package models_train import ( "database/sql" "errors" "fmt" "io" "math" "os" "os/exec" "path" "sort" "strconv" "strings" "text/template" model_classes "git.andr3h3nriqu3s.com/andr3/fyp/logic/models/classes" . "git.andr3h3nriqu3s.com/andr3/fyp/logic/models/utils" . "git.andr3h3nriqu3s.com/andr3/fyp/logic/utils" "github.com/charmbracelet/log" ) const EPOCH_PER_RUN = 20 const MAX_EPOCH = 100 func shapeToSize(shape string) string { split := strings.Split(shape, ",") return strings.Join(split[:len(split)-1], ",") } func getDir() string { dir, err := os.Getwd() if err != nil { panic(err) } return dir } // This function creates a new model_definition func MakeDefenition(db *sql.DB, model_id string, target_accuracy int) (id string, err error) { id = "" rows, err := db.Query("insert into model_definition (model_id, target_accuracy) values ($1, $2) returning id;", model_id, target_accuracy) if err != nil { return } defer rows.Close() if !rows.Next() { return id, errors.New("Something wrong!") } err = rows.Scan(&id) return } func ModelDefinitionUpdateStatus(c *Context, id string, status ModelDefinitionStatus) (err error) { _, err = c.Db.Exec("update model_definition set status = $1 where id = $2", status, id) return } func UpdateStatus(c *Context, table string, id string, status int) (err error) { _, err = c.Db.Exec(fmt.Sprintf("update %s set status = $1 where id = $2", table), status, id) return } func MakeLayer(db *sql.DB, def_id string, layer_order int, layer_type LayerType, shape string) (err error) { _, err = db.Exec("insert into model_definition_layer (def_id, layer_order, layer_type, shape) values ($1, $2, $3, $4)", def_id, layer_order, layer_type, shape) return } func MakeLayerExpandable(db *sql.DB, def_id string, layer_order int, layer_type LayerType, shape string, exp_type int) (err error) { _, err = db.Exec("insert into model_definition_layer (def_id, layer_order, layer_type, shape, exp_type) values ($1, $2, $3, $4, $5)", def_id, layer_order, layer_type, shape, exp_type) return } func generateCvs(c *Context, run_path string, model_id string) (count int, err error) { var co struct { Count int `db:"count(*)"` } err = GetDBOnce(c, &co, "model_classes where model_id=$1;", model_id) if err != nil { return } count = co.Count data, err := c.Db.Query("select mdp.id, mc.class_order, mdp.file_path from model_data_point as mdp inner join model_classes as mc on mc.id = mdp.class_id where mc.model_id = $1 and mdp.model_mode=$2;", model_id, model_classes.DATA_POINT_MODE_TRAINING) if err != nil { return } defer data.Close() f, err := os.Create(path.Join(run_path, "train.csv")) if err != nil { return } defer f.Close() f.Write([]byte("Id,Index\n")) for data.Next() { var id string var class_order int var file_path string if err = data.Scan(&id, &class_order, &file_path); err != nil { return } if file_path == "id://" { f.Write([]byte(id + "," + strconv.Itoa(class_order) + "\n")) } else { return count, errors.New("TODO generateCvs to file_path " + file_path) } } return } func setModelClassStatus(c *Context, status ModelClassStatus, filter string, args ...any) (err error) { _, err = c.Db.Exec(fmt.Sprintf("update model_classes set status=%d where %s", status, filter), args...) return } func generateCvsExp(c *Context, run_path string, model_id string, doPanic bool) (count int, err error) { var co struct { Count int `db:"count(*)"` } err = GetDBOnce(c, &co, "model_classes where model_id=$1 and status=$2;", model_id, MODEL_CLASS_STATUS_TRAINING) if err != nil { return } count = co.Count if count == 0 { err = setModelClassStatus(c, MODEL_CLASS_STATUS_TRAINING, "model_id=$1 and status=$2;", model_id, MODEL_CLASS_STATUS_TO_TRAIN) if err != nil { return } if doPanic { return 0, errors.New("No model classes available") } return generateCvsExp(c, run_path, model_id, true) } data, err := c.Db.Query("select mdp.id, mc.class_order, mdp.file_path from model_data_point as mdp inner join model_classes as mc on mc.id = mdp.class_id where mc.model_id = $1 and mdp.model_mode=$2 and mc.status=$3;", model_id, model_classes.DATA_POINT_MODE_TRAINING, MODEL_CLASS_STATUS_TRAINING) if err != nil { return } defer data.Close() f, err := os.Create(path.Join(run_path, "train.csv")) if err != nil { return } defer f.Close() f.Write([]byte("Id,Index\n")) for data.Next() { var id string var class_order int var file_path string if err = data.Scan(&id, &class_order, &file_path); err != nil { return } if file_path == "id://" { f.Write([]byte(id + "," + strconv.Itoa(class_order) + "\n")) } else { return count, errors.New("TODO generateCvs to file_path " + file_path) } } return } func trainDefinition(c *Context, model *BaseModel, definition_id string, load_prev bool) (accuracy float64, err error) { c.Logger.Warn("About to start training definition") accuracy = 0 layers, err := c.Db.Query("select layer_type, shape from model_definition_layer where def_id=$1 order by layer_order asc;", definition_id) if err != nil { return } defer layers.Close() type layerrow struct { LayerType int Shape string LayerNum int } got := []layerrow{} i := 1 for layers.Next() { var row = layerrow{} if err = layers.Scan(&row.LayerType, &row.Shape); err != nil { return } row.Shape = shapeToSize(row.Shape) row.LayerNum = 1 got = append(got, row) i = i + 1 } // Generate run folder run_path := path.Join("/tmp", model.Id, "defs", definition_id) err = os.MkdirAll(run_path, os.ModePerm) if err != nil { return } classCount, err := generateCvs(c, run_path, model.Id) if err != nil { return } // Create python script f, err := os.Create(path.Join(run_path, "run.py")) if err != nil { return } defer f.Close() tmpl, err := template.New("python_model_template.py").ParseFiles("views/py/python_model_template.py") if err != nil { return } // Copy result around result_path := path.Join("savedData", model.Id, "defs", definition_id) if err = tmpl.Execute(f, AnyMap{ "Layers": got, "Size": got[0].Shape, "DataDir": path.Join(getDir(), "savedData", model.Id, "data"), "RunPath": run_path, "ColorMode": model.ImageMode, "Model": model, "EPOCH_PER_RUN": EPOCH_PER_RUN, "DefId": definition_id, "LoadPrev": load_prev, "LastModelRunPath": path.Join(getDir(), result_path, "model.keras"), "SaveModelPath": path.Join(getDir(), result_path), "Depth": classCount, "StartPoint": 0, }); err != nil { return } // Run the command out, err := exec.Command("bash", "-c", fmt.Sprintf("cd %s && python run.py", run_path)).CombinedOutput() if err != nil { c.Logger.Debug(string(out)) return } c.Logger.Info("Python finished running") if err = os.MkdirAll(result_path, os.ModePerm); err != nil { return } accuracy_file, err := os.Open(path.Join(run_path, "accuracy.val")) if err != nil { return } defer accuracy_file.Close() accuracy_file_bytes, err := io.ReadAll(accuracy_file) if err != nil { return } accuracy, err = strconv.ParseFloat(string(accuracy_file_bytes), 64) if err != nil { return } os.RemoveAll(run_path) c.Logger.Info("Model finished training!", "accuracy", accuracy) return } func generateCvsExpandExp(c *Context, run_path string, model_id string, offset int, doPanic bool) (count_re int, err error) { var co struct { Count int `db:"count(*)"` } err = GetDBOnce(c, &co, "model_classes where model_id=$1 and status=$2;", model_id, MODEL_CLASS_STATUS_TRAINING) if err != nil { return } c.Logger.Info("test here", "count", co) count_re = co.Count count := co.Count if count == 0 { err = setModelClassStatus(c, MODEL_CLASS_STATUS_TRAINING, "model_id=$1 and status=$2;", model_id, MODEL_CLASS_STATUS_TO_TRAIN) if err != nil { return } else if doPanic { return 0, errors.New("No model classes available") } return generateCvsExpandExp(c, run_path, model_id, offset, true) } data, err := c.Db.Query("select mdp.id, mc.class_order, mdp.file_path from model_data_point as mdp inner join model_classes as mc on mc.id = mdp.class_id where mc.model_id = $1 and mdp.model_mode=$2 and mc.status=$3;", model_id, model_classes.DATA_POINT_MODE_TRAINING, MODEL_CLASS_STATUS_TRAINING) if err != nil { return } defer data.Close() f, err := os.Create(path.Join(run_path, "train.csv")) if err != nil { return } defer f.Close() f.Write([]byte("Id,Index\n")) count = 0 for data.Next() { var id string var class_order int var file_path string if err = data.Scan(&id, &class_order, &file_path); err != nil { return } if file_path == "id://" { f.Write([]byte(id + "," + strconv.Itoa(class_order-offset) + "\n")) } else { return count, errors.New("TODO generateCvs to file_path " + file_path) } count += 1 } // // This is to load some extra data so that the model has more things to train on // data_other, err := c.Db.Query("select mdp.id, mc.class_order, mdp.file_path from model_data_point as mdp inner join model_classes as mc on mc.id = mdp.class_id where mc.model_id = $1 and mdp.model_mode=$2 and mc.status=$3 limit $4;", model_id, model_classes.DATA_POINT_MODE_TRAINING, MODEL_CLASS_STATUS_TRAINED, count) if err != nil { return } defer data_other.Close() for data_other.Next() { var id string var class_order int var file_path string if err = data_other.Scan(&id, &class_order, &file_path); err != nil { return } if file_path == "id://" { f.Write([]byte(id + "," + strconv.Itoa(-1) + "\n")) } else { return count, errors.New("TODO generateCvs to file_path " + file_path) } } return } func trainDefinitionExpandExp(c *Context, model *BaseModel, definition_id string, load_prev bool) (accuracy float64, err error) { accuracy = 0 c.Logger.Warn("About to retrain model") // Get untrained models heads type ExpHead struct { Id string Start int `db:"range_start"` End int `db:"range_end"` } // status = 2 (INIT) 3 (TRAINING) heads, err := GetDbMultitple[ExpHead](c, "exp_model_head where def_id=$1 and (status = 2 or status = 3)", definition_id) if err != nil { return } else if len(heads) == 0 { log.Error("Failed to get the exp head of the model") return } else if len(heads) != 1 { log.Error("This training function can only train one model at the time") err = errors.New("This training function can only train one model at the time") return } exp := heads[0] c.Logger.Info("Got exp head", "head", exp) if err = UpdateStatus(c, "exp_model_head", exp.Id, MODEL_DEFINITION_STATUS_TRAINING); err != nil { return } layers, err := c.Db.Query("select layer_type, shape, exp_type from model_definition_layer where def_id=$1 order by layer_order asc;", definition_id) if err != nil { return } defer layers.Close() type layerrow struct { LayerType int Shape string ExpType int LayerNum int } got := []layerrow{} i := 1 var last *layerrow = nil got_2 := false var first *layerrow = nil for layers.Next() { var row = layerrow{} if err = layers.Scan(&row.LayerType, &row.Shape, &row.ExpType); err != nil { return } // Keep track of the first layer so we can keep the size of the image if first == nil { first = &row } row.LayerNum = i row.Shape = shapeToSize(row.Shape) if row.ExpType == 2 { if !got_2 { got = append(got, *last) got_2 = true } got = append(got, row) } last = &row i += 1 } got = append(got, layerrow{ LayerType: LAYER_DENSE, Shape: fmt.Sprintf("%d", exp.End-exp.Start+1), ExpType: 2, LayerNum: i, }) c.Logger.Info("Got layers", "layers", got) // Generate run folder run_path := path.Join("/tmp", model.Id+"-defs-"+definition_id+"-retrain") err = os.MkdirAll(run_path, os.ModePerm) if err != nil { return } classCount, err := generateCvsExpandExp(c, run_path, model.Id, exp.Start, false) if err != nil { return } c.Logger.Info("Generated cvs", "classCount", classCount) // TODO update the run script // Create python script f, err := os.Create(path.Join(run_path, "run.py")) if err != nil { return } defer f.Close() c.Logger.Info("About to run python!") tmpl, err := template.New("python_model_template_expand.py").ParseFiles("views/py/python_model_template_expand.py") if err != nil { return } // Copy result around result_path := path.Join("savedData", model.Id, "defs", definition_id) if err = tmpl.Execute(f, AnyMap{ "Layers": got, "Size": first.Shape, "DataDir": path.Join(getDir(), "savedData", model.Id, "data"), "HeadId": exp.Id, "RunPath": run_path, "ColorMode": model.ImageMode, "Model": model, "EPOCH_PER_RUN": EPOCH_PER_RUN, "LoadPrev": load_prev, "BaseModel": path.Join(getDir(), result_path, "base", "model.keras"), "LastModelRunPath": path.Join(getDir(), result_path, "head", exp.Id, "model.keras"), "SaveModelPath": path.Join(getDir(), result_path, "head", exp.Id), "Depth": classCount, "StartPoint": 0, }); err != nil { return } // Run the command out, err := exec.Command("bash", "-c", fmt.Sprintf("cd %s && python run.py", run_path)).CombinedOutput() if err != nil { c.Logger.Warn("Python failed to run", "err", err, "out", string(out)) return } c.Logger.Info("Python finished running") if err = os.MkdirAll(result_path, os.ModePerm); err != nil { return } accuracy_file, err := os.Open(path.Join(run_path, "accuracy.val")) if err != nil { return } defer accuracy_file.Close() accuracy_file_bytes, err := io.ReadAll(accuracy_file) if err != nil { return } accuracy, err = strconv.ParseFloat(string(accuracy_file_bytes), 64) if err != nil { return } os.RemoveAll(run_path) c.Logger.Info("Model finished training!", "accuracy", accuracy) return } func trainDefinitionExp(c *Context, model *BaseModel, definition_id string, load_prev bool) (accuracy float64, err error) { accuracy = 0 c.Logger.Warn("About to start training definition") // Get untrained models heads type ExpHead struct { Id string Start int `db:"range_start"` End int `db:"range_end"` } // status = 2 (INIT) 3 (TRAINING) heads, err := GetDbMultitple[ExpHead](c, "exp_model_head where def_id=$1 and (status = 2 or status = 3)", definition_id) if err != nil { return } else if len(heads) == 0 { log.Error("Failed to get the exp head of the model") return } else if len(heads) != 1 { log.Error("This training function can only train one model at the time") err = errors.New("This training function can only train one model at the time") return } exp := heads[0] if err = UpdateStatus(c, "exp_model_head", exp.Id, MODEL_DEFINITION_STATUS_TRAINING); err != nil { return } layers, err := c.Db.Query("select layer_type, shape, exp_type from model_definition_layer where def_id=$1 order by layer_order asc;", definition_id) if err != nil { return } defer layers.Close() type layerrow struct { LayerType int Shape string ExpType int LayerNum int } got := []layerrow{} i := 1 for layers.Next() { var row = layerrow{} if err = layers.Scan(&row.LayerType, &row.Shape, &row.ExpType); err != nil { return } row.LayerNum = i row.Shape = shapeToSize(row.Shape) got = append(got, row) i += 1 } got = append(got, layerrow{ LayerType: LAYER_DENSE, Shape: fmt.Sprintf("%d", exp.End-exp.Start+1), ExpType: 2, LayerNum: i, }) // Generate run folder run_path := path.Join("/tmp", model.Id+"-defs-"+definition_id) err = os.MkdirAll(run_path, os.ModePerm) if err != nil { return } classCount, err := generateCvsExp(c, run_path, model.Id, false) if err != nil { return } // TODO update the run script // Create python script f, err := os.Create(path.Join(run_path, "run.py")) if err != nil { return } defer f.Close() tmpl, err := template.New("python_model_template.py").ParseFiles("views/py/python_model_template.py") if err != nil { return } // Copy result around result_path := path.Join("savedData", model.Id, "defs", definition_id) if err = tmpl.Execute(f, AnyMap{ "Layers": got, "Size": got[0].Shape, "DataDir": path.Join(getDir(), "savedData", model.Id, "data"), "HeadId": exp.Id, "RunPath": run_path, "ColorMode": model.ImageMode, "Model": model, "EPOCH_PER_RUN": EPOCH_PER_RUN, "LoadPrev": load_prev, "LastModelRunPath": path.Join(getDir(), result_path, "model.keras"), "SaveModelPath": path.Join(getDir(), result_path), "Depth": classCount, "StartPoint": 0, }); err != nil { return } // Run the command out, err := exec.Command("bash", "-c", fmt.Sprintf("cd %s && python run.py", run_path)).CombinedOutput() if err != nil { c.Logger.Debug(string(out)) return } c.Logger.Info("Python finished running") if err = os.MkdirAll(result_path, os.ModePerm); err != nil { return } accuracy_file, err := os.Open(path.Join(run_path, "accuracy.val")) if err != nil { return } defer accuracy_file.Close() accuracy_file_bytes, err := io.ReadAll(accuracy_file) if err != nil { return } accuracy, err = strconv.ParseFloat(string(accuracy_file_bytes), 64) if err != nil { return } os.RemoveAll(run_path) c.Logger.Info("Model finished training!", "accuracy", accuracy) return } func remove[T interface{}](lst []T, i int) []T { lng := len(lst) if i >= lng { return []T{} } if i+1 >= lng { return lst[:lng-1] } if i == 0 { return lst[1:] } return append(lst[:i], lst[i+1:]...) } type TrainModelRow struct { id string target_accuracy int epoch int acuracy float64 } type TraingModelRowDefinitions []TrainModelRow func (nf TraingModelRowDefinitions) Len() int { return len(nf) } func (nf TraingModelRowDefinitions) Swap(i, j int) { nf[i], nf[j] = nf[j], nf[i] } func (nf TraingModelRowDefinitions) Less(i, j int) bool { return nf[i].acuracy < nf[j].acuracy } type ToRemoveList []int func (nf ToRemoveList) Len() int { return len(nf) } func (nf ToRemoveList) Swap(i, j int) { nf[i], nf[j] = nf[j], nf[i] } func (nf ToRemoveList) Less(i, j int) bool { return nf[i] < nf[j] } func trainModel(c *Context, model *BaseModel) { definitionsRows, err := c.Db.Query("select id, target_accuracy, epoch from model_definition where status=$1 and model_id=$2", MODEL_DEFINITION_STATUS_INIT, model.Id) if err != nil { c.Logger.Error("Failed to train Model! Err:") c.Logger.Error(err) ModelUpdateStatus(c, model.Id, FAILED_TRAINING) return } defer definitionsRows.Close() var definitions TraingModelRowDefinitions = []TrainModelRow{} for definitionsRows.Next() { var rowv TrainModelRow rowv.acuracy = 0 if err = definitionsRows.Scan(&rowv.id, &rowv.target_accuracy, &rowv.epoch); err != nil { c.Logger.Error("Failed to train Model Could not read definition from db!Err:") c.Logger.Error(err) ModelUpdateStatus(c, model.Id, FAILED_TRAINING) return } definitions = append(definitions, rowv) } if len(definitions) == 0 { c.Logger.Error("No Definitions defined!") ModelUpdateStatus(c, model.Id, FAILED_TRAINING) return } firstRound := true finished := false for { var toRemove ToRemoveList = []int{} for i, def := range definitions { ModelDefinitionUpdateStatus(c, def.id, MODEL_DEFINITION_STATUS_TRAINING) accuracy, err := trainDefinition(c, model, def.id, !firstRound) if err != nil { c.Logger.Error("Failed to train definition!Err:", "err", err) ModelDefinitionUpdateStatus(c, def.id, MODEL_DEFINITION_STATUS_FAILED_TRAINING) toRemove = append(toRemove, i) continue } def.epoch += EPOCH_PER_RUN accuracy = accuracy * 100 def.acuracy = float64(accuracy) definitions[i].epoch += EPOCH_PER_RUN definitions[i].acuracy = accuracy if accuracy >= float64(def.target_accuracy) { c.Logger.Info("Found a definition that reaches target_accuracy!") _, err = c.Db.Exec("update model_definition set accuracy=$1, status=$2, epoch=$3 where id=$4", accuracy, MODEL_DEFINITION_STATUS_TRANIED, def.epoch, def.id) if err != nil { c.Logger.Error("Failed to train definition!Err:\n", "err", err) ModelUpdateStatus(c, model.Id, FAILED_TRAINING) return } _, err = c.Db.Exec("update model_definition set status=$1 where id!=$2 and model_id=$3 and status!=$4", MODEL_DEFINITION_STATUS_CANCELD_TRAINING, def.id, model.Id, MODEL_DEFINITION_STATUS_FAILED_TRAINING) if err != nil { c.Logger.Error("Failed to train definition!Err:\n", "err", err) ModelUpdateStatus(c, model.Id, FAILED_TRAINING) return } finished = true break } if def.epoch > MAX_EPOCH { fmt.Printf("Failed to train definition! Accuracy less %f < %d\n", accuracy, def.target_accuracy) ModelDefinitionUpdateStatus(c, def.id, MODEL_DEFINITION_STATUS_FAILED_TRAINING) toRemove = append(toRemove, i) continue } _, err = c.Db.Exec("update model_definition set accuracy=$1, epoch=$2, status=$3 where id=$4", accuracy, def.epoch, MODEL_DEFINITION_STATUS_PAUSED_TRAINING, def.id) if err != nil { c.Logger.Error("Failed to train definition!Err:\n", "err", err) ModelUpdateStatus(c, model.Id, FAILED_TRAINING) return } } firstRound = false if finished { break } sort.Sort(sort.Reverse(toRemove)) c.Logger.Info("Round done", "toRemove", toRemove) for _, n := range toRemove { definitions = remove(definitions, n) } len_def := len(definitions) if len_def == 0 { break } if len_def == 1 { continue } sort.Sort(sort.Reverse(definitions)) acc := definitions[0].acuracy - 20.0 c.Logger.Info("Training models, Highest acc", "acc", definitions[0].acuracy, "mod_acc", acc) toRemove = []int{} for i, def := range definitions { if def.acuracy < acc { toRemove = append(toRemove, i) } } c.Logger.Info("Removing due to accuracy", "toRemove", toRemove) sort.Sort(sort.Reverse(toRemove)) for _, n := range toRemove { c.Logger.Warn("Removing definition not fast enough learning", "n", n) ModelDefinitionUpdateStatus(c, definitions[n].id, MODEL_DEFINITION_STATUS_FAILED_TRAINING) definitions = remove(definitions, n) } } rows, err := c.Db.Query("select id from model_definition where model_id=$1 and status=$2 order by accuracy desc limit 1;", model.Id, MODEL_DEFINITION_STATUS_TRANIED) if err != nil { c.Logger.Error("DB: failed to read definition") c.Logger.Error(err) ModelUpdateStatus(c, model.Id, FAILED_TRAINING) return } defer rows.Close() if !rows.Next() { // TODO Make the Model status have a message c.Logger.Error("All definitions failed to train!") ModelUpdateStatus(c, model.Id, FAILED_TRAINING) return } var id string if err = rows.Scan(&id); err != nil { c.Logger.Error("Failed to read id:") c.Logger.Error(err) ModelUpdateStatus(c, model.Id, FAILED_TRAINING) return } if _, err = c.Db.Exec("update model_definition set status=$1 where id=$2;", MODEL_DEFINITION_STATUS_READY, id); err != nil { c.Logger.Error("Failed to update model definition") c.Logger.Error(err) ModelUpdateStatus(c, model.Id, FAILED_TRAINING) return } to_delete, err := c.Db.Query("select id from model_definition where status != $1 and model_id=$2", MODEL_DEFINITION_STATUS_READY, model.Id) if err != nil { c.Logger.Error("Failed to select model_definition to delete") c.Logger.Error(err) ModelUpdateStatus(c, model.Id, FAILED_TRAINING) return } defer to_delete.Close() for to_delete.Next() { var id string if err = to_delete.Scan(&id); err != nil { c.Logger.Error("Failed to scan the id of a model_definition to delete") c.Logger.Error(err) ModelUpdateStatus(c, model.Id, FAILED_TRAINING) return } os.RemoveAll(path.Join("savedData", model.Id, "defs", id)) } // TODO Check if returning also works here if _, err = c.Db.Exec("delete from model_definition where status!=$1 and model_id=$2;", MODEL_DEFINITION_STATUS_READY, model.Id); err != nil { c.Logger.Error("Failed to delete model_definition") c.Logger.Error(err) ModelUpdateStatus(c, model.Id, FAILED_TRAINING) return } ModelUpdateStatus(c, model.Id, READY) } type TrainModelRowUsable struct { Id string TargetAccuracy int `db:"target_accuracy"` Epoch int Acuracy float64 `db:"0"` } type TrainModelRowUsables []*TrainModelRowUsable func (nf TrainModelRowUsables) Len() int { return len(nf) } func (nf TrainModelRowUsables) Swap(i, j int) { nf[i], nf[j] = nf[j], nf[i] } func (nf TrainModelRowUsables) Less(i, j int) bool { return nf[i].Acuracy < nf[j].Acuracy } func trainModelExp(c *Context, model *BaseModel) { var err error = nil failed := func(msg string) { c.Logger.Error(msg, "err", err) ModelUpdateStatus(c, model.Id, FAILED_TRAINING) } var definitions TrainModelRowUsables definitions, err = GetDbMultitple[TrainModelRowUsable](c, "model_definition where status=$1 and model_id=$2", MODEL_DEFINITION_STATUS_INIT, model.Id) if err != nil { failed("Failed to get definitions") return } if len(definitions) == 0 { failed("No Definitions defined!") return } firstRound := true finished := false for { var toRemove ToRemoveList = []int{} for i, def := range definitions { ModelDefinitionUpdateStatus(c, def.Id, MODEL_DEFINITION_STATUS_TRAINING) accuracy, err := trainDefinitionExp(c, model, def.Id, !firstRound) if err != nil { c.Logger.Error("Failed to train definition!Err:", "err", err) ModelDefinitionUpdateStatus(c, def.Id, MODEL_DEFINITION_STATUS_FAILED_TRAINING) toRemove = append(toRemove, i) continue } def.Epoch += EPOCH_PER_RUN accuracy = accuracy * 100 def.Acuracy = float64(accuracy) definitions[i].Epoch += EPOCH_PER_RUN definitions[i].Acuracy = accuracy if accuracy >= float64(def.TargetAccuracy) { c.Logger.Info("Found a definition that reaches target_accuracy!") _, err = c.Db.Exec("update model_definition set accuracy=$1, status=$2, epoch=$3 where id=$4", accuracy, MODEL_DEFINITION_STATUS_TRANIED, def.Epoch, def.Id) if err != nil { failed("Failed to train definition!") return } _, err = c.Db.Exec("update model_definition set status=$1 where id!=$2 and model_id=$3 and status!=$4", MODEL_DEFINITION_STATUS_CANCELD_TRAINING, def.Id, model.Id, MODEL_DEFINITION_STATUS_FAILED_TRAINING) if err != nil { failed("Failed to train definition!") return } _, err = c.Db.Exec("update exp_model_head set status=$1 where def_id=$2;", MODEL_HEAD_STATUS_READY, def.Id) if err != nil { failed("Failed to train definition!") return } finished = true break } if def.Epoch > MAX_EPOCH { fmt.Printf("Failed to train definition! Accuracy less %f < %d\n", accuracy, def.TargetAccuracy) ModelDefinitionUpdateStatus(c, def.Id, MODEL_DEFINITION_STATUS_FAILED_TRAINING) toRemove = append(toRemove, i) continue } _, err = c.Db.Exec("update model_definition set accuracy=$1, epoch=$2, status=$3 where id=$4", accuracy, def.Epoch, MODEL_DEFINITION_STATUS_PAUSED_TRAINING, def.Id) if err != nil { failed("Failed to train definition!") return } } firstRound = false if finished { break } sort.Sort(sort.Reverse(toRemove)) c.Logger.Info("Round done", "toRemove", toRemove) for _, n := range toRemove { definitions = remove(definitions, n) } len_def := len(definitions) if len_def == 0 { break } else if len_def == 1 { continue } sort.Sort(sort.Reverse(definitions)) acc := definitions[0].Acuracy - 20.0 c.Logger.Info("Training models, Highest acc", "acc", definitions[0].Acuracy, "mod_acc", acc) toRemove = []int{} for i, def := range definitions { if def.Acuracy < acc { toRemove = append(toRemove, i) } } c.Logger.Info("Removing due to accuracy", "toRemove", toRemove) sort.Sort(sort.Reverse(toRemove)) for _, n := range toRemove { c.Logger.Warn("Removing definition not fast enough learning", "n", n) ModelDefinitionUpdateStatus(c, definitions[n].Id, MODEL_DEFINITION_STATUS_FAILED_TRAINING) definitions = remove(definitions, n) } } var dat JustId err = GetDBOnce(c, &dat, "model_definition where model_id=$1 and status=$2 order by accuracy desc limit 1;", model.Id, MODEL_DEFINITION_STATUS_TRANIED) if err == NotFoundError { // Set the class status to trained err = setModelClassStatus(c, MODEL_CLASS_STATUS_TO_TRAIN, "model_id=$1 and status=$2;", model.Id, MODEL_CLASS_STATUS_TRAINING) if err != nil { failed("All definitions failed to train! And Failed to set class status") return } failed("All definitions failed to train!") return } else if err != nil { failed("DB: failed to read definition") return } if _, err = c.Db.Exec("update model_definition set status=$1 where id=$2;", MODEL_DEFINITION_STATUS_READY, dat.Id); err != nil { failed("Failed to update model definition") return } to_delete, err := GetDbMultitple[JustId](c, "model_definition where status!=$1 and model_id=$2", MODEL_DEFINITION_STATUS_READY, model.Id) if err != nil { failed("Failed to select model_definition to delete") return } for _, d := range to_delete { os.RemoveAll(path.Join("savedData", model.Id, "defs", d.Id)) } // TODO Check if returning also works here if _, err = c.Db.Exec("delete from model_definition where status!=$1 and model_id=$2;", MODEL_DEFINITION_STATUS_READY, model.Id); err != nil { failed("Failed to delete model_definition") return } if err = splitModel(c, model); err != nil { err = setModelClassStatus(c, MODEL_CLASS_STATUS_TO_TRAIN, "model_id=$1 and status=$2;", model.Id, MODEL_CLASS_STATUS_TRAINING) if err != nil { failed("Failed to split the model! And Failed to set class status") return } failed("Failed to split the model") return } // Set the class status to trained err = setModelClassStatus(c, MODEL_CLASS_STATUS_TRAINED, "model_id=$1 and status=$2;", model.Id, MODEL_CLASS_STATUS_TRAINING) if err != nil { failed("Failed to set class status") return } // There should only be one def availabale def := JustId{} if err = GetDBOnce(c, &def, "model_definition where model_id=$1", model.Id); err != nil { return } // Remove the base model c.Logger.Warn("Removing base model for", "model", model.Id, "def", def.Id) os.RemoveAll(path.Join("savedData", model.Id, "defs", def.Id, "model")) os.RemoveAll(path.Join("savedData", model.Id, "defs", def.Id, "model.keras")) ModelUpdateStatus(c, model.Id, READY) } func splitModel(c *Context, model *BaseModel) (err error) { def := JustId{} if err = GetDBOnce(c, &def, "model_definition where model_id=$1", model.Id); err != nil { return } head := JustId{} if err = GetDBOnce(c, &head, "exp_model_head where def_id=$1", def.Id); err != nil { return } // Generate run folder run_path := path.Join("/tmp", model.Id+"-defs-"+def.Id+"-split") err = os.MkdirAll(run_path, os.ModePerm) if err != nil { return } // Create python script f, err := os.Create(path.Join(run_path, "run.py")) if err != nil { return } defer f.Close() tmpl, err := template.New("python_split_model_template.py").ParseFiles("views/py/python_split_model_template.py") if err != nil { return } // Copy result around result_path := path.Join(getDir(), "savedData", model.Id, "defs", def.Id) // TODO maybe move this to a select count(*) // Get only fixed lawers layers, err := c.Db.Query("select exp_type from model_definition_layer where def_id=$1 and exp_type=$2 order by layer_order asc;", def.Id, 1) if err != nil { return } defer layers.Close() type layerrow struct { ExpType int } count := -1 for layers.Next() { count += 1 } if count == -1 { err = errors.New("Can not get layers") return } log.Warn("Spliting model", "def", def.Id, "head", head.Id, "count", count) basePath := path.Join(result_path, "base") headPath := path.Join(result_path, "head", head.Id) if err = os.MkdirAll(basePath, os.ModePerm); err != nil { return } if err = os.MkdirAll(headPath, os.ModePerm); err != nil { return } if err = tmpl.Execute(f, AnyMap{ "SplitLen": count, "ModelPath": path.Join(result_path, "model.keras"), "BaseModelPath": basePath, "HeadModelPath": headPath, }); err != nil { return } out, err := exec.Command("bash", "-c", fmt.Sprintf("cd %s && python run.py", run_path)).CombinedOutput() if err != nil { c.Logger.Debug(string(out)) return } os.RemoveAll(run_path) c.Logger.Info("Python finished running") return } func removeFailedDataPoints(c *Context, model *BaseModel) (err error) { rows, err := c.Db.Query("select mdp.id from model_data_point as mdp join model_classes as mc on mc.id=mdp.class_id where mc.model_id=$1 and mdp.status=-1;", model.Id) if err != nil { return } defer rows.Close() base_path := path.Join("savedData", model.Id, "data") for rows.Next() { var dataPointId string err = rows.Scan(&dataPointId) if err != nil { return } p := path.Join(base_path, dataPointId+"."+model.Format) c.Logger.Warn("Removing image", "path", p) err = os.RemoveAll(p) if err != nil { return } } _, err = c.Db.Exec("delete from model_data_point as mdp using model_classes as mc where mdp.class_id = mc.id and mc.model_id=$1 and mdp.status=-1;", model.Id) return } // This generates a definition func generateDefinition(c *Context, model *BaseModel, target_accuracy int, number_of_classes int, complexity int) *Error { var err error = nil failed := func() *Error { ModelUpdateStatus(c, model.Id, FAILED_PREPARING_TRAINING) // TODO improve this response return c.Error500(err) } def_id, err := MakeDefenition(c.Db, model.Id, target_accuracy) if err != nil { return failed() } order := 1 // Note the shape of the first layer defines the import size if complexity == 2 { // Note the shape for now is no used width := int(math.Pow(2, math.Floor(math.Log(float64(model.Width))/math.Log(2.0)))) height := int(math.Pow(2, math.Floor(math.Log(float64(model.Height))/math.Log(2.0)))) c.Logger.Warn("Complexity 2 creating model with smaller size", "width", width, "height", height) err = MakeLayer(c.Db, def_id, order, LAYER_INPUT, fmt.Sprintf("%d,%d,1", width, height)) if err != nil { return failed() } order++ } else { err = MakeLayer(c.Db, def_id, order, LAYER_INPUT, fmt.Sprintf("%d,%d,1", model.Width, model.Height)) if err != nil { return failed() } order++ } if complexity == 0 { err = MakeLayer(c.Db, def_id, order, LAYER_FLATTEN, "") if err != nil { return failed() } order++ loop := int(math.Log2(float64(number_of_classes))) for i := 0; i < loop; i++ { err = MakeLayer(c.Db, def_id, order, LAYER_DENSE, fmt.Sprintf("%d,1", number_of_classes*(loop-i))) order++ if err != nil { ModelUpdateStatus(c, model.Id, FAILED_PREPARING_TRAINING) // TODO improve this response return c.Error500(err) } } } else if complexity == 1 || complexity == 2 { loop := int((math.Log(float64(model.Width)) / math.Log(float64(10)))) if loop == 0 { loop = 1 } for i := 0; i < loop; i++ { err = MakeLayer(c.Db, def_id, order, LAYER_SIMPLE_BLOCK, "") order++ if err != nil { return failed() } } err = MakeLayer(c.Db, def_id, order, LAYER_FLATTEN, "") if err != nil { return failed() } order++ loop = int((math.Log(float64(number_of_classes)) / math.Log(float64(10))) / 2) if loop == 0 { loop = 1 } for i := 0; i < loop; i++ { err = MakeLayer(c.Db, def_id, order, LAYER_DENSE, fmt.Sprintf("%d,1", number_of_classes*(loop-i))) order++ if err != nil { return failed() } } } else { c.Logger.Error("Unkown complexity", "complexity", complexity) return failed() } err = ModelDefinitionUpdateStatus(c, def_id, MODEL_DEFINITION_STATUS_INIT) if err != nil { return failed() } return nil } func generateDefinitions(c *Context, model *BaseModel, target_accuracy int, number_of_models int) *Error { cls, err := model_classes.ListClasses(c, model.Id) if err != nil { ModelUpdateStatus(c, model.Id, FAILED_PREPARING_TRAINING) // TODO improve this response return c.Error500(err) } err = removeFailedDataPoints(c, model) if err != nil { return c.Error500(err) } cls_len := len(cls) if number_of_models == 1 { if model.Width < 100 && model.Height < 100 && cls_len < 30 { generateDefinition(c, model, target_accuracy, cls_len, 0) } else if model.Width > 100 && model.Height > 100 { generateDefinition(c, model, target_accuracy, cls_len, 2) } else { generateDefinition(c, model, target_accuracy, cls_len, 1) } } else if number_of_models == 3 { for i := 0; i < number_of_models; i++ { generateDefinition(c, model, target_accuracy, cls_len, i) } } else { // TODO handle incrisea the complexity for i := 0; i < number_of_models; i++ { generateDefinition(c, model, target_accuracy, cls_len, 0) } } return nil } func CreateExpModelHead(c *Context, def_id string, range_start int, range_end int, status ModelDefinitionStatus) (id string, err error) { rows, err := c.Db.Query("insert into exp_model_head (def_id, range_start, range_end, status) values ($1, $2, $3, $4) returning id", def_id, range_start, range_end, status) if err != nil { return } defer rows.Close() if !rows.Next() { c.Logger.Error("Could not get status of model definition") err = errors.New("Could not get status of model definition") return } err = rows.Scan(&id) if err != nil { return } return } func ExpModelHeadUpdateStatus(db *sql.DB, id string, status ModelDefinitionStatus) (err error) { _, err = db.Exec("update model_definition set status = $1 where id = $2", status, id) return } // This generates a definition func generateExpandableDefinition(c *Context, model *BaseModel, target_accuracy int, number_of_classes int, complexity int) *Error { c.Logger.Info("Generating expandable new definition for model", "id", model.Id, "complexity", complexity) var err error = nil failed := func() *Error { ModelUpdateStatus(c, model.Id, FAILED_PREPARING_TRAINING) // TODO improve this response return c.Error500(err) } if complexity == 0 { return failed() } def_id, err := MakeDefenition(c.Db, model.Id, target_accuracy) if err != nil { return failed() } order := 1 width := model.Width height := model.Height // Note the shape of the first layer defines the import size if complexity == 2 { // Note the shape for now is no used width := int(math.Pow(2, math.Floor(math.Log(float64(model.Width))/math.Log(2.0)))) height := int(math.Pow(2, math.Floor(math.Log(float64(model.Height))/math.Log(2.0)))) c.Logger.Warn("Complexity 2 creating model with smaller size", "width", width, "height", height) } err = MakeLayerExpandable(c.Db, def_id, order, LAYER_INPUT, fmt.Sprintf("%d,%d,1", width, height), 1) order++ // handle the errors inside the pervious if block if err != nil { return failed() } // Create the blocks loop := int((math.Log(float64(model.Width)) / math.Log(float64(10)))) if model.Width < 50 && model.Height < 50 { loop = 0 } log.Info("Size of the simple block", "loop", loop) //loop = max(loop, 3) for i := 0; i < loop; i++ { err = MakeLayerExpandable(c.Db, def_id, order, LAYER_SIMPLE_BLOCK, "", 1) order++ if err != nil { return failed() } } // Flatten the blocks into dense err = MakeLayerExpandable(c.Db, def_id, order, LAYER_FLATTEN, "", 1) if err != nil { return failed() } order++ // Flatten the blocks into dense err = MakeLayerExpandable(c.Db, def_id, order, LAYER_DENSE, fmt.Sprintf("%d,1", number_of_classes*2), 1) if err != nil { return failed() } order++ loop = int((math.Log(float64(number_of_classes)) / math.Log(float64(10))) / 2) log.Info("Size of the dense layers", "loop", loop) // loop = max(loop, 3) for i := 0; i < loop; i++ { err = MakeLayer(c.Db, def_id, order, LAYER_DENSE, fmt.Sprintf("%d,1", number_of_classes*(loop-i))) order++ if err != nil { return failed() } } _, err = CreateExpModelHead(c, def_id, 0, number_of_classes-1, MODEL_DEFINITION_STATUS_INIT) if err != nil { return failed() } err = ModelDefinitionUpdateStatus(c, def_id, MODEL_DEFINITION_STATUS_INIT) if err != nil { return failed() } return nil } // TODO make this json friendy func generateExpandableDefinitions(c *Context, model *BaseModel, target_accuracy int, number_of_models int) *Error { cls, err := model_classes.ListClasses(c, model.Id) if err != nil { ModelUpdateStatus(c, model.Id, FAILED_PREPARING_TRAINING) // TODO improve this response return c.Error500(err) } err = removeFailedDataPoints(c, model) if err != nil { return c.Error500(err) } cls_len := len(cls) if number_of_models == 1 { if model.Width > 100 && model.Height > 100 { generateExpandableDefinition(c, model, target_accuracy, cls_len, 2) } else { generateExpandableDefinition(c, model, target_accuracy, cls_len, 1) } } else if number_of_models == 3 { for i := 0; i < number_of_models; i++ { generateExpandableDefinition(c, model, target_accuracy, cls_len, i) } } else { // TODO handle incrisea the complexity for i := 0; i < number_of_models; i++ { generateExpandableDefinition(c, model, target_accuracy, cls_len, 1) } } return nil } func ResetClasses(c *Context, model *BaseModel) { _, err := c.Db.Exec("update model_classes set status=$1 where status=$2 and model_id=$3", MODEL_CLASS_STATUS_TO_TRAIN, MODEL_CLASS_STATUS_TRAINING, model.Id) if err != nil { c.Logger.Error("Error while reseting the classes", "error", err) } } func trainExpandable(c *Context, model *BaseModel) { var err error = nil failed := func(msg string) { c.Logger.Error(msg, "err", err) ModelUpdateStatus(c, model.Id, FAILED_TRAINING) ResetClasses(c, model) } var definitions TrainModelRowUsables definitions, err = GetDbMultitple[TrainModelRowUsable](c, "model_definition where status=$1 and model_id=$2", MODEL_DEFINITION_STATUS_READY, model.Id) if err != nil { failed("Failed to get definitions") return } if len(definitions) != 1 { failed("There should only be one definition available!") return } firstRound := true def := definitions[0] epoch := 0 for { acc, err := trainDefinitionExp(c, model, def.Id, !firstRound) if err != nil { failed("Failed to train definition!") return } epoch += EPOCH_PER_RUN if float64(acc*100) >= float64(def.Acuracy) { c.Logger.Info("Found a definition that reaches target_accuracy!") _, err = c.Db.Exec("update exp_model_head set status=$1 where def_id=$2 and status=$3;", MODEL_HEAD_STATUS_READY, def.Id, MODEL_HEAD_STATUS_TRAINING) if err != nil { failed("Failed to train definition!") return } break } else if def.Epoch > MAX_EPOCH { failed(fmt.Sprintf("Failed to train definition! Accuracy less %f < %d\n", acc*100, def.TargetAccuracy)) return } } // Set the class status to trained err = setModelClassStatus(c, MODEL_CLASS_STATUS_TRAINED, "model_id=$1 and status=$2;", model.Id, MODEL_CLASS_STATUS_TRAINING) if err != nil { failed("Failed to set class status") return } ModelUpdateStatus(c, model.Id, READY) } func trainRetrain(c *Context, model *BaseModel, defId string) { var err error failed := func() { ResetClasses(c, model) ModelUpdateStatus(c, model.Id, READY_RETRAIN_FAILED) c.Logger.Error("Failed to retrain", "err", err) return } // This is something I have to check acc, err := trainDefinitionExpandExp(c, model, defId, false) if err != nil { c.Logger.Error("Failed to retrain the model", "err", err) failed() return } c.Logger.Info("Retrained model", "accuracy", acc) // TODO check accuracy err = UpdateStatus(c, "models", model.Id, READY) if err != nil { failed() return } c.Logger.Info("model updaded") _, err = c.Db.Exec("update model_classes set status=$1 where status=$2 and model_id=$3", MODEL_CLASS_STATUS_TRAINED, MODEL_CLASS_STATUS_TRAINING, model.Id) if err != nil { c.Logger.Error("Error while updating the classes", "error", err) failed() return } } func handleRetrain(c *Context) *Error { var err error = nil if !c.CheckAuthLevel(1) { return nil } var dat JustId if err_ := c.ToJSON(&dat); err_ != nil { return err_ } if dat.Id == "" { return c.JsonBadRequest("Please provide a id") } model, err := GetBaseModel(c.Db, dat.Id) if err == ModelNotFoundError { return c.JsonBadRequest("Model not found") } else if err != nil { return c.Error500(err) } else if model.Status != READY && model.Status != READY_RETRAIN_FAILED && model.Status != READY_ALTERATION_FAILED { return c.JsonBadRequest("Model in invalid status for re-training") } c.Logger.Info("Expanding definitions for models", "id", model.Id) classesUpdated := false failed := func() *Error { if classesUpdated { ResetClasses(c, model) } ModelUpdateStatus(c, model.Id, READY_RETRAIN_FAILED) c.Logger.Error("Failed to retrain", "err", err) // TODO improve this response return c.Error500(err) } var def struct { Id string TargetAccuracy int `db:"target_accuracy"` } err = GetDBOnce(c, &def, "model_definition where model_id=$1;", model.Id) if err != nil { return failed() } type C struct { Id string ClassOrder int `db:"class_order"` } err = c.StartTx() if err != nil { return failed() } classes, err := GetDbMultitple[C]( c, "model_classes where model_id=$1 and status=$2 order by class_order asc", model.Id, MODEL_CLASS_STATUS_TO_TRAIN, ) if err != nil { _err := c.RollbackTx() if _err != nil { c.Logger.Error("Two errors happended rollback failed", "err", _err) } return failed() } if len(classes) == 0 { c.Logger.Error("No classes are available!") _err := c.RollbackTx() if _err != nil { c.Logger.Error("Two errors happended rollback failed", "err", _err) } return failed() } //Update the classes { stmt, err2 := c.Prepare("update model_classes set status=$1 where status=$2 and model_id=$3") err = err2 if err != nil { _err := c.RollbackTx() if _err != nil { c.Logger.Error("Two errors happended rollback failed", "err", _err) } return failed() } defer stmt.Close() _, err = stmt.Exec(MODEL_CLASS_STATUS_TRAINING, MODEL_CLASS_STATUS_TO_TRAIN, model.Id) if err != nil { _err := c.RollbackTx() if _err != nil { c.Logger.Error("Two errors happended rollback failed", "err", _err) } return failed() } err = c.CommitTx() if err != nil { _err := c.RollbackTx() if _err != nil { c.Logger.Error("Two errors happended rollback failed", "err", _err) } return failed() } classesUpdated = true } _, err = CreateExpModelHead(c, def.Id, classes[0].ClassOrder, classes[len(classes)-1].ClassOrder, MODEL_DEFINITION_STATUS_INIT) if err != nil { return failed() } go trainRetrain(c, model, def.Id) _, err = c.Db.Exec("update models set status=$1 where id=$2;", READY_RETRAIN, model.Id) if err != nil { fmt.Println("Failed to update model status") fmt.Println(err) // TODO improve this response return c.Error500(err) } return c.SendJSON(model.Id) } func handleTrain(handle *Handle) { handle.Post("/models/train", func(c *Context) *Error { if !c.CheckAuthLevel(1) { return nil } var dat struct { Id string `json:"id"` ModelType string `json:"model_type"` NumberOfModels int `json:"number_of_models"` Accuracy int `json:"accuracy"` } if err_ := c.ToJSON(&dat); err_ != nil { return err_ } if dat.Id == "" { return c.JsonBadRequest("Please provide a id") } modelTypeId := 1 if dat.ModelType == "expandable" { modelTypeId = 2 } else if dat.ModelType != "simple" { return c.JsonBadRequest("Invalid model type!") } model, err := GetBaseModel(c.Db, dat.Id) if err == ModelNotFoundError { return c.JsonBadRequest("Model not found") } else if err != nil { return c.Error500(err) } if model.Status != CONFIRM_PRE_TRAINING { return c.JsonBadRequest("Model in invalid status for training") } if modelTypeId == 2 { full_error := generateExpandableDefinitions(c, model, dat.Accuracy, dat.NumberOfModels) if full_error != nil { return full_error } } else { full_error := generateDefinitions(c, model, dat.Accuracy, dat.NumberOfModels) if full_error != nil { return full_error } } if modelTypeId == 2 { go trainModelExp(c, model) } else { go trainModel(c, model) } _, err = c.Db.Exec("update models set status = $1, model_type = $2 where id = $3", TRAINING, modelTypeId, model.Id) if err != nil { fmt.Println("Failed to update model status") fmt.Println(err) // TODO improve this response return c.Error500(err) } return c.SendJSON(model.Id) }) handle.Post("/model/train/retrain", handleRetrain) handle.Get("/model/epoch/update", func(c *Context) *Error { f := c.R.URL.Query() accuracy := 0.0 if !CheckId(f, "model_id") || !CheckId(f, "definition") || CheckEmpty(f, "epoch") || !CheckFloat64(f, "accuracy", &accuracy) { return c.JsonBadRequest("Invalid: model_id or definition or epoch or accuracy") } accuracy = accuracy * 100 model_id := f.Get("model_id") def_id := f.Get("definition") epoch, err := strconv.Atoi(f.Get("epoch")) if err != nil { return c.JsonBadRequest("Epoch is not a number") } rows, err := c.Db.Query("select md.status from model_definition as md where md.model_id=$1 and md.id=$2", model_id, def_id) if err != nil { return c.Error500(err) } defer rows.Close() if !rows.Next() { c.Logger.Error("Could not get status of model definition") return c.Error500(nil) } var status int err = rows.Scan(&status) if err != nil { return c.Error500(err) } if status != 3 { c.Logger.Warn("Definition not on status 3(training)", "status", status) return c.JsonBadRequest("Definition not on status 3(training)") } c.Logger.Info("Updated model_definition!", "model", model_id, "progress", epoch, "accuracy", accuracy) _, err = c.Db.Exec("update model_definition set epoch_progress=$1, accuracy=$2 where id=$3", epoch, accuracy, def_id) if err != nil { return c.Error500(err) } return nil }) handle.Get("/model/head/epoch/update", func(c *Context) *Error { f := c.R.URL.Query() accuracy := 0.0 if !CheckId(f, "head_id") || CheckEmpty(f, "epoch") || !CheckFloat64(f, "accuracy", &accuracy) { return c.JsonBadRequest("Invalid: model_id or definition or epoch or accuracy") } accuracy = accuracy * 100 head_id := f.Get("head_id") epoch, err := strconv.Atoi(f.Get("epoch")) if err != nil { return c.JsonBadRequest("Epoch is not a number") } rows, err := c.Db.Query("select hd.status from exp_model_head as hd where hd.id=$1;", head_id) if err != nil { return c.Error500(err) } defer rows.Close() if !rows.Next() { c.Logger.Error("Could not get status of model head") return c.Error500(nil) } var status int err = rows.Scan(&status) if err != nil { return c.Error500(err) } if status != 3 { c.Logger.Warn("Head not on status 3(training)", "status", status) return c.JsonBadRequest("Head not on status 3(training)") } c.Logger.Info("Updated model_head!", "head", head_id, "progress", epoch, "accuracy", accuracy) _, err = c.Db.Exec("update exp_model_head set epoch_progress=$1, accuracy=$2 where id=$3", epoch, accuracy, head_id) if err != nil { return c.Error500(err) } return nil }) }