models_VGGNet_VOC0712_SSD_300x300.tar.gz

from __future__ import print_function import caffe from caffe.model_libs import * from google.protobuf import text_format import math import os import shutil import stat import subprocess import sys # Add extra layers on top of a "base" network (e.g. VGGNet or Inception). def AddExtraLayers(net, use_batchnorm=True, lr_mult=1): use_relu = True # Add additional convolutional layers. # 19 x 19 from_layer = net.keys()[-1] # TODO(weiliu89): Construct the name using the last layer to avoid duplication. # 10 x 10 out_layer = "conv6_1" ConvBNLayer(net, from_layer, out_layer, use_batchnorm, use_relu, 256, 1, 0, 1, lr_mult=lr_mult) from_layer = out_layer out_layer = "conv6_2" ConvBNLayer(net, from_layer, out_layer, use_batchnorm, use_relu, 512, 3, 1, 2, lr_mult=lr_mult) # 5 x 5 from_layer = out_layer out_layer = "conv7_1" ConvBNLayer(net, from_layer, out_layer, use_batchnorm, use_relu, 128, 1, 0, 1, lr_mult=lr_mult) from_layer = out_layer out_layer = "conv7_2" ConvBNLayer(net, from_layer, out_layer, use_batchnorm, use_relu, 256, 3, 1, 2, lr_mult=lr_mult) # 3 x 3 from_layer = out_layer out_layer = "conv8_1" ConvBNLayer(net, from_layer, out_layer, use_batchnorm, use_relu, 128, 1, 0, 1, lr_mult=lr_mult) from_layer = out_layer out_layer = "conv8_2" ConvBNLayer(net, from_layer, out_layer, use_batchnorm, use_relu, 256, 3, 0, 1, lr_mult=lr_mult) # 1 x 1 from_layer = out_layer out_layer = "conv9_1" ConvBNLayer(net, from_layer, out_layer, use_batchnorm, use_relu, 128, 1, 0, 1, lr_mult=lr_mult) from_layer = out_layer out_layer = "conv9_2" ConvBNLayer(net, from_layer, out_layer, use_batchnorm, use_relu, 256, 3, 0, 1, lr_mult=lr_mult) return net ### Modify the following parameters accordingly ### # The directory which contains the caffe code. # We assume you are running the script at the CAFFE_ROOT. caffe_root = os.getcwd() # Set true if you want to start training right after generating all files. run_soon = True # Set true if you want to load from most recently saved snapshot. # Otherwise, we will load from the pretrain_model defined below. resume_training = True # If true, Remove old model files. remove_old_models = False # The database file for training data. Created by data/VOC0712/create_data.sh train_data = "examples/VOC0712/VOC0712_trainval_lmdb" # The database file for testing data. Created by data/VOC0712/create_data.sh test_data = "examples/VOC0712/VOC0712_test_lmdb" # Specify the batch sampler. resize_width = 300 resize_height = 300 resize = "{}x{}".format(resize_width, resize_height) batch_sampler = [ { 'sampler': { }, 'max_trials': 1, 'max_sample': 1, }, { 'sampler': { 'min_scale': 0.3, 'max_scale': 1.0, 'min_aspect_ratio': 0.5, 'max_aspect_ratio': 2.0, }, 'sample_constraint': { 'min_jaccard_overlap': 0.1, }, 'max_trials': 50, 'max_sample': 1, }, { 'sampler': { 'min_scale': 0.3, 'max_scale': 1.0, 'min_aspect_ratio': 0.5, 'max_aspect_ratio': 2.0, }, 'sample_constraint': { 'min_jaccard_overlap': 0.3, }, 'max_trials': 50, 'max_sample': 1, }, { 'sampler': { 'min_scale': 0.3, 'max_scale': 1.0, 'min_aspect_ratio': 0.5, 'max_aspect_ratio': 2.0, }, 'sample_constraint': { 'min_jaccard_overlap': 0.5, }, 'max_trials': 50, 'max_sample': 1, }, { 'sampler': { 'min_scale': 0.3, 'max_scale': 1.0, 'min_aspect_ratio': 0.5, 'max_aspect_ratio': 2.0, }, 'sample_constraint': { 'min_jaccard_overlap': 0.7, }, 'max_trials': 50, 'max_sample': 1, }, { 'sampler': { 'min_scale': 0.3, 'max_scale': 1.0, 'min_aspect_ratio': 0.5, 'max_aspect_ratio': 2.0, }, 'sample_constraint': { 'min_jaccard_overlap': 0.9, }, 'max_trials': 50, 'max_sample': 1, }, { 'sampler': { 'min_scale': 0.3, 'max_scale': 1.0, 'min_aspect_ratio': 0.5, 'max_aspect_ratio': 2.0, }, 'sample_constraint': { 'max_jaccard_overlap': 1.0, }, 'max_trials': 50, 'max_sample': 1, }, ] train_transform_param = { 'mirror': True, 'mean_value': [104, 117, 123], 'resize_param': { 'prob': 1, 'resize_mode': P.Resize.WARP, 'height': resize_height, 'width': resize_width, 'interp_mode': [ P.Resize.LINEAR, P.Resize.AREA, P.Resize.NEAREST, P.Resize.CUBIC, P.Resize.LANCZOS4, ], }, 'distort_param': { 'brightness_prob': 0.5, 'brightness_delta': 32, 'contrast_prob': 0.5, 'contrast_lower': 0.5, 'contrast_upper': 1.5, 'hue_prob': 0.5, 'hue_delta': 18, 'saturation_prob': 0.5, 'saturation_lower': 0.5, 'saturation_upper': 1.5, 'random_order_prob': 0.0, }, 'expand_param': { 'prob': 0.5, 'max_expand_ratio': 4.0, }, 'emit_constraint': { 'emit_type': caffe_pb2.EmitConstraint.CENTER, } } test_transform_param = { 'mean_value': [104, 117, 123], 'resize_param': { 'prob': 1, 'resize_mode': P.Resize.WARP, 'height': resize_height, 'width': resize_width, 'interp_mode': [P.Resize.LINEAR], }, } # If true, use batch norm for all newly added layers. # Currently only the non batch norm version has been tested. use_batchnorm = False lr_mult = 1 # Use different initial learning rate. if use_batchnorm: base_lr = 0.0004 else: # A learning rate for batch_size = 1, num_gpus = 1. base_lr = 0.00004 # Modify the job name if you want. job_name = "SSD_{}".format(resize) # The name of the model. Modify it if you want. model_name = "VGG_VOC0712_{}".format(job_name) # Directory which stores the model .prototxt file. save_dir = "models/VGGNet/VOC0712/{}".format(job_name) # Directory which stores the snapshot of models. snapshot_dir = "models/VGGNet/VOC0712/{}".format(job_name) # Directory which stores the job script and log file. job_dir = "jobs/VGGNet/VOC0712/{}".format(job_name) # Directory which stores the detection results. output_result_dir = "{}/data