Pinned Repositories
Atividade-14.5-JSON-PPI2
14.5 - Requisição GET retornando um JSON
azure_analyze_sentiments_opnion_mining
azure_computer_vision
cnn_classifier
dataset: https://www.kaggle.com/datasets/likhon148/animal-data
cnn_classifier_keras
easy cnn classifier using Keras
CNN_Classifier_Pytorch
CNN using pytorch for classify vegetables
CUDA-Sankoff-AWS
deep_learning_utils
deep learning scripts
Object_detection_Faster_RCNN
teste_tecnico_node_mongo_javascript
rodrigorochag's Repositories
rodrigorochag/Atividade-14.5-JSON-PPI2
14.5 - Requisição GET retornando um JSON
rodrigorochag/azure_analyze_sentiments_opnion_mining
rodrigorochag/azure_computer_vision
rodrigorochag/cnn_classifier
dataset: https://www.kaggle.com/datasets/likhon148/animal-data
rodrigorochag/cnn_classifier_keras
easy cnn classifier using Keras
rodrigorochag/CNN_Classifier_Pytorch
CNN using pytorch for classify vegetables
rodrigorochag/CUDA-Sankoff-AWS
rodrigorochag/CUDA_Sankoff_AWS
rodrigorochag/cuda_sankoff_web_local
rodrigorochag/dcc_visualizacao_dados
TP final
rodrigorochag/deep_learning_utils
deep learning scripts
rodrigorochag/fractured_bones_classificator
rodrigorochag/instalador_cuda_sankoff
rodrigorochag/machine_learning
rodrigorochag/Object_detection_Faster_RCNN
rodrigorochag/PPGCC_visualizacao_dados
rodrigorochag/scriptsBioinfo
some basic scrips for bioinformatics
rodrigorochag/teste_tecnico_node_mongo_javascript
rodrigorochag/copilot_dio
rodrigorochag/data_mining_azure
rodrigorochag/dio-lab-open-source
⚠LEIA A ISSUE FIXADA! Repositório do lab Contribuindo em um Projeto Open Source no GitHub da Digital Innovation One.
rodrigorochag/dio_ml
rodrigorochag/image_segmentations_kmeans
K-means clustering works well when we have a small dataset. It can segment objects in images and also give better results. But when it is applied on large datasets (more number of images), it looks at all the samples in one iteration which leads to a lot of time being taken up.
rodrigorochag/Transfer-Learning-CNN
Transfer Learning CNN using IMAGENET1K_V1 weights. Using Fine Tuning standard