res = net.blobs[pr].data[...] 216 pr = pr.replace('/', '_') 217 pr = pr.replace('-', '_') 218 print (res.shape) 219 for index in range(0,res.shape[0]): 220 if len(res.shape) == 4: 221 filename = os.path.join(output_dir, "%s_output%d_%d_%d_%d_caffe.linear.float"%(pr,index,res.shape[1],res.shape[2],res.shape[3])) 222 elif len(res.shape) == 3: 223 filename = os.path.join(output_dir, "%s_output%d_%d_%d_caffe.linear.float"%(pr, index,res.shape[1],res.shape[2])) 224 elif len(res.shape) == 2: 225 filename = os.path.join(output_dir, "%s_output%d_%d_caffe.linear.float"%(pr,index,res.shape[1])) 226 elif len(res.shape) == 1: 227 filename = os.path.join(output_dir, "%s_output%d_caffe.linear.float"%(pr,index)) 228 f = open(filename, 'wb') 229 230 np.savetxt(f, list(res.reshape(-1, 1))) 231 232 # save result by layer name 233 def save_result(train_net, net, output_dir): 234 #logging.debug(net_param) 235 max_len = len(train_net.layer) 236 237 # input data layer 238 index = 0 239 for input in train_net.input: 240 layer_data = net.blobs[input].data[...] 241 layer_name=input.replace("/", "_") 242 layer_name=input.replace("-", "_") 243 shape_str= str(layer_data.shape) 244 shape_str=shape_str[shape_str.find(", ") + 1:].replace("(", "").replace(")", "").replace(" ", "").replace(",", "_") 245 filename = os.path.join(output_dir, "%s_output%d_%s_caffe.linear.float"%(layer_name, index, shape_str)) 246 np.savetxt(filename, layer_data.reshape(-1, 1)) 247 index = index + 1 248 # other layer 249 i = 0 250 for layer in train_net.layer: 251 index = 0 252 for top in layer.top: 253 # ignore inplace layer 254 if 1 == len(layer.top) and 1 == len(layer.bottom) and layer.top[0] == layer.bottom[0]: 255 break 256 layer_data = net.blobs[top].data[...] 257 layer_name=layer.name.replace("/", "_") 258 layer_name=layer.name.replace("-", "_") 259 shape_str= str(layer_data.shape) 260 shape_str=shape_str[shape_str.find(", ") + 1:].replace("(", "").replace(")", "").replace(" ", "").replace(",", "_") 261 filename = os.path.join(output_dir, "%s_output%d_%s_caffe.linear.float"%(layer_name, index, shape_str)) 262 np.savetxt(filename, layer_data.reshape(-1, 1)) 263 index = index + 1 264 # update the process_bar 265 i = i + 1 266 k = i * 100 / max_len 267 process_str = ">" * int(k) + " " * (100 - int(k)) 268 sys.stdout.write('\r'+ process_str +'[%s%%]'%(k)) 269 sys.stdout.flush() 270 sys.stdout.write("\n") 271 sys.stdout.flush() 272 273 def main(argv): 274 if len(argv) < 6: 275 print ('CNN_convert_bin_and_print_featuremap.py -m <model_file> -w <weight_file> -i <img_file or bin_file or float_file> -p <"104","117","123" or "ilsvrc_2012_mean.npy">') 276 print ('-m <model_file>: .prototxt, batch num should be 1') 277 print ('-w <weight_file>: .caffemodel') 278 print ('-i <img_file>: .JPEG or jpg or png or PNG or bmp or BMP') 279 print ('-i <bin_file>: test_img_$c_$h_$w.bin') 280 print ('-i <float_file>: %s_output%d_%d_%d_%d_caffe.linear.float') 281 print ('-n <norm_type>: 0(default): no process, 1: sub img-val and please give the img path in the parameter p, 2: sub channel mean value and please give each channel value in the parameter p in BGR order, 3: dividing 256, 4: sub mean image file and dividing 256, 5: sub channel mean value and dividing 256') 282 print ('-s <data_scale>: optional, if not set, 0.003906 is set by default') 283 print ('-p <"104", "117", "123" or "ilsvrc_2012_mean.npy" or "xxx.binaryproto">: -p "104", "117", "123" is sub channel-mean-val, -p "ilsvrc_2012_mean.npy" is sub img-val and need a ilsvrc_2012_mean.npy') 284 print ('-o <output_dir: optional, if not set, there will be a directory named output created in current dir>') 285 print ('-c <0 or 1> 1, gpu, 0 cpu') 286 print ('any parameter only need one input') 287 288 sys.exit(2) 289 norm_type = 0 290 data_scale = 0.003906 291 output_dir = 'output/' 292 opts, args = getopt.getopt(argv, "hm:w:i:n:s:p:o:c:") 293 cuda_flag = 0 294 for opt, arg in opts: 295 if opt == '-h': 296 print ('CNN_convert_bin_and_print_featuremap.py -m <model_file> -w <weight_file> -i <img_file or bin_file or float_file> -p <"104","117","123" or "ilsvrc_2012_mean.npy">') 297 print ('-m <model_file>: .prototxt, batch num should be 1') 298 print ('-w <weight_file>: .caffemodel') 299 print ('-i <img_file>: .JPEG or jpg or png or PNG or bmp or BMP') 300 print ('-i <bin_file>: test_img_$c_$h_$w.bin') 301 print ('-i <float_file>: %s_output%d_%d_%d_%d_caffe.linear.float') 302 print ('-n <norm_type>: 0(default): no process, 1: sub img-val and please give the img path in the parameter p, 2: sub channel mean value and please give each channel value in the parameter p in BGR order, 3: dividing 256, 4: sub mean image file and dividing 256, 5: sub channel mean value and dividing 256') 303 print ('-s <data_scale>: optional, if not set, 0.003906 is set by default') 304 print ('-p <"104", "117", "123", "ilsvrc_2012_mean.npy" or "xxx.binaryproto">: -p "104", "117", "123" is sub channel-mean-val, -p "ilsvrc_2012_mean.npy" is sub img-val and need a ilsvrc_2012_mean.npy') 305 print ('-o <output_dir: optional, if not set, there will be a directory named output created in current dir>') 306 print ('-c <0 or 1> 1, gpu, 0 cpu') 307 print ('any parameter only need one input') 308 309 sys.exit() 310 elif opt == "-m": 311 model_filename = arg 312 elif opt == "-w": 313 weight_filename = arg 314 elif opt == "-i": 315 img_filename = arg 316 elif opt == "-n": 317 norm_type = arg 318 elif opt == "-s": 319 data_scale = arg 320 elif opt == "-o": 321 output_dir = arg 322 elif opt == "-p": 323 meanfile = arg # default is to divide by 255 324 initialway = "sub mean by: " + meanfile 325 elif opt == "-c": 326 cuda_flag = arg 327 328 if('1' == cuda_flag): 329 caffe.set_mode_gpu() 330 caffe.set_device(0) 331 332 train_net = caffe_pb2.NetParameter() 333 if(platform.system()=="Linux"): 334 f=open(model_filename, 'rb') 335 else: 336 f=open(model_filename.encode('gbk'), 'rb') 337 338 train_str = f.read() 339 caffe_protobuf.text_format.Parse(train_str, train_net) 340 f.close() 341 layers = train_net.layer 342 343 for layer in layers: 344 if(False == isSupportedLayer(layer.type)): 345 print("Layer " + layer.name + " with type " + layer.type + " is not supported, please refer to chapter 3.1.4 and FAQ of \"HiSVP Development Guide.pdf\" to extend caffe!") 346 sys.exit(1) 347 print ('model file is ', model_filename) 348 print ('weight file is ', weight_filename) 349 print ('image file is ', img_filename) 350 print ('image preprocessing method is ', norm_type) # default is no process 351 print ('output dir is ', output_dir) 352 print ('data scale is ', data_scale) 353 if(platform.system()=="Linux"): 354 net = caffe.Net(model_filename, weight_filename, caffe.TEST) 355 else: 356 net = caffe.Net(model_filename.encode('gbk'), weight_filename.encode('gbk'), caffe.TEST) 357 358 print ('model load success') 359 360 if norm_type == '1' or norm_type == '4': 361 if not os.path.isfile(meanfile): 362 print("Please give the mean image file path") 363 sys.exit(1) 364 if meanfile.endswith('.binaryproto'): 365 meanfileBlob = caffe.proto.caffe_pb2.BlobProto() 366 if(platform.system()=="Linux"): 367 meanfileData = open(meanfile, 'rb').read() 368 else: 369 meanfileData = open(meanfile.encode('gbk'), 'rb').read() 370 meanfileBlob.ParseFromString(meanfileData) 371 arr = np.array(caffe.io.blobproto_to_array(meanfileBlob)) 372 out = arr[0] 373 np.save('transMean.npy', out) 374 meanfile = 'transMean.npy' 375 376 print ('model file is ', model_filename) 377 print ('weight file is ', weight_filename) 378 print ('image file is ', img_filename) 379 print ('image preprocessing method is ', norm_type) # default is no process 380 print ('output dir is ', output_dir) 381 print ('data scale is ', data_scale) 382 383 if not os.path.isdir(output_dir): 384 os.mkdir(output_dir) 385 386 if img_filename.endswith('.jpg') or img_filename.endswith('.png') or img_filename.endswith('.jpeg') or img_filename.endswith('.bmp') or img_filename.endswith('.JPEG') or img_filename.endswith('.PNG') or img_filename.endswith('.JPG') or img_filename.endswith('.BMP'): 387 388 image_to_bin(img_filename, net.blobs['data'].data.shape[1:], output_dir) 389 if net.blobs['data'].data.shape[1]==1: 390 color = False 391 elif net.blobs['data'].data.shape[1]==3: 392 image_to_rgb(img_filename, net.blobs['data'].data.shape[1:], output_dir) 393 image_to_bgr(img_filename, net.blobs['data'].data.shape[1:], output_dir) 394 color = True 395 img = cv2.imdecode(np.fromfile(img_filename, dtype=np.uint8), -1) 396 #img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) #add here 397 inputs = img 398 elif img_filename.endswith('.bin'): 399 if(platform.system()=="Linux"): 400 fbin = open(img_filename) 401 else: 402 fbin = open(img_filename.encode('gbk')) 403 data = bin_to_image(img_filename,net.blobs['data'].data.shape[1:]) 404 inputs = data 405 elif img_filename.endswith('.float'): 406 data = np.asarray(get_float_numbers(img_filename)) 407 inputs = data 408 inputs= np.reshape(inputs, net.blobs[list(net.blobs.keys())[0]].data.shape) 409 elif img_filename.endswith('.hex'): 410 data = np.asarray(get_hex_numbers(img_filename)) 411 inputs = data 412 inputs= np.reshape(inputs,net.blobs[list(net.blobs.keys())[0]].data.shape) 413 else: 414 print("errors: unknown input file!") 415 sys.exit(1) 416 417 if len(inputs): 418 transformer = caffe.io.Transformer({'data': net.blobs['data'].data.shape}) 419 if net.blobs['data'].data.shape[1]==3: 420 transformer.set_transpose('data', (2,0,1)) 421 if norm_type == '1' or norm_type == '4' and os.path.isfile(meanfile): # (sub mean by meanfile): 422 if net.blobs['data'].data.shape[1]==3: 423 transformer.set_mean('data',np.load(meanfile).mean(1).mean(1)) 424 elif net.blobs['data'].data.shape[1]==1: 425 tempMeanValue = np.load(meanfile).mean(1).mean(1) 426 tempa = list(tempMeanValue) 427 inputs = inputs - np.array(list(map(float, [tempa[0]]))) 428 elif norm_type == '2' or norm_type == '5': 429 if net.blobs['data'].data.shape[1]==3: 430 lmeanfile=meanfile.split(',') 431 if len(lmeanfile) != 3: 432 print("Please give the channel mean value in BGR order with 3 values, like 112,113,120") 433 sys.exit(1) 434 if not isfloat(lmeanfile[0]) or not isfloat(lmeanfile[1]) or not isfloat(lmeanfile[2]): 435 print("Please give the channel mean value in BGR order") 436 sys.exit(1) 437 else: 438 transformer.set_mean('data',np.array(list(map(float,re.findall(r'[-+]?\d*\.\d+|\d+',meanfile))))) 439 elif net.blobs['data'].data.shape[1]==1: 440 lmeanfile=meanfile.split(',') 441 if isfloat(lmeanfile[0]): # (sub mean by channel) 442 inputs = inputs - np.array(list(map(float, [lmeanfile[0]]))) 443 444 elif norm_type == '3': 445 inputs = inputs * float(data_scale) 446 if img_filename.endswith('.txt') or img_filename.endswith('.float') or img_filename.endswith('.hex'): 447 print (inputs.shape) 448 data = inputs 449 else: 450 data = np.asarray([transformer.preprocess('data', inputs)]) 451 if norm_type == '4' or norm_type == '5': 452 data = data * float(data_scale) 453 454 data_reshape= np.reshape(data,net.blobs[list(net.blobs.keys())[0]].data.shape) 455 net.blobs[list(net.blobs.keys())[0]].data[...] = data_reshape.astype('float') 456 out = net.forward() 457 save_result(train_net, net, output_dir) 458 #print_CNNfeaturemap(net, output_dir) 459 sys.exit(0) 460 if __name__=='__main__': 461 main(sys.argv[1:])